1
|
Zobeiri A, Rezaee A, Hajati F, Argha A, Alinejad-Rokny H. Post-Cardiac arrest outcome prediction using machine learning: A systematic review and meta-analysis. Int J Med Inform 2025; 193:105659. [PMID: 39481177 DOI: 10.1016/j.ijmedinf.2024.105659] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2024] [Revised: 10/16/2024] [Accepted: 10/18/2024] [Indexed: 11/02/2024]
Abstract
BACKGROUND Early and reliable prognostication in post-cardiac arrest patients remains challenging, with various factors linked to return of spontaneous circulation (ROSC), survival, and neurological results. Machine learning and deep learning models show promise in improving these predictions. This systematic review and meta-analysis evaluates how effective these approaches are in predicting clinical outcomes at different time points using structured data. METHODS This study followed PRISMA guidelines, involving a comprehensive search across PubMed, Scopus, and Web of Science databases until March 2024. Studies aimed at predicting ROSC, survival (or mortality), and neurological outcomes after cardiac arrest through the application of machine learning or deep learning techniques with structured data were included. Data extraction followed the guidelines of the CHARMS checklist, and the bias risk was evaluated using PROBAST tool. Models reporting the AUC metric with 95 % confidence intervals were incorporated into the quantitative synthesis and meta-analysis. RESULTS After extracting 2,753 initial records, 41 studies met the inclusion criteria, yielding 97 machine learning and 16 deep learning models. The pooled AUC for predicting favorable neurological outcomes (CPC 1 or 2) at hospital discharge was 0.871 (95 % CI: 0.813 - 0.928) for machine learning models and 0.877 (95 % CI: 0.831-0.924) across deep learning algorithms. For survival prediction, this value was found to be 0.837 (95 % CI: 0.757-0.916). Considerable heterogeneity and high risk of bias were observed, mainly attributable to inadequate management of missing data and the absence of calibration plots. Most studies focused on pre-hospital factors, with age, sex, and initial arrest rhythm being the most frequent features. CONCLUSION Predictive models utilizing AI-based approaches, including machine and deep learning models exhibit enhanced effectiveness compared to previous regression algorithms, but significant heterogeneity and high risk of bias limit their dependability. Evaluating state-of-the-art deep learning models tailored for tabular data and their clinical generalizability can enhance outcome prediction after cardiac arrest.
Collapse
Affiliation(s)
- Amirhosein Zobeiri
- Department of Mechatronics, School of Intelligent Systems, College of Interdisciplinary Science and Technology, University of Tehran, Tehran, Iran
| | - Alireza Rezaee
- Department of Mechatronics, School of Intelligent Systems, College of Interdisciplinary Science and Technology, University of Tehran, Tehran, Iran
| | - Farshid Hajati
- School of Science and Technology, Faculty of Science, Agriculture, Business and Law, University of New England, Armidale, NSW 2350, Australia.
| | - Ahmadreza Argha
- School of Biomedical Engineering, UNSW Sydney, Randwick, NSW 2052, Australia
| | - Hamid Alinejad-Rokny
- BioMedical Machine Learning Lab, School of Biomedical Engineering, UNSW Sydney, Randwick, NSW 2052, Australia
| |
Collapse
|
2
|
Lee S, Lee KS, Park SH, Lee SW, Kim SJ. A Machine Learning-Based Decision Support System for the Prognostication of Neurological Outcomes in Successfully Resuscitated Out-of-Hospital Cardiac Arrest Patients. J Clin Med 2024; 13:7600. [PMID: 39768524 PMCID: PMC11676625 DOI: 10.3390/jcm13247600] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2024] [Revised: 11/29/2024] [Accepted: 12/03/2024] [Indexed: 01/11/2025] Open
Abstract
Background/Objectives: This study uses machine learning and multicenter registry data for analyzing the determinants of a favorable neurological outcome in patients with out-of-hospital cardiac arrest (OHCA) and developing decision support systems for various subgroups. Methods: The data came from the Korean Cardiac Arrest Research Consortium registry, with 2679 patients who underwent OHCA aged 18 or above with the return of spontaneous circulation (ROSC). The dependent variable was a favorable neurological outcome (Cerebral Performance Category score 1-2), and 68 independent variables were included, e.g., first monitored rhythm, in-hospital cardiopulmonary resuscitation (CPR) duration and post-ROSC pH. A random forest was used for identifying the major determinants of the favorable neurological outcome and developing decision support systems for the various subgroups stratified by the major variables. Results: Based on the random forest variable importance, the major determinants of the OHCA patient outcomes were the in-hospital CPR duration (0.0824), in-hospital electrocardiogram on emergency room arrival (0.0692), post-ROSC pH (0.0579), prehospital ROSC before emergency room arrival (0.0565), coronary angiography (0.0527), age (0.0415), first monitored rhythm (EMS) (0.0402), first monitored rhythm (community) (0.0401), early coronary angiography within 24 h (0.0304) and time from scene arrival to CPR stop (0.0301). It was also found that the patients could be divided into six subgroups in terms of their prehospital ROSC and first monitored rhythm (EMS), and that a decision tree could be developed as a decision support system for each subgroup to find the effective cut-off points regarding the in-hospital CPR duration, post-ROSC pH, age and hemoglobin. Conclusions: We identified the major determinants of favorable neurological outcomes in successfully resuscitated patients who underwent OHCA using machine learning. This study demonstrates the strengths of a random forest as an effective decision support system for each stratified subgroup (prehospital ROSC and first monitored rhythm by EMS) to find its own optimal cut-off points for the major in-hospital variables (in-hospital CPR duration, post-ROSC pH, age and hemoglobin).
Collapse
Affiliation(s)
- Sijin Lee
- Department of Emergency Medicine, Korea University Anam Hospital, Seoul 02841, Republic of Korea; (S.L.); (S.W.L.)
| | - Kwang-Sig Lee
- AI Center, Korea University College of Medicine, Seoul 02841, Republic of Korea;
| | - Sang-Hyun Park
- Biomedical Research Institute, Korea University College of Medicine, Seoul 02841, Republic of Korea;
| | - Sung Woo Lee
- Department of Emergency Medicine, Korea University Anam Hospital, Seoul 02841, Republic of Korea; (S.L.); (S.W.L.)
| | - Su Jin Kim
- Department of Emergency Medicine, Korea University Anam Hospital, Seoul 02841, Republic of Korea; (S.L.); (S.W.L.)
| |
Collapse
|
3
|
Ni P, Zhang S, Hu W, Diao M. Application of multi-feature-based machine learning models to predict neurological outcomes of cardiac arrest. Resusc Plus 2024; 20:100829. [PMID: 39639943 PMCID: PMC11617783 DOI: 10.1016/j.resplu.2024.100829] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2024] [Revised: 11/01/2024] [Accepted: 11/12/2024] [Indexed: 12/07/2024] Open
Abstract
Cardiac arrest (CA) is a major disease burden worldwide and has a poor prognosis. Early prediction of CA outcomes helps optimize the therapeutic regimen and improve patients' neurological function. As the current guidelines recommend, many factors can be used to evaluate the neurological outcomes of CA patients. Machine learning (ML) has strong analytical abilities and fast computing speed; thus, it plays an irreplaceable role in prediction model development. An increasing number of researchers are using ML algorithms to incorporate demographics, arrest characteristics, clinical variables, biomarkers, physical examination findings, electroencephalograms, imaging, and other factors with predictive value to construct multi-feature prediction models for neurological outcomes of CA survivors. In this review, we explore the current application of ML models using multiple features to predict the neurological outcomes of CA patients. Although the outcome prediction model is still in development, it has strong potential to become a powerful tool in clinical practice.
Collapse
Affiliation(s)
- Peifeng Ni
- Department of Critical Care Medicine, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310000, China
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, Hangzhou, Zhejiang 310000, China
| | - Sheng Zhang
- Department of Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200000, China
| | - Wei Hu
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, Hangzhou, Zhejiang 310000, China
| | - Mengyuan Diao
- Department of Critical Care Medicine, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310000, China
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, Hangzhou, Zhejiang 310000, China
| |
Collapse
|
4
|
Soleimanian M, Bijani M, Nikrouz L, Naghizadeh MM, Ranjbar K, Heidari G. A timeliness analysis of emergency services and cardiovascular outcomes in cardiac patients referred through prehospital emergency services between 2020 and 2023: a cross-sectional study in Iran. BMC Res Notes 2024; 17:250. [PMID: 39237991 PMCID: PMC11378617 DOI: 10.1186/s13104-024-06922-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2024] [Accepted: 08/28/2024] [Indexed: 09/07/2024] Open
Abstract
OBJECTIVE Effective time management is crucial for the survival of all patients, particularly those with cardiovascular conditions. This is especially true in the context of pre-hospital emergency services, where prompt intervention can significantly impact outcomes. This study delves into the timeliness of emergency services and the subsequent outcomes for hospitalized cardiovascular patients in EMS center in Fasa University of Medical Sciences, southern Iran. RESULTS A total of 4972 emergency calls related to cardiac diagnoses were received between 2020 and 2023. The transport time was significantly correlated with age, location of the mission, and type of mission. Of the total, 86 underwent angioplasty within the standard time of less than 90 min, of which 81 were discharged and 5 died. 51 patients underwent angioplasty after more than 90 min, of which 47 were discharged and 4 died. In addition, 124 of these patients experienced cardiopulmonary resuscitation, of which 63 were successful and 61 were unsuccessful.
Collapse
Affiliation(s)
- Mohammad Soleimanian
- Student Research Committee, School of Nursing, Fasa University of Medical Sciences, Fasa, Iran
| | - Mostafa Bijani
- Department of Medical Surgical Nursing, School of Nursing, Fasa University of Medical Sciences, Fasa, Iran.
| | - Leila Nikrouz
- Department of Medical Surgical Nursing, School of Nursing, Fasa University of Medical Sciences, Fasa, Iran.
| | | | - Kamran Ranjbar
- Department of Medical Surgical Nursing, School of Nursing, Fasa University of Medical Sciences, Fasa, Iran
| | - Gholamali Heidari
- Department of Medical Surgical Nursing, School of Nursing, Fasa University of Medical Sciences, Fasa, Iran
| |
Collapse
|
5
|
Higgins S, Dlamini S, Hattingh M, Rambharose S, Theron E, Stassen W. Views and perceptions of advanced life support practitioners on initiating, withholding and terminating resuscitation in out-of-hospital cardiac arrest in the Emergency Medical Services of South Africa. Resusc Plus 2024; 19:100709. [PMID: 39104446 PMCID: PMC11298628 DOI: 10.1016/j.resplu.2024.100709] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2024] [Revised: 06/25/2024] [Accepted: 06/26/2024] [Indexed: 08/07/2024] Open
Abstract
Introduction This study aimed to explore the views and perceptions of Advanced Life Support (ALS) practitioners in two South African provinces on initiating, withholding, and terminating resuscitation in OHCA. Methodology Semi-structured one-on-one interviews were conducted with operational ALS practitioners working within the prehospital setting in the Western Cape and Free State provinces. Recorded interviews were transcribed and subjected to inductive-dominant, manifest content analysis. After familiarisation with the data, meaning units were condensed, codes were applied and collated into categories that were then assessed, reviewed, and refined repeatedly. Results A total of 18 ALS providers were interviewed. Five main categories were developed from the data analysis: 1) assessment of prognosis, 2) internal factors affecting decision-making, 3) external factors affecting decision-making, 4) system challenges, and 5) ideas for improvement. Factors influencing the assessment of prognosis were history, clinical presentation, and response to resuscitation. Internal factors affecting decision-making were driven by emotion and contemplation. External factors affecting decision-making included family, safety, and disposition. System challenges relating to bystander response and resources were identified. Ideas for improvement in training and support were brought forward. Conclusion Many factors influence OHCA decision-making in the Western Cape and Free State provinces, and numerous system challenges have been identified. The findings of this study can be used as a frame of reference for prehospital emergency care personnel and contribute to the development of context-specific guidelines.
Collapse
Affiliation(s)
- S. Higgins
- Division of Emergency Medicine, University of Cape Town, Cape Town, South Africa
| | - S. Dlamini
- Division of Emergency Medicine, University of Cape Town, Cape Town, South Africa
| | - M. Hattingh
- School of Nursing, University of the Free State, Bloemfontein, South Africa
| | - S. Rambharose
- Department of Physiological Sciences, Stellenbosch University, Stellenbosch, South Africa
| | - E. Theron
- Division of Emergency Medicine, University of Cape Town, Cape Town, South Africa
| | - W. Stassen
- Division of Emergency Medicine, University of Cape Town, Cape Town, South Africa
| |
Collapse
|
6
|
Majewski D, Ball S, Talikowska M, Belcher J, Brits R, Finn J. Do differences in emergency medical services (EMS) response time to an arrest account for the survival differences between EMS-witnessed and bystander-witnessed out of hospital cardiac arrest? Resusc Plus 2024; 19:100696. [PMID: 39035408 PMCID: PMC11259960 DOI: 10.1016/j.resplu.2024.100696] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2024] [Revised: 06/10/2024] [Accepted: 06/11/2024] [Indexed: 07/23/2024] Open
Abstract
Introduction Out-of-hospital cardiac arrests (OHCA) witnessed by Emergency Medical Services (EMS) are reported to have more favourable survival than bystander-witnessed arrests, even after adjusting for patient and arrest factors known to be associated with increased OHCA survival. This study aims to determine whether the survival advantage in EMS-witnessed arrests can be attributed to differences in the EMS response time to the arrest. Methods Using registry data we conducted a retrospective, population-based cohort study of bystander- and EMS-witnessed OHCAs of medical aetiology who received an EMS resuscitation attempt in Western Australia between 2018-2021. EMS response time to arrest was assumed to be zero for EMS-witnessed arrests. Multivariable logistic regression was used to compare 30-day OHCA survival by witness and bystander CPR (B-CPR) status, adjusting for EMS response time to arrest, and patient and arrest characteristics. Results Of 2,130 OHCA cases, 510 (23.9%) were EMS-witnessed and 1620 were bystander-witnessed: 1318/1620 (81.4%) with B-CPR, and 302/1620 (18.6%) with no B-CPR. The median EMS response time to bystander-witnessed arrests who received B-CPR was 9.9 [Q1,Q3: 7.4, 13.3] minutes. After adjusting for the EMS response time and patient and arrest factors, 30-day survival remained significantly lower in both the bystander-witnessed group with B-CPR (aOR 0.56; 95% CI 0.34 - 0.91) and bystander-witnessed group without B-CPR (aOR 0.23; 95% CI 0.11 - 0.46). Conclusion An increased EMS response time does not fully account for the higher OHCA survival in EMS-witnessed arrests compared to bystander-witnessed arrests.
Collapse
Affiliation(s)
- David Majewski
- Prehospital, Resuscitation and Emergency Care Research Unit (PRECRU), Curtin School of Nursing, Curtin University, Bentley, Western Australia, Australia
| | - Stephen Ball
- Prehospital, Resuscitation and Emergency Care Research Unit (PRECRU), Curtin School of Nursing, Curtin University, Bentley, Western Australia, Australia
- St John WA, Belmont, Western Australia, Australia
| | - Milena Talikowska
- Prehospital, Resuscitation and Emergency Care Research Unit (PRECRU), Curtin School of Nursing, Curtin University, Bentley, Western Australia, Australia
| | - Jason Belcher
- Prehospital, Resuscitation and Emergency Care Research Unit (PRECRU), Curtin School of Nursing, Curtin University, Bentley, Western Australia, Australia
- St John WA, Belmont, Western Australia, Australia
| | | | - Judith Finn
- Prehospital, Resuscitation and Emergency Care Research Unit (PRECRU), Curtin School of Nursing, Curtin University, Bentley, Western Australia, Australia
- St John WA, Belmont, Western Australia, Australia
- Medical School (Emergency Medicine), The University of Western Australia, Nedlands, Western Australia, Australia
- School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia
| |
Collapse
|
7
|
Matta A, Philippe J, Nader V, Levai L, Moussallem N, Kazzi AA, Ohlmann P. Predictors and rate of survival after Out-of-Hospital Cardiac Arrest. Curr Probl Cardiol 2024; 49:102719. [PMID: 38908728 DOI: 10.1016/j.cpcardiol.2024.102719] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2024] [Accepted: 06/19/2024] [Indexed: 06/24/2024]
Abstract
BACKGROUND Out-of-hospital cardiac arrest (OHCA) is a major public health concern and encloses a wide spectrum of causes. The purpose of this study is to assess predictors and rate of survival at hospital discharge and long-term in the setting of OHCA. The secondary endpoint is to compare OHCA-survival outcomes of presumed ischemic versus non ischemic cause. METHODS A retrospective cohort was conducted on 318 consecutive patients admitted for OHCA at Civilian Hospitals of Colmar between 2010 and 2019. Data concerning baseline characteristics, EKG, biological parameters, and coronary angiograms were collected. We observed the living status (alive or dead) of each of study's participants by March 2023. RESULTS The observed survival rate was 34.3 % at hospital discharge and 26.7 % at 7.1-year follow up. The mean age of study population was 63 ± 16 years and 32.7 % were women. 65.7 % of OHCA-patients underwent coronary angiography that revealed a significant coronary artery disease (CAD) in half of study participants. Primary angioplasty was performed in 43.4 % of study population. The in-hospital mortality rate was significantly higher in those with RBBB (83.7 % vs. 62.5 %, p = 0.004), diabetes mellitus (84.2 % vs. 59.9 %, p < 0.001), arterial hypertension (72.2 % vs. 57.7 %, p = 0.007), peripheral arterial disease (79.2 % vs. 52.2 %, p = 0.031) whereas it was lower in case of anterior STEMI (43.9 % vs 71.4 %, p < 0.001), presence of obstructive CAD (52.2 % vs. 79.2 %, p < 0.001), primary angioplasty performance (48.6 % vs. 78.9 %, p < 0.001), initial shockable rhythm (43.8 % vs. 88.6 %, p < 0.001), initial chest pain (49.4 % vs. 71.5 %, p < 0.001). After adjusting on covariates, the Cox model only identified an initial shockable rhythm as independent predictor of survival at hospital discharge [HR = 0.185, 95 %CI (0.085-0.404), p < 0.001] and 7-year follow up [HR = 0.201, 95 %CI (0.082-0.492), p < 0.001]. The Kaplan-Meier and log Rank test showed a difference in survival outcomes between OHCA with versus without CAD (p < 0.001). CONCLUSION The proportion of OHCA-survivors is small despite the development of emergency health care system. Initial shockable rhythm is the strong predictor of survival. OHCA of presumed coronary cause is associated with a better long-term survival outcome.
Collapse
Affiliation(s)
- Anthony Matta
- Department of cardiology, Civilian Hospitals of Colmar, Colmar, France; School of medicine and medical sciences, Holy Spirit University of Kaslik, P.O.Box 446, Jounieh, Lebanon.
| | - John Philippe
- Department of cardiology, Civilian Hospitals of Colmar, Colmar, France
| | - Vanessa Nader
- Department of cardiology, Civilian Hospitals of Colmar, Colmar, France
| | - Laszlo Levai
- Department of cardiology, Civilian Hospitals of Colmar, Colmar, France
| | - Nicolas Moussallem
- School of medicine and medical sciences, Holy Spirit University of Kaslik, P.O.Box 446, Jounieh, Lebanon
| | - Amin A Kazzi
- Department of Emergency Medicine, American University of Beirut Medical Center, Beirut, Lebanon
| | - Patrick Ohlmann
- Department of cardiology, Strasbourg University Hospital, Strasbourg, France
| |
Collapse
|
8
|
Ning Y, Li S, Ng YY, Chia MYC, Gan HN, Tiah L, Mao DR, Ng WM, Leong BSH, Doctor N, Ong MEH, Liu N. Variable importance analysis with interpretable machine learning for fair risk prediction. PLOS DIGITAL HEALTH 2024; 3:e0000542. [PMID: 38995879 PMCID: PMC11244764 DOI: 10.1371/journal.pdig.0000542] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/09/2023] [Accepted: 06/01/2024] [Indexed: 07/14/2024]
Abstract
Machine learning (ML) methods are increasingly used to assess variable importance, but such black box models lack stability when limited in sample sizes, and do not formally indicate non-important factors. The Shapley variable importance cloud (ShapleyVIC) addresses these limitations by assessing variable importance from an ensemble of regression models, which enhances robustness while maintaining interpretability, and estimates uncertainty of overall importance to formally test its significance. In a clinical study, ShapleyVIC reasonably identified important variables when the random forest and XGBoost failed to, and generally reproduced the findings from smaller subsamples (n = 2500 and 500) when statistical power of the logistic regression became attenuated. Moreover, ShapleyVIC reasonably estimated non-significant importance of race to justify its exclusion from the final prediction model, as opposed to the race-dependent model from the conventional stepwise model building. Hence, ShapleyVIC is robust and interpretable for variable importance assessment, with potential contribution to fairer clinical risk prediction.
Collapse
Affiliation(s)
- Yilin Ning
- Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore
| | - Siqi Li
- Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore
| | - Yih Yng Ng
- Digital and Smart Health Office, Ng Teng Fong Centre for Healthcare Innovation, Singapore, Singapore
- Department of Preventive and Population Medicine, Tan Tock Seng Hospital, Singapore, Singapore
| | | | - Han Nee Gan
- Accident & Emergency, Changi General Hospital, Singapore, Singapore
| | - Ling Tiah
- Accident & Emergency, Changi General Hospital, Singapore, Singapore
| | - Desmond Renhao Mao
- Department of Acute and Emergency Care, Khoo Teck Puat Hospital, Singapore, Singapore
| | - Wei Ming Ng
- Emergency Medicine Department, Ng Teng Fong General Hospital, Singapore, Singapore
| | | | - Nausheen Doctor
- Department of Emergency Medicine, Sengkang General Hospital, Singapore, Singapore
| | - Marcus Eng Hock Ong
- Programme in Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
- Department of Emergency Medicine, Singapore General Hospital, Singapore, Singapore
- Health Services Research Centre, Singapore Health Services, Singapore, Singapore
| | - Nan Liu
- Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore
- Programme in Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
- Institute of Data Science, National University of Singapore, Singapore, Singapore
| |
Collapse
|
9
|
Grubic N, Hill B, Allan KS, Maximova K, Banack HR, Del Rios M, Johri AM. Mediators of the Association Between Socioeconomic Status and Survival After Out-of-Hospital Cardiac Arrest: A Systematic Review. Can J Cardiol 2024; 40:1088-1101. [PMID: 38211888 DOI: 10.1016/j.cjca.2024.01.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2023] [Revised: 12/21/2023] [Accepted: 01/01/2024] [Indexed: 01/13/2024] Open
Abstract
Low socioeconomic status (SES) is associated with poor outcomes after out-of-hospital cardiac arrest (OHCA). Patient characteristics, care processes, and other contextual factors may mediate the association between SES and survival after OHCA. Interventions that target these mediating factors may reduce disparities in OHCA outcomes across the socioeconomic spectrum. This systematic review identified and quantified mediators of the SES-survival after OHCA association. Electronic databases (MEDLINE, Embase, PubMed, Web of Science) and grey literature sources were searched from inception to July or August 2023. Observational studies of OHCA patients that conducted mediation analyses to evaluate potential mediators of the association between SES (defined by income, education, occupation, or a composite index) and survival outcomes were included. A total of 10 studies were included in this review. Income (n = 9), education (n = 4), occupation (n = 1), and composite indices (n = 1) were used to define SES. The proportion of OHCA cases that had bystander involvement, presented with an initial shockable rhythm, and survived to hospital discharge or 30 days increased with higher SES. Common mediators of the SES-survival association that were evaluated included initial rhythm (n = 6), emergency medical services response time (n = 5), and bystander cardiopulmonary resuscitation (n = 4). Initial rhythm was the most important mediator of this association, with a median percent excess risk explained of 37.4% (range 28.6%-40.0%; n = 5; 1 study reported no mediation) and mediation proportion of 41.8% (n = 1). To mitigate socioeconomic disparities in outcomes after OHCA, interventions should target potentially modifiable mediators, such as initial rhythm, which may involve improving bystander awareness of OHCA and the need for prompt resuscitation.
Collapse
Affiliation(s)
- Nicholas Grubic
- Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada; Department of Medicine, Queen's University, Kingston, Ontario, Canada.
| | - Braeden Hill
- Department of Medicine, Queen's University, Kingston, Ontario, Canada
| | - Katherine S Allan
- Division of Cardiology, St Michael's Hospital, Toronto, Ontario, Canada
| | - Katerina Maximova
- Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada; MAP Centre for Urban Health Solutions, St Michael's Hospital, Toronto, Ontario, Canada
| | - Hailey R Banack
- Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada
| | - Marina Del Rios
- Carver College of Medicine, University of Iowa, Iowa City, Iowa, United States
| | - Amer M Johri
- Department of Medicine, Queen's University, Kingston, Ontario, Canada
| |
Collapse
|
10
|
Meilandt C, Qvortrup M, Bøtker MT, Folke F, Borup L, Christensen HC, Milling L, Lauridsen KG, Løfgren B. Association Between Defibrillation Using LIFEPAK 15 or ZOLL X Series and Survival Outcomes in Out-of-Hospital Cardiac Arrest: A Nationwide Cohort Study. J Am Heart Assoc 2024; 13:e033913. [PMID: 38533945 PMCID: PMC11179748 DOI: 10.1161/jaha.123.033913] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Accepted: 03/05/2024] [Indexed: 03/28/2024]
Abstract
BACKGROUND Defibrillation is essential for achieving return of spontaneous circulation (ROSC) following out-of-hospital cardiac arrest (OHCA) with shockable rhythms. This study aimed to investigate if the type of defibrillator used was associated with ROSC in OHCA. METHODS AND RESULTS This study included adult patients with OHCA from the Danish Cardiac Arrest Registry from 2016 to 2021 with at least 1 defibrillation by the emergency medical services. We used multivariable logistic regression and a difference-in-difference analysis, including all patients with or without emergency medical services shock to assess the causal inference of using the different defibrillator models (LIFEPAK or ZOLL) for OHCA defibrillation. Among 6516 patients, 77% were male, the median age (quartile 1; quartile 3) was 70 (59; 79), and 57% achieved ROSC. In total, 5514 patients (85%) were defibrillated using LIFEPAK (ROSC: 56%) and 1002 patients (15%) were defibrillated using ZOLL (ROSC: 63%). Patients defibrillated using ZOLL had an increased adjusted odds ratio (aOR) for ROSC compared with LIFEPAK (aOR, 1.22 [95% CI, 1.04-1.43]). There was no significant difference in 30-day mortality (aOR, 1.11 [95% CI, 0.95-1.30]). Patients without emergency medical services defibrillation, but treated by ZOLL-equipped emergency medical services, had a nonsignificant aOR for ROSC compared with LIFEPAK (aOR, 1.10 [95% CI, 0.99-1.23]) and the difference-in-difference analysis was not statistically significant (OR, 1.10 [95% CI, 0.91-1.34]). CONCLUSIONS Defibrillation using ZOLL X Series was associated with increased odds for ROSC compared with defibrillation using LIFEPAK 15 for patients with OHCA. However, a difference-in-difference analysis suggested that other factors may be responsible for the observed association.
Collapse
Affiliation(s)
- Carsten Meilandt
- Prehospital Emergency Medical Services, Central Denmark RegionAarhusDenmark
- Department of Research and DevelopmentPrehospital Emergency Medical Services, Central Denmark RegionAarhusDenmark
| | - Mette Qvortrup
- Department of CardiologyViborg Regional HospitalViborgDenmark
| | - Morten Thingemann Bøtker
- Prehospital Emergency Medical Services, Central Denmark RegionAarhusDenmark
- Department of Research and DevelopmentPrehospital Emergency Medical Services, Central Denmark RegionAarhusDenmark
| | - Fredrik Folke
- Copenhagen Emergency Medical Services, Capital Region of DenmarkCopenhagenDenmark
- Department of CardiologyHerlev Gentofte University HospitalHerlevDenmark
- Department of Clinical MedicineUniversity of CopenhagenCopenhagenDenmark
| | - Lars Borup
- Prehospital Emergency Medical Services, North Denmark RegionAalborgDenmark
| | | | - Louise Milling
- The Prehospital Research Unit, Region of Southern DenmarkOdenseDenmark
- Department of Regional Health ResearchUniversity of Southern DenmarkOdenseDenmark
| | - Kasper G. Lauridsen
- Research Center for Emergency MedicineAarhus UniversityAarhusDenmark
- Department of MedicineRanders Regional HospitalRandersDenmark
- Department of Clinical MedicineAarhus UniversityAarhusDenmark
| | - Bo Løfgren
- Research Center for Emergency MedicineAarhus UniversityAarhusDenmark
- Department of MedicineRanders Regional HospitalRandersDenmark
| |
Collapse
|
11
|
Tanaka C, Tagami T, Nakayama F, Kuno M, Kitamura N, Yasunaga H, Aso S, Takeda M, Unemoto K. Changes Over 7 Years in Temperature Control Treatment and Outcomes After Out-of-Hospital Cardiac Arrest: A Japanese, Multicenter Cohort Study. Ther Hypothermia Temp Manag 2024. [PMID: 38386985 DOI: 10.1089/ther.2023.0087] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/24/2024] Open
Abstract
Temperature control is the only neuroprotective intervention suggested in current international guidelines for patients with return of spontaneous circulation after cardiac arrest, but the prevalence of temperature control therapy, temperature settings, and outcomes have not been clearly reported. We aimed to investigate changes over 7 years in provision of temperature control treatment among out-of-hospital cardiac arrest (OHCA) patients in Kanto region, Japan. Data of all adult OHCA patients who survived for more than 24 hours in the prospective cohort studies, SOS-KANTO 2012 (conducted from 2012 to 2013) and SOS-KANTO 2017 (conducted from 2019 to 2021), in Japan were included. We compared the prevalence of temperature control and the proportion of mild (≥35°C) and moderate (from 32°C to 34.9°C) hypothermia between the two study groups. We also performed a Cox regression analysis to evaluate 30-day mortality adjusted by temperature control therapy (none, moderate hypothermia, or mild hypothermia), age, sex, past medical history, witnessed status, bystander cardiopulmonary resuscitation, initial rhythm, location of arrest, and dataset (SOS-KANTO 2012 or 2017). We analyzed data from 2936 patients (n = 1710, SOS-KANTO 2012; n = 1226, SOS-KANTO 2017). Use of temperature control was lower (45.3% vs. 41.4%, p = 0.04), moderate hypothermia was lower (p < 0.01), and mild hypothermia was higher (p < 0.01) in SOS-KANTO 2017 compared with SOS-KANTO 2012. The survival rate was significantly higher for patients with mild (p < 0.01) and moderate (p < 0.01) hypothermia compared with those who did not receive temperature control therapy. Overall, the incidence of moderate hypothermia decreased and that of mild hypothermia increased and the use of temperature control decreased between the two studies conducted 7 years apart in the Kanto area, Japan. Temperature control management might improve survival of patients with OHCA.
Collapse
Affiliation(s)
- Chie Tanaka
- Department of Emergency and Critical Care Medicine, Nippon Medical School Tama Nagayama Hospital, Tama-shi, Japan
| | - Takashi Tagami
- Department of Emergency and Critical Care Medicine, Nippon Medical School Musashikosugi Hospital, Kawasaki, Japan
- Department of Clinical Epidemiology and Health Economics, School of Public Health, The University of Tokyo, Bunkyo, Japan
| | - Fumihiko Nakayama
- Department of Emergency and Critical Care Medicine, Nippon Medical School Tama Nagayama Hospital, Tama-shi, Japan
| | - Masamune Kuno
- Department of Emergency and Critical Care Medicine, Nippon Medical School Tama Nagayama Hospital, Tama-shi, Japan
| | - Nobuya Kitamura
- Department of Emergency and Critical Care Medicine, Kimitsu Chuo Hospital, Chiba, Japan
| | - Hideo Yasunaga
- Department of Clinical Epidemiology and Health Economics, School of Public Health, The University of Tokyo, Bunkyo, Japan
| | - Shotaro Aso
- Department of Real-World Evidence, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Munekazu Takeda
- Department of Critical Care and Emergency Medicine, Tokyo Women's Medical University, Tokyo, Japan
| | - Kyoko Unemoto
- Department of Emergency and Critical Care Medicine, Nippon Medical School Tama Nagayama Hospital, Tama-shi, Japan
| |
Collapse
|
12
|
Tanaka C, Tagami T, Kaneko J, Kitamura N, Yasunaga H, Aso S, Takeda M, Kuno M. Impact of the COVID-19 pandemic on prehospital and in-hospital treatment and outcomes of patients after out-of-hospital cardiac arrest: a Japanese multicenter cohort study. BMC Emerg Med 2024; 24:12. [PMID: 38191311 PMCID: PMC10775511 DOI: 10.1186/s12873-024-00929-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2023] [Accepted: 01/02/2024] [Indexed: 01/10/2024] Open
Abstract
BACKGROUND In the chain of survival for Out-of-hospital cardiac arrest (OHCA), each component of care contributes to improve the prognosis of the patient with OHCA. The SARS-CoV-2 (COVID-19) pandemic potentially affected each part of care in the chain of survival. The aim of this study was to compare prehospital care, in-hospital treatment, and outcomes among OHCA patients before and after the COVID-19 pandemic. METHODS We analyzed data from a multicenter prospective study in Kanto area, Japan, named SOS-KANTO 2017. We enrolled patients who registered during the pre-pandemic period (September 2019 to December 2019) and the post-pandemic period (June 2020 to March 2021). The main outcome measures were 30-day mortality and the proportion of favorable outcomes at 1 month, and secondary outcome measures were changes in prehospital and in-hospital treatments between the pre- and post-pandemic periods. RESULTS There were 2015 patients in the pre-pandemic group, and 5023 in the post-pandemic group. The proportion of advanced airway management by emergency medical service (EMS) increased (p < 0.01), and EMS call-to-hospital time was prolonged (p < 0.01) in the post- versus pre-pandemic group. There were no differences between the groups in defibrillation, extracorporeal membrane oxygenation, or temperature control therapy (p = 0.43, p = 0.14, and p = 0.16, respectively). Survival rate at 1 month and favorable outcome rate at 1 month were lower (p = 0.01 and p < 0.01, respectively) in the post- versus pre-pandemic group. CONCLUSION Survival rate and favorable outcome rate 1 month after return of spontaneous circulation of OHCA worsened, EMS response time was prolonged, and advanced airway management by EMS increased in the post- versus pre-pandemic group; however, most prehospital and in-hospital management did not change between pre- and post-COVID-19 pandemic.
Collapse
Affiliation(s)
- Chie Tanaka
- Department of Emergency and Critical Care Medicine, Nippon Medical School Tama Nagayama Hospital, Tama-shi, Tokyo, 2068512, Japan
| | - Takashi Tagami
- Department of Emergency and Critical Care Medicine, Nippon Medical School Musashikosugi Hospital, 1-396 Kosugimachi, Nakahara-ku, Kawasaki, Kanagawa, 211-8533, Japan.
- Department of Clinical Epidemiology and Health Economics, School of Public Health, The University of Tokyo, Bunkyo, Tokyo, 1138654, Japan.
| | - Junya Kaneko
- Department of Emergency and Critical Care Medicine, Nippon Medical School Tama Nagayama Hospital, Tama-shi, Tokyo, 2068512, Japan
| | - Nobuya Kitamura
- Department of Emergency and Critical Care Medicine, Kimitsu Chuo Hospital, Kimitsu, Chiba, 2928535, Japan
| | - Hideo Yasunaga
- Department of Clinical Epidemiology and Health Economics, School of Public Health, The University of Tokyo, Bunkyo, Tokyo, 1138654, Japan
| | - Shotaro Aso
- Department of Real-world Evidence, Graduate School of Medicine, The University of Tokyo, Tokyo, 1138654, Japan
| | - Munekazu Takeda
- Department of Critical Care and Emergency Medicine, Tokyo Women's Medical University, Tokyo, 1628666, Japan
| | - Masamune Kuno
- Department of Emergency and Critical Care Medicine, Nippon Medical School Tama Nagayama Hospital, Tama-shi, Tokyo, 2068512, Japan
| |
Collapse
|
13
|
Piliuk K, Tomforde S. Artificial intelligence in emergency medicine. A systematic literature review. Int J Med Inform 2023; 180:105274. [PMID: 37944275 DOI: 10.1016/j.ijmedinf.2023.105274] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2023] [Revised: 10/21/2023] [Accepted: 10/26/2023] [Indexed: 11/12/2023]
Abstract
Motivation and objective: Emergency medicine is becoming a popular application area for artificial intelligence methods but remains less investigated than other healthcare branches. The need for time-sensitive decision-making on the basis of high data volumes makes the use of quantitative technologies inevitable. However, the specifics of healthcare regulations impose strict requirements for such applications. Published contributions cover separate parts of emergency medicine and use disparate data and algorithms. This study aims to systematize the relevant contributions, investigate the main obstacles to artificial intelligence applications in emergency medicine, and propose directions for further studies. METHODS The contributions selection process was conducted with systematic electronic databases querying and filtering with respect to established exclusion criteria. Among the 380 papers gathered from IEEE Xplore, ACM Digital Library, Springer Library, ScienceDirect, and Nature databases 116 were considered to be a part of the survey. The main features of the selected papers are the focus on emergency medicine and the use of machine learning or deep learning algorithms. FINDINGS AND DISCUSSION The selected papers were classified into two branches: diagnostics-specific and triage-specific. The former ones are focused on either diagnosis prediction or decision support. The latter covers such applications as mortality, outcome, admission prediction, condition severity estimation, and urgent care prediction. The observed contributions are highly specialized within a single disease or medical operation and often use privately collected retrospective data, making them incomparable. These and other issues can be addressed by creating an end-to-end solution based on human-machine interaction. CONCLUSION Artificial intelligence applications are finding their place in emergency medicine, while most of the corresponding studies remain isolated and lack higher generalization and more sophisticated methodology, which can be a matter of forthcoming improvements.
Collapse
Affiliation(s)
| | - Sven Tomforde
- Christian-Albrechts-Universität zu Kiel, 24118 Kiel, Germany
| |
Collapse
|
14
|
Toy J, Bosson N, Schlesinger S, Gausche-Hill M, Stratton S. Artificial intelligence to support out-of-hospital cardiac arrest care: A scoping review. Resusc Plus 2023; 16:100491. [PMID: 37965243 PMCID: PMC10641545 DOI: 10.1016/j.resplu.2023.100491] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2023] [Revised: 09/23/2023] [Accepted: 10/11/2023] [Indexed: 11/16/2023] Open
Abstract
Background Artificial intelligence (AI) has demonstrated significant potential in supporting emergency medical services personnel during out-of-hospital cardiac arrest (OHCA) care; however, the extent of research evaluating this topic is unknown. This scoping review examines the breadth of literature on the application of AI in early OHCA care. Methods We conducted a search of PubMed®, Embase, and Web of Science in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews guidelines. Articles focused on non-traumatic OHCA and published prior to January 18th, 2023 were included. Studies were excluded if they did not use an AI intervention (including machine learning, deep learning, or natural language processing), or did not utilize data from the prehospital phase of care. Results Of 173 unique articles identified, 54 (31%) were included after screening. Of these studies, 15 (28%) were from the year 2022 and with an increasing trend annually starting in 2019. The majority were carried out by multinational collaborations (20/54, 38%) with additional studies from the United States (10/54, 19%), Korea (5/54, 10%), and Spain (3/54, 6%). Studies were classified into three major categories including ECG waveform classification and outcome prediction (24/54, 44%), early dispatch-level detection and outcome prediction (7/54, 13%), return of spontaneous circulation and survival outcome prediction (15/54, 20%), and other (9/54, 16%). All but one study had a retrospective design. Conclusions A small but growing body of literature exists describing the use of AI to augment early OHCA care.
Collapse
Affiliation(s)
- Jake Toy
- University of California Los Angeles, Fielding School of Public Health, 650 Charles E Young Drive South, Los Angeles, CA 90095, USA
- Harbor-UCLA Department of Emergency Medicine & The Lundquist Research Institute, 1000 W Carson Street, Torrance, CA 90502, USA
- Los Angeles County EMS Agency, 10100 Pioneer Blvd, Santa Fe Springs, CA 90670, USA
- David Geffen School of Medicine at UCLA, Department of Emergency Medicine, 10833 Le Conte Ave, Los Angeles, CA 90095, USA
| | - Nichole Bosson
- Harbor-UCLA Department of Emergency Medicine & The Lundquist Research Institute, 1000 W Carson Street, Torrance, CA 90502, USA
- Los Angeles County EMS Agency, 10100 Pioneer Blvd, Santa Fe Springs, CA 90670, USA
- David Geffen School of Medicine at UCLA, Department of Emergency Medicine, 10833 Le Conte Ave, Los Angeles, CA 90095, USA
| | - Shira Schlesinger
- Harbor-UCLA Department of Emergency Medicine & The Lundquist Research Institute, 1000 W Carson Street, Torrance, CA 90502, USA
- David Geffen School of Medicine at UCLA, Department of Emergency Medicine, 10833 Le Conte Ave, Los Angeles, CA 90095, USA
| | - Marianne Gausche-Hill
- Harbor-UCLA Department of Emergency Medicine & The Lundquist Research Institute, 1000 W Carson Street, Torrance, CA 90502, USA
- Los Angeles County EMS Agency, 10100 Pioneer Blvd, Santa Fe Springs, CA 90670, USA
- David Geffen School of Medicine at UCLA, Department of Emergency Medicine, 10833 Le Conte Ave, Los Angeles, CA 90095, USA
| | - Samuel Stratton
- University of California Los Angeles, Fielding School of Public Health, 650 Charles E Young Drive South, Los Angeles, CA 90095, USA
- Orange County California Emergency Medical Services Agency, 405 W. 5th Street, Santa Ana, CA 92705, USA
| |
Collapse
|
15
|
Lindqvist E, Hollenberg J, Ringh M, Nordberg P, Forsberg S. Out-of-hospital cardiac arrest caused by poisoning - a Swedish nationwide study over 15 years. Resuscitation 2023; 193:110012. [PMID: 39491087 DOI: 10.1016/j.resuscitation.2023.110012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Revised: 09/28/2023] [Accepted: 10/15/2023] [Indexed: 11/05/2024]
Abstract
INTRODUCTION The epidemiology and outcomes for patients with an out-of-hospital cardiac arrest (OHCA) caused by poisoning are largely unknown and may differ from OHCA of other causes. The study's aim is to compare key characteristics and outcomes between OHCA caused by poisoning vs. other causes. METHOD A retrospective observational study based on three Swedish national registries. All adult patients with an OHCA between January 1st 2007 and December 31st 2021 were included. The study population was divided into medical, non-medical and poisoning cause according to ICD-10-codes. RESULTS Of the 66,261 included OHCA (65.8% men, median 73 years), 89% were classified as medical and 11% non-medical. 47% of the non-medical OHCA were caused by poisoning, which represents 5.2% of all OHCA. Patients with an OHCA caused by poisoning were significantly younger (median 43 years), a larger proportion of men (67%), had the lowest frequency of witnessed event and shockable rhythm of the groups. The most common poisoning was poly-substance. The crude 30-day mortality for OHCA caused by poisoning was 83.7%, which was lower than in the medical (88%) and non-medical groups (93.8%). The adjusted 30-day mortality for OHCA caused by poisoning vs medical had an OR of 3.1 (95% CI 2.5-3.8) and vs non-medical OR 3.7 (95% CI 2.8-5.0). CONCLUSION Patients with an OHCA caused by poisoning were younger, a larger proportion of men and had several predictors for increased mortality, yet still had a lower 30-day mortality rate when compared to other causes.
Collapse
Affiliation(s)
- Elin Lindqvist
- Center for Resuscitation Science, Karolinska Institutet, South General Hospital, Stockholm, Sweden; Department of Anesthesiology and Intensive Care, South General Hospital, Stockholm, Sweden.
| | - Jacob Hollenberg
- Center for Resuscitation Science, Karolinska Institutet, South General Hospital, Stockholm, Sweden; Department of Cardiology, South General Hospital, Stockholm, Sweden
| | - Mattias Ringh
- Center for Resuscitation Science, Karolinska Institutet, South General Hospital, Stockholm, Sweden; Department of Cardiology, South General Hospital, Stockholm, Sweden
| | - Per Nordberg
- Center for Resuscitation Science, Karolinska Institutet, South General Hospital, Stockholm, Sweden; Function Perioperative Medicine and Intensive Care, Karolinska University Hospital, Stockholm, Sweden
| | - Sune Forsberg
- Center for Resuscitation Science, Karolinska Institutet, South General Hospital, Stockholm, Sweden; Department of Anesthesiology and Intensive Norrtälje Hospital, Norrtälje, Sweden
| |
Collapse
|
16
|
Shinada K, Matsuoka A, Koami H, Sakamoto Y. Bayesian network predicted variables for good neurological outcomes in patients with out-of-hospital cardiac arrest. PLoS One 2023; 18:e0291258. [PMID: 37768915 PMCID: PMC10538776 DOI: 10.1371/journal.pone.0291258] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Accepted: 08/24/2023] [Indexed: 09/30/2023] Open
Abstract
Out-of-hospital cardiac arrest (OHCA) is linked to a poor prognosis and remains a public health concern. Several studies have predicted good neurological outcomes of OHCA. In this study, we used the Bayesian network to identify variables closely associated with good neurological survival outcomes in patients with OHCA. This was a retrospective observational study using the Japan Association for Acute Medicine OHCA registry. Fifteen explanatory variables were used, and the outcome was one-month survival with Glasgow-Pittsburgh cerebral performance category (CPC) 1-2. The 2014-2018 dataset was used as training data. The variables selected were identified and a sensitivity analysis was performed. The 2019 dataset was used for the validation analysis. Four variables were identified, including the motor response component of the Glasgow Coma Scale (GCS M), initial rhythm, age, and absence of epinephrine. Estimated probabilities were increased in the following order: GCS M score: 2-6; epinephrine: non-administered; initial rhythm: spontaneous rhythm and shockable; and age: <58 and 59-70 years. The validation showed a sensitivity of 75.4% and a specificity of 95.4%. We identified GCS M score of 2-6, initial rhythm (spontaneous rhythm and shockable), younger age, and absence of epinephrine as variables associated with one-month survival with CPC 1-2. These variables may help clinicians in the decision-making process while treating patients with OHCA.
Collapse
Affiliation(s)
- Kota Shinada
- Department of Emergency and Critical Care Medicine, Faculty of Medicine, Saga University, Saga City, Saga Prefecture, Japan
| | - Ayaka Matsuoka
- Department of Emergency and Critical Care Medicine, Faculty of Medicine, Saga University, Saga City, Saga Prefecture, Japan
| | - Hiroyuki Koami
- Department of Emergency and Critical Care Medicine, Faculty of Medicine, Saga University, Saga City, Saga Prefecture, Japan
| | - Yuichiro Sakamoto
- Department of Emergency and Critical Care Medicine, Faculty of Medicine, Saga University, Saga City, Saga Prefecture, Japan
| |
Collapse
|
17
|
Kawai Y, Yamamoto K, Miyazaki K, Asai H, Fukushima H. Machine learning-based analysis of regional differences in out-of-hospital cardiopulmonary arrest outcomes and resuscitation interventions in Japan. Sci Rep 2023; 13:15884. [PMID: 37741881 PMCID: PMC10518013 DOI: 10.1038/s41598-023-43210-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2023] [Accepted: 09/21/2023] [Indexed: 09/25/2023] Open
Abstract
Refining out-of-hospital cardiopulmonary arrest (OHCA) resuscitation protocols for local emergency practices is vital. The lack of comprehensive evaluation methods for individualized protocols impedes targeted improvements. Thus, we employed machine learning to assess emergency medical service (EMS) records for examining regional disparities in time reduction strategies. In this retrospective study, we examined Japanese EMS records and neurological outcomes from 2015 to 2020 using nationwide data. We included patients aged ≥ 18 years with cardiogenic OHCA and visualized EMS activity time variations across prefectures. A five-layer neural network generated a neurological outcome predictive model that was trained on 80% of the data and tested on the remaining 20%. We evaluated interventions associated with changes in prognosis by simulating these changes after adjusting for time factors, including EMS contact to hospital arrival and initial defibrillation or drug administration. The study encompassed 460,540 patients, with the model's area under the curve and accuracy being 0.96 and 0.95, respectively. Reducing transport time and defibrillation improved outcomes universally, while combining transport time and drug administration showed varied efficacy. In conclusion, the association of emergency activity time with neurological outcomes varied across Japanese prefectures, suggesting the need to set targets for reducing activity time in localized emergency protocols.
Collapse
Affiliation(s)
- Yasuyuki Kawai
- Department of Emergency and Critical Care Medicine, Nara Medical University, 840 Shijo-Cho, Kashihara, Nara, 634-8522, Japan.
| | - Koji Yamamoto
- Department of Emergency and Critical Care Medicine, Nara Medical University, 840 Shijo-Cho, Kashihara, Nara, 634-8522, Japan
| | - Keita Miyazaki
- Department of Emergency and Critical Care Medicine, Nara Medical University, 840 Shijo-Cho, Kashihara, Nara, 634-8522, Japan
| | - Hideki Asai
- Department of Emergency and Critical Care Medicine, Nara Medical University, 840 Shijo-Cho, Kashihara, Nara, 634-8522, Japan
| | - Hidetada Fukushima
- Department of Emergency and Critical Care Medicine, Nara Medical University, 840 Shijo-Cho, Kashihara, Nara, 634-8522, Japan
| |
Collapse
|
18
|
Patel H, Mahtani AU, Mehta LS, Kalra A, Prabhakaran D, Yadav R, Naik N, Tamirisa KP. Outcomes of out of hospital sudden cardiac arrest in India: A review and proposed reforms. Indian Heart J 2023; 75:321-326. [PMID: 37657626 PMCID: PMC10568059 DOI: 10.1016/j.ihj.2023.08.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2023] [Revised: 08/19/2023] [Accepted: 08/29/2023] [Indexed: 09/03/2023] Open
Abstract
BACKGROUND Bystander cardiopulmonary resuscitation (CPR) is the cornerstone in managing out-of-hospital cardiac arrest (OHCA). However, India lacks a formal sudden cardiac arrest (SCA) registry and the infrastructure for a robust emergency medical services (EMS) response system. Also, there exists an opportunity to improve widespread health literacy and awareness regarding SCA. Other confounding variables, including religious, societal, and cultural sentiments hindering timely intervention, need to be considered for better SCA outcomes. OBJECTIVES We highlight the current trends and practices of managing OHCA in India and lay the groundwork for improving the awareness, education, and infrastructure regarding the management of SCA. CONCLUSION Effective management of OHCA in India needs collaborative grassroots reformation. Establishing a large-scale SCA registry and creating official and societal guidelines will be pivotal for transforming OHCA patient outcomes.
Collapse
Affiliation(s)
- Hiren Patel
- Department of Cardiology, Saint Louis University School of Medicine, St. Louis, MO, United States; Department of Cardiology, Lahey Hospital and Medical Center, Burlington, MA, United States
| | - Arun Umesh Mahtani
- Department of Medicine, Richmond University Medical Center, Staten Island, NY, United States
| | - Laxmi S Mehta
- Department of Cardiology, The Ohio State University Wexner Medical Center, Columbus, OH, United States
| | - Ankur Kalra
- Franciscan Health, Lafayette, IN, United States
| | | | - Rakesh Yadav
- Department of Cardiology, Cardiothoracic Center, All India Institute of Medical Sciences, New Delhi, India
| | - Nitish Naik
- Department of Cardiology, Cardiothoracic Center, All India Institute of Medical Sciences, New Delhi, India
| | - Kamala P Tamirisa
- Clinical Cardiac Electrophysiologist, Texas Cardiac Arrhythmia Institute, Austin and Dallas, Texas, United States.
| |
Collapse
|
19
|
Schultz BV, Rolley A, Doan TN, Bodnar D, Isoardi K. Epidemiology and survival outcomes of out-of-hospital cardiac arrest following volatile substance use in Queensland, Australia. Clin Toxicol (Phila) 2023; 61:649-655. [PMID: 37988117 DOI: 10.1080/15563650.2023.2267172] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2023] [Accepted: 10/01/2023] [Indexed: 11/22/2023]
Abstract
INTRODUCTION The deliberate inhalation of volatile substances for their psychotropic properties is a recognised public health issue that can precipitate sudden death. This study aimed to describe the epidemiological characteristics and survival outcomes of patients with out-of-hospital cardiac arrests following volatile substance use. METHODS We conducted a retrospective cohort analysis of all out-of-hospital cardiac arrest attended by the Queensland Ambulance Service over a ten-year period (2012-2021). Incidents were extracted from the Queensland Ambulance Service cardiac arrest registry, which collects clinical information using the Utstein-style guidelines and linked hospital data. RESULTS During the study period, 52,102 out-of-hospital cardiac arrests were attended, with 22 (0.04%) occurring following volatile substance use. The incidence rate was 0.04 per 100,000 population, with no temporal trends identified. The most commonly used product was deodorant cans (19/22), followed by butane canisters (2/22), and nitrous oxide canisters (1/22). The median age of patients was 15 years (interquartile range 13-23), with 14/22 male and 8/22 Indigenous Australians. Overall, 16/22 patients received a resuscitation attempt by paramedics. Of these, 12/16 were bystander witnessed, 10/16 presented in an initial shockable rhythm, and 9/16 received bystander chest compressions. The rates of event survival, survival to hospital discharge, and survival with good neurological outcome (Cerebral Performance Category 1-2) were 69% (11/16, 95% CI 41-89%), 38% (6/16, 95% CI 15-65%) and 31% (5/16, 11-59%), respectively. Eight patients in the paramedic-treated cohort that used hydrocarbon-based products were administered epinephrine during resuscitation. Of these, none subsequently survived to hospital discharge. In contrast, all six patients that did not receive epinephrine survived to hospital discharge, with 5/6 having a good neurological outcome. CONCLUSION Out-of-hospital cardiac arrest following volatile substance use is rare and associated with relatively favourable survival rates. Patients were predominately aged in their adolescence with Indigenous Australians disproportionately represented.
Collapse
Affiliation(s)
- Brendan V Schultz
- Department of Health, Queensland Ambulance Service, Brisbane, Queensland, Australia
| | - Adam Rolley
- Department of Health, Queensland Ambulance Service, Brisbane, Queensland, Australia
- Jamieson Trauma Institute, Royal Brisbane and Women's Hospital, Metro North Hospital and Health Service, Brisbane, Queensland, Australia
- School of Clinical Sciences, Queensland University of Technology, Brisbane, Queensland, Australia
| | - Tan N Doan
- Department of Health, Queensland Ambulance Service, Brisbane, Queensland, Australia
- Department of Medicine at the Royal Melbourne Hospital, University of Melbourne, Melbourne, Victoria, Australia
| | - Daniel Bodnar
- Department of Health, Queensland Ambulance Service, Brisbane, Queensland, Australia
- Emergency and Trauma Centre, Royal Brisbane and Women's Hospital, Brisbane, Queensland, Australia
- Emergency Department, Queensland Children's Hospital, Brisbane, Queensland, Australia
| | - Katherine Isoardi
- Clinical Toxicology Unit, Princess Alexandra Hospital, Brisbane, Queensland, Australia
- Faculty of Medicine, University of Queensland, Brisbane, Queensland, Australia
| |
Collapse
|
20
|
Chee ML, Chee ML, Huang H, Mazzochi K, Taylor K, Wang H, Feng M, Ho AFW, Siddiqui FJ, Ong MEH, Liu N. Artificial intelligence and machine learning in prehospital emergency care: A scoping review. iScience 2023; 26:107407. [PMID: 37609632 PMCID: PMC10440716 DOI: 10.1016/j.isci.2023.107407] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/24/2023] Open
Abstract
Our scoping review provides a comprehensive analysis of the landscape of artificial intelligence (AI) applications in prehospital emergency care (PEC). It contributes to the field by highlighting the most studied AI applications and identifying the most common methodological approaches across 106 included studies. The findings indicate a promising future for AI in PEC, with many unique use cases, such as prognostication, demand prediction, resource optimization, and the Internet of Things continuous monitoring systems. Comparisons with other approaches showed AI outperforming clinicians and non-AI algorithms in most cases. However, most studies were internally validated and retrospective, highlighting the need for rigorous prospective validation of AI applications before implementation in clinical settings. We identified knowledge and methodological gaps using an evidence map, offering a roadmap for future investigators. We also discussed the significance of explainable AI for establishing trust in AI systems among clinicians and facilitating real-world validation of AI models.
Collapse
Affiliation(s)
- Marcel Lucas Chee
- Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, VIC, Australia
| | - Mark Leonard Chee
- Faculty of Health and Medical Sciences, University of Adelaide, Adelaide, SA, Australia
| | - Haotian Huang
- Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, VIC, Australia
| | - Katelyn Mazzochi
- Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, VIC, Australia
| | - Kieran Taylor
- Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, VIC, Australia
| | - Han Wang
- Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore
| | - Mengling Feng
- Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore
| | - Andrew Fu Wah Ho
- Department of Emergency Medicine, Singapore General Hospital, Singapore, Singapore
- Pre-Hospital and Emergency Research Centre, Duke-NUS Medical School, Singapore, Singapore
| | - Fahad Javaid Siddiqui
- Pre-Hospital and Emergency Research Centre, Duke-NUS Medical School, Singapore, Singapore
| | - Marcus Eng Hock Ong
- Department of Emergency Medicine, Singapore General Hospital, Singapore, Singapore
- Pre-Hospital and Emergency Research Centre, Duke-NUS Medical School, Singapore, Singapore
| | - Nan Liu
- Pre-Hospital and Emergency Research Centre, Duke-NUS Medical School, Singapore, Singapore
- Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore
- Institute of Data Science, National University of Singapore, Singapore, Singapore
| |
Collapse
|
21
|
Ziapour A, Hatami Garosi V, Tamri Y, Ghazvineh S, Azizi A. Investigating the outcomes of cardiopulmonary resuscitation and factors affecting it: A cross-sectional study at Dr. Moaven Hospital, Sahneh City from 2014 to 2021. Health Sci Rep 2023; 6:e1493. [PMID: 37599656 PMCID: PMC10435728 DOI: 10.1002/hsr2.1493] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2023] [Revised: 07/16/2023] [Accepted: 08/01/2023] [Indexed: 08/22/2023] Open
Abstract
Background and Aims Cardiopulmonary resuscitation (CPR) is referred to an attempt to maintain the respiratory system and blood circulation active to oxygenate the body's important organs until the heart and blood circulation system return to normal. CPR results are influenced by a variety of circumstances and factors. The purpose of this study was to look into the outcomes of CPR and the factors that influence them at the Dr. Moaven Hospital in Sahneh. Methods This cross-sectional descriptive study was carried out retrospectively from the start of 2014 to the start of 2021. Kermanshah University of Medical Sciences provides hospitals with a two-page form for data collection. After entering the data into SPSS24, descriptive and inferential statistical tests were applied to analyze the results. Results Out of 497 patients who referred to Dr. Moaven Hospital in Sahne City, 280 were men and 217 were women, with a resuscitation success rate of 22.5% in men and 23.5% in women. CPR was conducted on 63.2% of patients in the emergency department, with 22.2% of them having successful CPR. The existence of the underlying disease had a statistically significant link with the outcomes of CPR (p = 0.007). The most prevalent cause for visit was cardiorespiratory arrest (30.6%), and there was no statistically significant difference between the diagnostic and reason for visit and the outcome of resuscitation, according to the χ 2 test. Conclusion According to the findings of this study, increasing age and duration of CPR, the existence of underlying diseases, and the absence of shockable rhythms all reduce the likelihood of success in CPR.
Collapse
Affiliation(s)
- Arash Ziapour
- Cardiovascular Research Center, Health Institute, Imam‐Ali HospitalKermanshah University of Medical SciencesKermanshahIran
| | - Vahid Hatami Garosi
- Student Research CommitteeKermanshah University of Medical SciencesKermanshahIran
| | - Yasaman Tamri
- Kermanshah University of Medical SciencesKermanshahIran
| | | | - Ali Azizi
- Department of Community Medicine, Faculty of MedicineKermanshah University of Medical SciencesKermanshahIran
| |
Collapse
|
22
|
Jensen TW, Ersbøll AK, Folke F, Andersen MP, Blomberg SN, Holgersen MG, Andersen LB, Lippert F, Torp-Pedersen C, Christensen HC. Geographical Association Between Basic Life Support Courses and Bystander Cardiopulmonary Resuscitation and Survival from OHCA in Denmark. Open Access Emerg Med 2023; 15:241-252. [PMID: 37342237 PMCID: PMC10278866 DOI: 10.2147/oaem.s405397] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2023] [Accepted: 05/20/2023] [Indexed: 06/22/2023] Open
Abstract
Introduction Annually, approximately 4% of the entire adult population of Denmark participate in certified basic life support (BLS) courses. It is still unknown whether increases in BLS course participation in a geographical area increase bystander cardiopulmonary resuscitation (CPR) or survival from out-of-hospital cardiac arrest (OHCA). The aim of the study was to examine the geographical association between BLS course participation, bystander CPR, and 30-day survival from OHCA. Methods This nationwide register-based cohort study includes all OHCAs from the Danish Cardiac Arrest Register. Data concerning BLS course participation were supplied by the major Danish BLS course providers. A total of 704,234 individuals with BLS course certificates and 15,097 OHCA were included from the period 2016-2019. Associations were examined using logistic regression and Bayesian conditional autoregressive analyses conducted at municipality level. Results A 5% increase in BLS course certificates at municipality level was significantly associated with an increased likelihood of bystander CPR prior to ambulance arrival with an adjusted odds ratio (OR) of 1.34 (credible intervals: 1.02;1.76). The same trends were observed for OHCAs in out-of-office hours (4pm-08am) with a significant OR of 1.43 (credible intervals: 1.09;1.89). Local clusters with low rate of BLS course participation and bystander CPR were identified. Conclusion This study found a positive effect of mass education in BLS on bystander CPR rates. Even a 5% increase in BLS course participation at municipal level significantly increased the likelihood of bystander CPR. The effect was even more profound in out-of-office hours with an increase in bystander CPR rate at OHCA.
Collapse
Affiliation(s)
- Theo Walther Jensen
- Emergency Medical Services Region Zealand, Naestved, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Copenhagen Emergency Medical Services, University of Copenhagen, Copenhagen, Denmark
| | - Annette Kjær Ersbøll
- Copenhagen Emergency Medical Services, University of Copenhagen, Copenhagen, Denmark
- National Institute of Public Health, University of Southern Denmark, Copenhagen, Denmark
| | - Fredrik Folke
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Copenhagen Emergency Medical Services, University of Copenhagen, Copenhagen, Denmark
- Department of Cardiology, Herlev Gentofte University Hospital, Gentofte, Denmark
| | | | - Stig Nikolaj Blomberg
- Emergency Medical Services Region Zealand, Naestved, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Copenhagen Emergency Medical Services, University of Copenhagen, Copenhagen, Denmark
| | - Mathias Geldermann Holgersen
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Paediatric Pulmonary Service, Department of Paediatrics and Adolescent Medicine, Copenhagen University Hospital, Copenhagen, Denmark
| | | | - Freddy Lippert
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Copenhagen Emergency Medical Services, University of Copenhagen, Copenhagen, Denmark
| | - Christian Torp-Pedersen
- Department of Cardiology, Nordsjaellands Hospital, Hilleroed, Denmark
- Aalborg University Hospital, Aalborg & Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | - Helle Collatz Christensen
- Emergency Medical Services Region Zealand, Naestved, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Danish Clinical Quality Program (RKKP), National Clinical Registries & Department of Clinical Medicine, Copenhagen, Denmark
| |
Collapse
|
23
|
Masoumian Hosseini M, Masoumian Hosseini ST, Qayumi K, Ahmady S, Koohestani HR. The Aspects of Running Artificial Intelligence in Emergency Care; a Scoping Review. ARCHIVES OF ACADEMIC EMERGENCY MEDICINE 2023; 11:e38. [PMID: 37215232 PMCID: PMC10197918 DOI: 10.22037/aaem.v11i1.1974] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 05/24/2023]
Abstract
Introduction Artificial Inteligence (AI) application in emergency medicine is subject to ethical and legal inconsistencies. The purposes of this study were to map the extent of AI applications in emergency medicine, to identify ethical issues related to the use of AI, and to propose an ethical framework for its use. Methods A comprehensive literature collection was compiled through electronic databases/internet search engines (PubMed, Web of Science Platform, MEDLINE, Scopus, Google Scholar/Academia, and ERIC) and reference lists. We considered studies published between 1 January 2014 and 6 October 2022. Articles that did not self-classify as studies of an AI intervention, those that were not relevant to Emergency Departments (EDs), and articles that did not report outcomes or evaluations were excluded. Descriptive and thematic analyses of data extracted from the included articles were conducted. Results A total of 137 out of the 2175 citations in the original database were eligible for full-text evaluation. Of these articles, 47 were included in the scoping review and considered for theme extraction. This review covers seven main areas of AI techniques in emergency medicine: Machine Learning (ML) Algorithms (10.64%), prehospital emergency management (12.76%), triage, patient acuity and disposition of patients (19.15%), disease and condition prediction (23.40%), emergency department management (17.03%), the future impact of AI on Emergency Medical Services (EMS) (8.51%), and ethical issues (8.51%). Conclusion There has been a rapid increase in AI research in emergency medicine in recent years. Several studies have demonstrated the potential of AI in diverse contexts, particularly when improving patient outcomes through predictive modelling. According to the synthesis of studies in our review, AI-based decision-making lacks transparency. This feature makes AI decision-making opaque.
Collapse
Affiliation(s)
| | | | - Karim Qayumi
- Centre of Excellence for Simulation Education and Innovation, Department of Surgery, University of British Columbia, Vancouver, BC, Canada
| | - Soleiman Ahmady
- Department of Medical Education, Virtual School of Medical Education & Management, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Hamid Reza Koohestani
- Department of Nursing, Social Determinants of Health Research Center, Saveh University of Medical Sciences, Saveh, Iran
| |
Collapse
|
24
|
Wang H, Ng QX, Arulanandam S, Tan C, Ong MEH, Feng M. Building a Machine Learning-based Ambulance Dispatch Triage Model for Emergency Medical Services. HEALTH DATA SCIENCE 2023; 3:0008. [PMID: 38487206 PMCID: PMC10880163 DOI: 10.34133/hds.0008] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/07/2022] [Accepted: 02/05/2023] [Indexed: 03/17/2024]
Abstract
Background In charge of dispatching the ambulances, Emergency Medical Services (EMS) call center specialists often have difficulty deciding the acuity of a case given the information they can gather within a limited time. Although there are protocols to guide their decision-making, observed performance can still lack sensitivity and specificity. Machine learning models have been known to capture complex relationships that are subtle, and well-trained data models can yield accurate predictions in a split of a second. Methods In this study, we proposed a proof-of-concept approach to construct a machine learning model to better predict the acuity of emergency cases. We used more than 360,000 structured emergency call center records of cases received by the national emergency call center in Singapore from 2018 to 2020. Features were created using call records, and multiple machine learning models were trained. Results A Random Forest model achieved the best performance, reducing the over-triage rate by an absolute margin of 15% compared to the call center specialists while maintaining a similar level of under-triage rate. Conclusions The model has the potential to be deployed as a decision support tool for dispatchers alongside current protocols to optimize ambulance dispatch triage and the utilization of emergency ambulance resources.
Collapse
Affiliation(s)
- Han Wang
- Saw Swee Hock School of Public Health, National University Health System, National University of Singapore, Singapore
| | | | | | - Colin Tan
- Singapore Civil Defence Force, Singapore
| | - Marcus E. H. Ong
- Health Services Research Centre, Singapore Health Services, Singapore
- Health Services and Systems Research, Duke-NUS Medical School, National University of Singapore, Singapore
- Department of Emergency Medicine, Singapore General Hospital, Singapore
| | - Mengling Feng
- Saw Swee Hock School of Public Health, National University Health System, National University of Singapore, Singapore
- Institute of Data Science, National University of Singapore, Singapore
| |
Collapse
|
25
|
Viderman D, Abdildin YG, Batkuldinova K, Badenes R, Bilotta F. Artificial Intelligence in Resuscitation: A Scoping Review. J Clin Med 2023; 12:jcm12062254. [PMID: 36983255 PMCID: PMC10054374 DOI: 10.3390/jcm12062254] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2023] [Revised: 02/17/2023] [Accepted: 03/09/2023] [Indexed: 03/17/2023] Open
Abstract
Introduction: Cardiac arrest is a significant cause of premature mortality and severe disability. Despite the death rate steadily decreasing over the previous decade, only 22% of survivors achieve good clinical status and only 25% of patients survive until their discharge from the hospital. The objective of this scoping review was to review relevant AI modalities and the main potential applications of AI in resuscitation. Methods: We conducted the literature search for related studies in PubMed, EMBASE, and Google Scholar. We included peer-reviewed publications and articles in the press, pooling and characterizing the data by their model types, goals, and benefits. Results: After identifying 268 original studies, we chose 59 original studies (reporting 1,817,419 patients) to include in the qualitative synthesis. AI-based methods appear to be superior to traditional methods in achieving high-level performance. Conclusion: AI might be useful in predicting cardiac arrest, heart rhythm disorders, and post-cardiac arrest outcomes, as well as in the delivery of drone-delivered defibrillators and notification of dispatchers. AI-powered technologies could be valuable assistants to continuously track patient conditions. Healthcare professionals should assist in the research and development of AI-powered technologies as well as their implementation into clinical practice.
Collapse
Affiliation(s)
- Dmitriy Viderman
- Department of Surgery, Nazarbayev University School of Medicine (NUSOM), Kerei, Zhanibek khandar Str. 5/1, Astana 010000, Kazakhstan;
| | - Yerkin G. Abdildin
- Department of Mechanical and Aerospace Engineering, School of Engineering and Digital Sciences, Nazarbayev University, 53 Kabanbay Batyr Ave., Astana 010000, Kazakhstan
| | - Kamila Batkuldinova
- Department of Mechanical and Aerospace Engineering, School of Engineering and Digital Sciences, Nazarbayev University, 53 Kabanbay Batyr Ave., Astana 010000, Kazakhstan
| | - Rafael Badenes
- Department of Anaesthesiology and Intensive Care, Hospital Clìnico Universitario de Valencia, University of Valencia, 46001 Valencia, Spain
- Correspondence:
| | - Federico Bilotta
- Department of Anesthesia and Intensive Care, University La Sapienza, 00185 Rome, Italy
| |
Collapse
|
26
|
Jensen TW, Ersbøll AK, Folke F, Wolthers SA, Andersen MP, Blomberg SN, Andersen LB, Lippert F, Torp-Pedersen C, Christensen HC. Training in Basic Life Support and Bystander-Performed Cardiopulmonary Resuscitation and Survival in Out-of-Hospital Cardiac Arrests in Denmark, 2005 to 2019. JAMA Netw Open 2023; 6:e233338. [PMID: 36929397 PMCID: PMC10020888 DOI: 10.1001/jamanetworkopen.2023.3338] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/18/2023] Open
Abstract
IMPORTANCE Strategies to improve survival from out-of-hospital cardiac arrest (OHCA) include mass education of laypersons with no official duty to respond to OHCA. In Denmark, basic life support (BLS) course attendance has been mandated by law in October 2006 for obtaining a driver's license for all vehicles and in vocational education programs. OBJECTIVES To examine the association between yearly BLS course participation rate and bystander cardiopulmonary resuscitation (CPR) and 30-day survival from OHCA and to examine if bystander CPR rate acted as a mediator on the association between mass education of laypersons in BLS and survival from OHCA. DESIGN, SETTING, AND PARTICIPANTS This cohort study included outcomes for all OHCA incidents from the Danish Cardiac Arrest Register between 2005 and 2019. Data concerning BLS course participation were supplied by the major Danish BLS course providers. MAIN OUTCOMES AND MEASURES The main outcome was 30-day survival of patients who experienced OHCA. Logistic regression analysis was used to examine the association between BLS training rate, bystander CPR rate, and survival, and a bayesian mediation analysis was conducted to examine mediation. RESULTS A total of 51 057 OHCA incidents and 2 717 933 course certificates were included. The study showed that the annual 30-day survival from OHCA increased by 14% (odds ratio [OR], 1.14; 95% CI, 1.10-1.18; P < .001) when BLS course participation rate increased by 5% in analysis adjusted for initial rhythm, automatic external defibrillator use, and mean age. An average mediated proportion of 0.39 (95% QBCI, 0.049-0.818; P = .01). In other words, the last result indicated that 39% of the association between mass educating laypersons in BLS and survival was mediated through an increased bystander CPR rate. CONCLUSIONS AND RELEVANCE In this cohort study of Danish BLS course participation and survival, a positive association was found between annual rate of mass education in BLS and 30-day survival from OHCA. The association of BLS course participation rate on 30-day survival was mediated by the bystander CPR rate; approximately 60% of the association of BLS course participation rate on 30-day survival was based on factors other than increased CPR rates.
Collapse
Affiliation(s)
- Theo Walther Jensen
- Prehospital Center Region Zealand, Næstved, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Copenhagen Emergency Medical Services, Copenhagen, Denmark
| | - Annette Kjær Ersbøll
- Copenhagen Emergency Medical Services, Copenhagen, Denmark
- National Institute of Public Health, University of Southern Denmark, Copenhagen, Denmark
| | - Fredrik Folke
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Copenhagen Emergency Medical Services, Copenhagen, Denmark
- Department of Cardiology, Herlev Gentofte University Hospital, Gentofte, Denmark
| | - Signe Amalie Wolthers
- Prehospital Center Region Zealand, Næstved, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | | | - Stig Nikolaj Blomberg
- Prehospital Center Region Zealand, Næstved, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Copenhagen Emergency Medical Services, Copenhagen, Denmark
| | | | - Freddy Lippert
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Copenhagen Emergency Medical Services, Copenhagen, Denmark
| | - Christian Torp-Pedersen
- Department of Cardiology, Nordsjaellands Hospital, Hillerød, Denmark
- Department of Clinical Medicine, Aalborg University Hospital, University of Copenhagen, Copenhagen, Denmark
| | - Helle Collatz Christensen
- Prehospital Center Region Zealand, Næstved, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Danish Clinical Quality Program (RKKP), National Clinical Registries, Department of Clinical Medicine, Denmark
| |
Collapse
|
27
|
Gamberini L, Del Giudice D, Saltalamacchia S, Taylor B, Sala I, Allegri D, Pastori A, Coniglio C, Gordini G, Semeraro F. Factors associated with the arrival of smartphone-activated first responders before the emergency medical services in Out-of-Hospital cardiac arrest dispatch. Resuscitation 2023; 185:109746. [PMID: 36822460 DOI: 10.1016/j.resuscitation.2023.109746] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Revised: 02/10/2023] [Accepted: 02/14/2023] [Indexed: 02/23/2023]
Abstract
BACKGROUND First responder programs were developed to speed up access to cardiopulmonary resuscitation and defibrillation for out-of-hospital cardiac arrest (OHCA) victims. Little is known about the factors influencing the efficiency of the first responders arriving before the EMS and, therefore, effectively contributing to the chain of survival. OBJECTIVES The primary objective of this retrospective observational study was to identify the factors associated with first responders' arrival before EMS in the context of a regional first responder program arranged to deliver automated external defibrillators on suspected OHCA scenes. METHODS Eight hundred ninety-six dispatches where FRs intervened were collected from 2018 to 2022. A robust Poisson regression was performed to estimate the role of the time of day, the immediate availability of a defibrillator, the type of first responder, distances between the responder, the event and the dispatched vehicle, and the nearest available defibrillator on the probability of responder arriving before EMS. Moreover, a geospatial logistic regression model was built. RESULTS Responders arrived before EMS in 13.4% of dispatches and delivered a shock in 0.9%. The immediate availability of a defibrillator for the responder (OR = 3.24) and special categories such as taxi drivers and police (OR = 1.74) were factors significantly associated with the responder arriving before EMS. Moreover, a geospatial effect suggested that first responder programs may have a greater impact in rural areas. CONCLUSIONS When dispatched to OHCA scenes, responders already carrying defibrillators could more probably reach the scene before EMS. Special first responder categories are more competitive and should be further investigated.
Collapse
Affiliation(s)
- Lorenzo Gamberini
- Department of Anesthesia, Intensive Care and Prehospital Emergency, Ospedale Maggiore Carlo Alberto Pizzardi, Bologna, Italy
| | | | - Stefano Saltalamacchia
- Department of Anesthesia, Intensive Care and Prehospital Emergency, Ospedale Maggiore Carlo Alberto Pizzardi, Bologna, Italy
| | - Benjamin Taylor
- University College Cork, Department School of Mathematical Sciences, Ireland
| | - Isabella Sala
- Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy; Department of Medicine and Surgery, University of Milan-Bicocca, Milan, Italy
| | - Davide Allegri
- Department of Clinical Governance and Quality, Bologna Local Healthcare Authority, Bologna, Italy
| | - Antonio Pastori
- Settore Assistenza Ospedaliera, Direzione Generale Cura della Persona, Salute e Welfare, Assessorato Politiche per la Salute, Regione Emilia, Bologna, Italy
| | - Carlo Coniglio
- Department of Anesthesia, Intensive Care and Prehospital Emergency, Ospedale Maggiore Carlo Alberto Pizzardi, Bologna, Italy.
| | - Giovanni Gordini
- Department of Anesthesia, Intensive Care and Prehospital Emergency, Ospedale Maggiore Carlo Alberto Pizzardi, Bologna, Italy
| | - Federico Semeraro
- Department of Anesthesia, Intensive Care and Prehospital Emergency, Ospedale Maggiore Carlo Alberto Pizzardi, Bologna, Italy
| | | |
Collapse
|
28
|
Lakbar I, Ippolito M, Nassiri A, Delamarre L, Tadger P, Leone M, Einav S. Sex and out-of-hospital cardiac arrest survival: a systematic review. Ann Intensive Care 2022; 12:114. [PMID: 36534195 PMCID: PMC9763524 DOI: 10.1186/s13613-022-01091-9] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2022] [Accepted: 12/05/2022] [Indexed: 12/23/2022] Open
Abstract
BACKGROUND The literature is unresolved on whether female receive advanced cardiac life support less than do male and on whether female have a survival advantage over male after cardiopulmonary resuscitation. METHODS We systematically searched PubMed, Embase and Web of Science databases (from inception to 23-April-2022) for papers reporting outcomes in adult male and female after out-of-hospital cardiac arrest. The main study outcome was the rate of adjusted survival to hospital discharge or 30 days. Secondary outcomes included unadjusted survival to hospital discharge and favourable neurological outcome. RESULTS A total of 28 studies were included, involving 1,931,123 patients. Female were older than male, their cardiac arrests were less likely to be witnessed and less likely to present with a shockable rhythm. Unadjusted analysis showed that females had a lower likelihood of survival than males (OR 0.68 [0.62-0.74], I2 = 97%). After adjustment, no significant difference was identified between male and female in survival at hospital discharge/30 days (OR 1.01 [0.93-1.11], I2 = 87%). Data showed that male had a significantly higher likelihood of favorable neurological outcome in unadjusted analysis but this trend disappeared after adjustment. Both the primary outcome (adjusted for several variables) and the secondary outcomes were associated with substantial heterogeneity. The variables examined using meta-regression, subgroup and sensitivity analyses (i.e., study type, location, years, population, quality of adjustment, risk of bias) did not reduce heterogeneity. CONCLUSIONS The adjusted rate of survival to hospital discharge/30 days was similar for male and female despite an initial seeming survival advantage for male. The validity of this finding is limited by substantial heterogeneity despite in-depth investigation of its causes, which raises concerns regarding latent inequalities in some reports nonetheless. Further study on this topic may require inclusion of factors not reported in the Utstein template and in-depth analysis of decision-making processes.
Collapse
Affiliation(s)
- Ines Lakbar
- Aix-Marseille University, Publique Hôpitaux de Marseille, Marseille, France.
- Department of Anesthesiology and Intensive Care, Hôpital Nord, 13015, Marseille, France.
- CEReSS, Health Service Research and Quality of Life Centre, School of Medicine - La Timone Medical, Aix-Marseille University, Marseille, France.
| | - Mariachiara Ippolito
- Department of Surgical, Oncological and Oral Science (Di.Chir.On.S.), University of Palermo, Palermo, Italy
- Department of Anaesthesia, Intensive Care and Emergency, Policlinico Paolo Giaccone, Via del Vespro 129, 90127, Palermo, Italy
| | - Aviv Nassiri
- Department of Military Medicine and Tzameret, Faculty of Medicine, Hebrew University of Jerusalem, Jerusalem, Israel
- Medical Corps, Israel Defense Forces, Tel HaShomer, Israel
| | - Louis Delamarre
- Aix-Marseille University, Publique Hôpitaux de Marseille, Marseille, France
- Department of Anesthesiology and Intensive Care, Hôpital Nord, 13015, Marseille, France
| | | | - Marc Leone
- Aix-Marseille University, Publique Hôpitaux de Marseille, Marseille, France
- Department of Anesthesiology and Intensive Care, Hôpital Nord, 13015, Marseille, France
- CEReSS, Health Service Research and Quality of Life Centre, School of Medicine - La Timone Medical, Aix-Marseille University, Marseille, France
| | - Sharon Einav
- Intensive Care Unit, Shaare Zedek Medical Center, Jerusalem, Israel
| |
Collapse
|
29
|
Darginavicius L, Kajokaite I, Mikelionis N, Vencloviene J, Dobozinskas P, Vaitkaitiene E, Vaitkaitis D, Krikscionaitiene A. Short- and long-term survival after out-of-hospital cardiac arrest in Kaunas (Lithuania) from 2016 to 2018. BMC Cardiovasc Disord 2022; 22:519. [PMID: 36460967 PMCID: PMC9719236 DOI: 10.1186/s12872-022-02964-4] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2021] [Accepted: 11/19/2022] [Indexed: 12/05/2022] Open
Abstract
BACKGROUND No studies analysing out-of-hospital cardiac arrest (OHCA) epidemiology and outcomes in Lithuania were published in the last decade. METHODS We conducted a retrospective analysis of prospectively collected data. The incidence of OHCA and the demographics and outcomes of patients who were treated for OHCA between 1 and 2016 and 31 December 2018 at Kaunas Emergency Medical Service (EMS) were collected and are reported in accordance with the Utstein recommendations. Multivariable logistic regression analysis was used to identify predictors of survival to hospital discharge. RESULTS In total, 838 OHCA cases of EMS-treated cardiac arrest (CA) were reported (95.8 per 100.000 inhabitants). The median age was 71 (IQR 58-81) years of age, and 66.7% of patients were males. A total of 73.8% of OHCA cases occurred at home, 59.3% were witnessed by a bystander, and 54.5% received bystander cardiopulmonary resuscitation. The median EMS response time was 10 min. Cardiac aetiology was the leading cause of CA (78.8%). The initial rhythm was shockable in 27.6% of all cases. Return of spontaneous circulation at hospital transfer was evident in 24.9% of all cases. The survival to hospital discharge rate was 10.9%, and the 1-year survival rate was 6.9%. The survival to hospital discharge rate in the Utstein comparator group was 36.1%, and the 1-year survival rate was 27.2%. Five factors were associated with improved survival to hospital discharge: shockable rhythm, time from call to arrival at the patient less than 10 min, witnessed OHCA, age < 80 years, and male sex. CONCLUSION This is the first OHCA study from Lithuania examining OHCA epidemiology and outcomes over a three year period. Routine OHCA data collection and analysis will allow us to track the efficacy of service improvements and should become a standard practice in all Lithuanian regions. TRIAL REGISTRATION This research was registered in the clinicaltrials.gov database: Identifiers: NCT04784117, Unique Protocol ID: LITOHCA. Brief Title: Out-of-hospital Cardiac Arrest Epidemiology and Outcomes in Kaunas 2016-2021.
Collapse
Affiliation(s)
- Linas Darginavicius
- grid.45083.3a0000 0004 0432 6841Department of Disaster Medicine, Lithuanian University of Health Sciences, Eiveniu 4-512, 50161 Kaunas, Lithuania
| | | | | | - Jone Vencloviene
- grid.19190.300000 0001 2325 0545Department of Environmental Sciences, Faculty of Natural Sciences, Vytautas Magnus University, Kaunas, Lithuania
| | - Paulius Dobozinskas
- grid.45083.3a0000 0004 0432 6841Department of Disaster Medicine, Lithuanian University of Health Sciences, Eiveniu 4-512, 50161 Kaunas, Lithuania
| | - Egle Vaitkaitiene
- grid.45083.3a0000 0004 0432 6841Department of Disaster Medicine, Lithuanian University of Health Sciences, Eiveniu 4-512, 50161 Kaunas, Lithuania ,grid.45083.3a0000 0004 0432 6841Department of Public Health, Lithuanian University of Health Sciences, Kaunas, Lithuania
| | - Dinas Vaitkaitis
- grid.45083.3a0000 0004 0432 6841Department of Disaster Medicine, Lithuanian University of Health Sciences, Eiveniu 4-512, 50161 Kaunas, Lithuania
| | - Asta Krikscionaitiene
- grid.45083.3a0000 0004 0432 6841Department of Disaster Medicine, Lithuanian University of Health Sciences, Eiveniu 4-512, 50161 Kaunas, Lithuania
| |
Collapse
|
30
|
Visual assessment of interactions among resuscitation activity factors in out-of-hospital cardiopulmonary arrest using a machine learning model. PLoS One 2022; 17:e0273787. [PMID: 36067174 PMCID: PMC9447882 DOI: 10.1371/journal.pone.0273787] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/24/2021] [Accepted: 08/15/2022] [Indexed: 11/19/2022] Open
Abstract
Aim The evaluation of the effects of resuscitation activity factors on the outcome of out-of-hospital cardiopulmonary arrest (OHCA) requires consideration of the interactions among these factors. To improve OHCA success rates, this study assessed the prognostic interactions resulting from simultaneously modifying two prehospital factors using a trained machine learning model. Methods We enrolled 8274 OHCA patients resuscitated by emergency medical services (EMS) in Nara prefecture, Japan, with a unified activity protocol between January 2010 and December 2018; patients younger than 18 and those with noncardiogenic cardiopulmonary arrest were excluded. Next, a three-layer neural network model was constructed to predict the cerebral performance category score of 1 or 2 at one month based on 24 features of prehospital EMS activity. Using this model, we evaluated the prognostic impact of continuously and simultaneously varying the transport time and the defibrillation or drug-administration time in the test data based on heatmaps. Results The average class sensitivity of the prognostic model was more than 0.86, with a full area under the receiver operating characteristics curve of 0.94 (95% confidence interval of 0.92–0.96). By adjusting the two time factors simultaneously, a nonlinear interaction was obtained between the two adjustments, instead of a linear prediction of the outcome. Conclusion Modifications to the parameters using a machine-learning-based prognostic model indicated an interaction among the prognostic factors. These findings could be used to evaluate which factors should be prioritized to reduce time in the trained region of machine learning in order to improve EMS activities.
Collapse
|
31
|
Awad EM, Humphries KH, Grunau BE, Norris CM, Christenson JM. Predictors of neurological outcome after out-of-hospital cardiac arrest: sex-based analysis: do males derive greater benefit from hypothermia management than females? Int J Emerg Med 2022; 15:43. [PMID: 36064329 PMCID: PMC9442968 DOI: 10.1186/s12245-022-00447-z] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2022] [Accepted: 08/19/2022] [Indexed: 11/23/2022] Open
Abstract
Background Previous studies of the effect of sex on after out-of-hospital cardiac arrest (OHCA) outcomes focused on survival to hospital discharge and 1-month survival. Studies on the effect of sex on neurological function after OHCA are still limited. The objective of this study was to identify the predictors of favorable neurological outcome and to examine the association between sex as a biological variable and favorable neurological outcome OHCA. Methods Retrospective analyses of clustered data from the Resuscitation Outcomes Consortium multi-center randomized controlled trial (2011–2015). We included adults with non-traumatic OHCA and EMS-attended OHCA. We used multilevel logistic regression to examine the association between sex and favorable neurological outcomes (modified Rankin Scale) and to identify the predictors of favorable neurological outcome. Results In total, 22,416 patients were included. Of those, 8109 (36.2%) were females. The multilevel analysis identified the following variables as significant predictors of favorable neurological outcome: younger age, shorter duration of EMS arrival to the scene, arrest in public location, witnessed arrest, bystander CPR, chest compression rate (CCR) of 100–120 compressions per minute, induction of hypothermia, and initial shockable rhythm. Two variables, insertion of an advanced airway and administration of epinephrine, were associated with poor neurological outcome. Our analysis showed that males have higher crude rates of survival with favorable neurological outcome (8.6 vs. 4.9%, p < 0.001). However, the adjusted rate was not significant. Further analyses showed that hypothermia had a significantly greater effect on males than females. Conclusions Males had significantly higher crude rates of survival with favorable neurological outcome. However, the adjusted rate was not statistically significant. Males derived significantly greater benefit from hypothermia management than females, but this can possibly be explained by differences in arrest characteristics or in-hospital treatment. In-depth confirmatory studies on the hypothermia effect size by sex are required.
Collapse
Affiliation(s)
- Emad M Awad
- Faculty of Medicine, Experimental Medicine, University of British Columbia, 2775 Laurel Street, 10th Floor, Room 10117, Vancouver, BC, V5Z 1M9, Canada. .,BC RESURECT: BC Resuscitation Research Collaborative, Vancouver, British Columbia, Canada.
| | - Karin H Humphries
- BC RESURECT: BC Resuscitation Research Collaborative, Vancouver, British Columbia, Canada.,Division of Cardiology, Faculty of Medicine, University of British Columbia, Vancouver, British Columbia, Canada.,BC Centre for Improved Cardiovascular Health, Vancouver, British Columbia, Canada
| | - Brian E Grunau
- BC RESURECT: BC Resuscitation Research Collaborative, Vancouver, British Columbia, Canada.,Department of Emergency Medicine, St. Paul's Hospital, Vancouver, British Columbia, Canada.,Department of Emergency Medicine, University of British Columbia, Vancouver, British Columbia, Canada
| | - Colleen M Norris
- Faculties of Nursing, Medicine, and School of Public Health, University of Alberta, Edmonton, Alberta, Canada
| | - Jim M Christenson
- BC RESURECT: BC Resuscitation Research Collaborative, Vancouver, British Columbia, Canada.,Department of Emergency Medicine, St. Paul's Hospital, Vancouver, British Columbia, Canada.,Department of Emergency Medicine, University of British Columbia, Vancouver, British Columbia, Canada
| |
Collapse
|
32
|
Jerkeman M, Sultanian P, Lundgren P, Nielsen N, Helleryd E, Dworeck C, Omerovic E, Nordberg P, Rosengren A, Hollenberg J, Claesson A, Aune S, Strömsöe A, Ravn-Fischer A, Friberg H, Herlitz J, Rawshani A. Trends in survival after cardiac arrest: a Swedish nationwide study over 30 years. Eur Heart J 2022; 43:4817-4829. [PMID: 35924401 PMCID: PMC9726448 DOI: 10.1093/eurheartj/ehac414] [Citation(s) in RCA: 56] [Impact Index Per Article: 18.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/03/2021] [Revised: 07/06/2022] [Accepted: 07/14/2022] [Indexed: 01/12/2023] Open
Abstract
AIMS Trends in characteristics, management, and survival in out-of-hospital cardiac arrest (OHCA) and in-hospital cardiac arrest (IHCA) were studied in the Swedish Cardiopulmonary Resuscitation Registry (SCRR). METHODS AND RESULTS The SCRR was used to study 106 296 cases of OHCA (1990-2020) and 30 032 cases of IHCA (2004-20) in whom resuscitation was attempted. In OHCA, survival increased from 5.7% in 1990 to 10.1% in 2011 and remained unchanged thereafter. Odds ratios [ORs, 95% confidence interval (CI)] for survival in 2017-20 vs. 1990-93 were 2.17 (1.93-2.43) overall, 2.36 (2.07-2.71) for men, and 1.67 (1.34-2.10) for women. Survival increased for all aetiologies, except trauma, suffocation, and drowning. OR for cardiac aetiology in 2017-20 vs. 1990-93 was 0.45 (0.42-0.48). Bystander cardiopulmonary resuscitation increased from 30.9% to 82.2%. Shockable rhythm decreased from 39.5% in 1990 to 17.4% in 2020. Use of targeted temperature management decreased from 42.1% (2010) to 18.2% (2020). In IHCA, OR for survival in 2017-20 vs. 2004-07 was 1.18 (1.06-1.31), showing a non-linear trend with probability of survival increasing by 46.6% during 2011-20. Myocardial ischaemia or infarction as aetiology decreased during 2004-20 from 67.4% to 28.3% [OR 0.30 (0.27-0.34)]. Shockable rhythm decreased from 37.4% to 23.0% [OR 0.57 (0.51-0.64)]. Approximately 90% of survivors (IHCA and OHCA) had no or mild neurological sequelae. CONCLUSION Survival increased 2.2-fold in OHCA during 1990-2020 but without any improvement in the final decade, and 1.2-fold in IHCA during 2004-20, with rapid improvement the last decade. Cardiac aetiology and shockable rhythms were halved. Neurological outcome has not improved.
Collapse
Affiliation(s)
| | | | - Peter Lundgren
- Institute of Medicine, Department of Molecular and Clinical Medicine, University of Gothenburg, Gothenburg, Sweden,Department of Cardiology, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Niklas Nielsen
- Department of Clinical Sciences Lund, Anesthesiology and Intensive care, Lund University, Helsingborg Hospital, Lund, Sweden
| | - Edvin Helleryd
- Institute of Medicine, Department of Molecular and Clinical Medicine, University of Gothenburg, Gothenburg, Sweden
| | - Christian Dworeck
- Institute of Medicine, Department of Molecular and Clinical Medicine, University of Gothenburg, Gothenburg, Sweden,Department of Cardiology, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Elmir Omerovic
- Institute of Medicine, Department of Molecular and Clinical Medicine, University of Gothenburg, Gothenburg, Sweden,Department of Cardiology, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Per Nordberg
- Department of Clinical Science and Education, Södersjukhuset, Centre for Resuscitation Science, Karolinska Institutet, Stockholm, Sweden
| | - Annika Rosengren
- Institute of Medicine, Department of Molecular and Clinical Medicine, University of Gothenburg, Gothenburg, Sweden
| | - Jacob Hollenberg
- Department of Clinical Science and Education, Södersjukhuset, Centre for Resuscitation Science, Karolinska Institutet, Stockholm, Sweden
| | - Andreas Claesson
- Department of Clinical Science and Education, Södersjukhuset, Centre for Resuscitation Science, Karolinska Institutet, Stockholm, Sweden
| | - Solveig Aune
- Institute of Medicine, Department of Molecular and Clinical Medicine, University of Gothenburg, Gothenburg, Sweden
| | - Anneli Strömsöe
- Centre for Clinical Research Dalarna, Uppsala University, Falun, Sweden,Department of Clinical Sciences Lund, Anesthesiology and Intensive care, Lund University, Lund, Sweden
| | - Annica Ravn-Fischer
- Institute of Medicine, Department of Molecular and Clinical Medicine, University of Gothenburg, Gothenburg, Sweden,Department of Cardiology, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Hans Friberg
- Department of Clinical Sciences Lund, Anesthesiology and Intensive care, Lund University, Lund, Sweden
| | - Johan Herlitz
- Prehospen—Centre for Prehospital Research, University of Borås, Borås, Sweden,The Swedish Registry for Cardiopulmonary Resuscitation, Centre of Registries, Västra Götaland, Sweden
| | | |
Collapse
|
33
|
Paulin J, Reunamo A, Kurola J, Moen H, Salanterä S, Riihimäki H, Vesanen T, Koivisto M, Iirola T. Using machine learning to predict subsequent events after EMS non-conveyance decisions. BMC Med Inform Decis Mak 2022; 22:166. [PMID: 35739501 PMCID: PMC9229877 DOI: 10.1186/s12911-022-01901-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2021] [Accepted: 06/11/2022] [Indexed: 12/03/2022] Open
Abstract
Background Predictors of subsequent events after Emergency Medical Services (EMS) non-conveyance decisions are still unclear, though patient safety is the priority in prehospital emergency care. The aim of this study was to find out whether machine learning can be used in this context and to identify the predictors of subsequent events based on narrative texts of electronic patient care records (ePCR). Methods This was a prospective cohort study of EMS patients in Finland. The data was collected from three different regions between June 1 and November 30, 2018. Machine learning, in form of text classification, and manual evaluation were used to predict subsequent events from the clinical notes after a non-conveyance mission. Results FastText-model (AUC 0.654) performed best in prediction of subsequent events after EMS non-conveyance missions (n = 11,846). The model and manual analyses showed that many of the subsequent events were planned before, EMS guided the patients to visit primary health care facilities or ED next or following days after non-conveyance. The most frequent signs and symptoms as subsequent event predictors were musculoskeletal-, infection-related and non-specific complaints. 1 in 5 the EMS documentation was inadequate and many of these led to a subsequent event. Conclusion Machine learning can be used to predict subsequent events after EMS non-conveyance missions. From the patient safety perspective, it is notable that subsequent event does not necessarily mean that patient safety is compromised. There were a number of subsequent visits to primary health care or EDs, which were planned before by EMS. This demonstrates the appropriate use of limited resources to avoid unnecessary conveyance to the ED. However, further studies are needed without planned subsequent events to find out the harmful subsequent events, where EMS non-conveyance puts patient safety at risk.
Collapse
Affiliation(s)
- Jani Paulin
- Department of Clinical Medicine, University of Turku and Turku University of Applied Sciences, Turku, Finland.
| | - Akseli Reunamo
- Department of Biology, University of Turku, Turku, Finland
| | - Jouni Kurola
- Centre for Prehospital Emergency Care, Kuopio University Hospital and University of Eastern Finland, Kuopio, Finland
| | - Hans Moen
- Department of Computing, University of Turku, Turku, Finland
| | - Sanna Salanterä
- Department of Nursing Science, University of Turku and Turku University Hospital, Turku, Finland
| | - Heikki Riihimäki
- Department of Nursing Science, University of Turku, Turku, Finland
| | - Tero Vesanen
- Department of Nursing Science, University of Turku, Turku, Finland
| | - Mari Koivisto
- Department of Biostatistics, University of Turku, Turku, Finland
| | - Timo Iirola
- Emergency Medical Services, Turku University Hospital and University of Turku, Turku, Finland
| |
Collapse
|
34
|
Harris M, Crowe RP, Anders J, D'Acunto S, Adelgais KM, Fishe JN. Identification of factors associated with return of spontaneous circulation after pediatric out-of-hospital cardiac arrest using natural language processing. PREHOSP EMERG CARE 2022:1-8. [PMID: 35510881 DOI: 10.1080/10903127.2022.2074180] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
Abstract
Introduction: Prior studies examining prehospital characteristics related to return of spontaneous circulation (ROSC) in pediatric out-of-hospital cardiac arrest (OHCA) are limited to structured data. Natural language processing (NLP) could identify new factors from unstructured data using free-text narratives. The purpose of this study was to use NLP to examine EMS clinician free-text narratives for characteristics associated with prehospital ROSC in pediatric OHCA.Methods: This was a retrospective analysis of patients ages 0-17 with OHCA in 2019 from the ESO Data Collaborative. We performed an exploratory analysis of EMS narratives using NLP with an a priori token library. We then constructed biostatistical and machine learning models and compared their performance in predicting ROSC.Results: There were 1,726 included EMS encounters for pediatric OHCA; 60% were male patients, and the median age was 1 year (IQR 0-9). Most cardiac arrest events (61.3%) were unwitnessed, 87.3% were identified as having medical causes, and 5.9% had initial shockable rhythms. Prehospital ROSC was achieved in 23.1%. Words most positively correlated with ROSC were "ROSC" (r = 0.42), "pulse" (r = 0.29), "drowning" (r = 0.13), and "PEA" (r = 0.12). Words negatively correlated with ROSC included "asystole" (r = -0.25), "lividity" (r = -0.14), and "cold" (r = -0.14). The terms 'asystole,' 'pulse', 'no breathing', 'PEA', and 'dry' had the greatest difference in frequency of appearance between encounters with and without ROSC (p < 0.05). The best-performing model for predicting prehospital ROSC was logistic regression with random oversampling using free-text data only (area under the receiver operating characteristic curve 0.92).Conclusions: EMS clinician free-text narratives reveal additional characteristics associated with prehospital ROSC in pediatric OHCA. Incorporating those terms into machine learning models of prehospital ROSC improves predictive ability. Therefore, NLP holds promise as a tool for use in predictive models with the goal to increase evidence-based management of pediatric OHCA.
Collapse
Affiliation(s)
- Matthew Harris
- Northwell Hofstra School of Medicine, Departments of Pediatrics and Emergency Medicine, New Hyde Park, NY
| | | | - Jennifer Anders
- Johns Hopkins School of Medicine, Department of Pediatrics, Baltimore, MD
| | - Salvatore D'Acunto
- University of Florida College of Medicine - Jacksonville, Center for Data Solutions, Jacksonville, FL
| | - Kathlen M Adelgais
- University of Colorado School of Medicine, Department of Pediatrics, Section of Pediatric Emergency Medicine, Aurora, CO
| | - Jennifer N Fishe
- University of Florida College of Medicine - Jacksonville, Center for Data Solutions, Jacksonville, FL.,University of Florida College of Medicine - Jacksonville, Department of Emergency Medicine, Jacksonville, FL
| |
Collapse
|
35
|
Schultz BV, Rolley MEpi A, Doan TN, Isoardi K. Epidemiology of out-of-hospital cardiac arrests that occur secondary to chemical asphyxiants: a retrospective series. Resuscitation 2022; 175:113-119. [DOI: 10.1016/j.resuscitation.2022.03.019] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2021] [Revised: 03/01/2022] [Accepted: 03/16/2022] [Indexed: 10/18/2022]
|
36
|
Byrsell F, Claesson A, Jonsson M, Ringh M, Svensson L, Nordberg P, Forsberg S, Hollenberg J, Nord A. Swedish dispatchers’ compliance with the American Heart Association performance goals for dispatch-assisted cardiopulmonary resuscitation and its association with survival in out-of-hospital cardiac arrest: A retrospective study. Resusc Plus 2022; 9:100190. [PMID: 35535343 PMCID: PMC9076962 DOI: 10.1016/j.resplu.2021.100190] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2021] [Revised: 11/30/2021] [Accepted: 11/30/2021] [Indexed: 11/30/2022] Open
Abstract
Aim We aimed 1) to investigate how Swedish dispatchers perform during emergency calls in accordance with the American Heart Association (AHA) goals for dispatcher-assisted cardiopulmonary resuscitation (DA-CPR), 2) calculate the potential impact on 30-day survival. Methods This observational study includes a random sample of 1000 out-of-hospital cardiac arrest (OHCA) emergency ambulance calls during 2018 in Sweden. Voice logs were audited to evaluate dispatchers’ handling of emergency calls according to the AHA performance goals. Number of possible additional survivors was estimated assuming the timeframes of the AHA performance goals was achieved. Results A total of 936 cases were included. An OHCA was recognized by a dispatcher in 79% (AHA goal 75%). In recognizable OHCA, dispatchers recognized 85% (AHA goal 95%). Dispatch-directed compressions were given in 61% (AHA goal 75%). Median time to OHCA recognition was 113 s [interquartile range (IQR), 62, 204 s] (AHA goal < 60 s). The first dispatch-directed compression was performed at a median time of 240 s [IQR, 176, 332 s] (AHA goal < 90 s). If eligible patients receive dispatch-directed compressions within the AHA 90 s goal, 73 additional lives may be saved; if all cases are recognized within the AHA 60 s goal, 25 additional lives may be saved. Conclusions The AHA policy statement serves as a benchmark for all emergency medical dispatch centres (EMDC). Additional effort is needed at Swedish EMDC to achieve AHA goals for DA-CPR. Our study suggests that if EMDC further optimize handling of OHCA calls in accordance with AHA goals, many more lives may be saved.
Collapse
Affiliation(s)
- Fredrik Byrsell
- Department of Clinical Science and Education, Centre for Resuscitation Science, Karolinska Institutet, Södersjukhuset, Stockholm, Sweden
- SOS Alarm AB, Stockholm, Sweden
- Corresponding author at: SOS Alarm AB, Annetorpsvägen 4, 216 23 Malmö, Sweden.
| | - Andreas Claesson
- Department of Clinical Science and Education, Centre for Resuscitation Science, Karolinska Institutet, Södersjukhuset, Stockholm, Sweden
| | - Martin Jonsson
- Department of Clinical Science and Education, Centre for Resuscitation Science, Karolinska Institutet, Södersjukhuset, Stockholm, Sweden
| | - Mattias Ringh
- Department of Clinical Science and Education, Centre for Resuscitation Science, Karolinska Institutet, Södersjukhuset, Stockholm, Sweden
| | - Leif Svensson
- Department of Medicine, Solna Karolinska Institutet, Stockholm, Sweden
| | - Per Nordberg
- Department of Clinical Science and Education, Centre for Resuscitation Science, Karolinska Institutet, Södersjukhuset, Stockholm, Sweden
| | - Sune Forsberg
- Department of Clinical Science and Education, Centre for Resuscitation Science, Karolinska Institutet, Södersjukhuset, Stockholm, Sweden
| | - Jacob Hollenberg
- Department of Clinical Science and Education, Centre for Resuscitation Science, Karolinska Institutet, Södersjukhuset, Stockholm, Sweden
| | - Anette Nord
- Department of Clinical Science and Education, Centre for Resuscitation Science, Karolinska Institutet, Södersjukhuset, Stockholm, Sweden
| |
Collapse
|
37
|
Desai MD, Tootooni MS, Bobay KL. Can Prehospital Data Improve Early Identification of Sepsis in Emergency Department? An Integrative Review of Machine Learning Approaches. Appl Clin Inform 2022; 13:189-202. [PMID: 35108741 PMCID: PMC8810268 DOI: 10.1055/s-0042-1742369] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/04/2023] Open
Abstract
BACKGROUND Sepsis is associated with high mortality, especially during the novel coronavirus disease 2019 (COVID-19) pandemic. Along with high monetary health care costs for sepsis treatment, there is a lasting impact on lives of sepsis survivors and their caregivers. Early identification is necessary to reduce the negative impact of sepsis and to improve patient outcomes. Prehospital data are among the earliest information collected by health care systems. Using these untapped sources of data in machine learning (ML)-based approaches can identify patients with sepsis earlier in emergency department (ED). OBJECTIVES This integrative literature review aims to discuss the importance of utilizing prehospital data elements in ED, summarize their current use in developing ML-based prediction models, and specifically identify those data elements that can potentially contribute to early identification of sepsis in ED when used in ML-based approaches. METHOD Literature search strategy includes following two separate searches: (1) use of prehospital data in ML models in ED; and (2) ML models that are developed specifically to predict/detect sepsis in ED. In total, 24 articles are used in this review. RESULTS A summary of prehospital data used to identify time-sensitive conditions earlier in ED is provided. Literature related to use of ML models for early identification of sepsis in ED is limited and no studies were found related to ML models using prehospital data in prediction/early identification of sepsis in ED. Among those using ED data, ML models outperform traditional statistical models. In addition, the use of the free-text elements and natural language processing (NLP) methods could result in better prediction of sepsis in ED. CONCLUSION This study reviews the use of prehospital data in early decision-making in ED and suggests that researchers utilize such data elements for prediction/early identification of sepsis in ML-based approaches.
Collapse
Affiliation(s)
- Manushi D. Desai
- Marcella Niehoff School of Nursing, Loyola University Chicago, Maywood, Illinois, United States
| | - Mohammad S. Tootooni
- Department of Health Informatics and Data Science, Parkinson School of Health Sciences and Public Health, Loyola University Chicago, Maywood, Illinois, United States
| | - Kathleen L. Bobay
- Department of Health Informatics and Data Science, Parkinson School of Health Sciences and Public Health, Loyola University Chicago, Maywood, Illinois, United States,Address for correspondence Kathleen L. Bobay, PhD, RN, FAAN Department of Health Informatics and Data Science, Parkinson School of Health Sciences and Public Health, Marcella Niehoff School of Nursing, Loyola University Chicago2160 South First Avenue, Maywood, IL 60153United States
| |
Collapse
|
38
|
Harford S, Del Rios M, Heinert S, Weber J, Markul E, Tataris K, Campbell T, Vanden Hoek T, Darabi H. A machine learning approach for modeling decisions in the out of hospital cardiac arrest care workflow. BMC Med Inform Decis Mak 2022; 22:21. [PMID: 35078470 PMCID: PMC8787933 DOI: 10.1186/s12911-021-01730-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2021] [Accepted: 12/08/2021] [Indexed: 01/21/2023] Open
Abstract
BACKGROUND A growing body of research has shown that machine learning (ML) can be a useful tool to predict how different variable combinations affect out-of-hospital cardiac arrest (OHCA) survival outcomes. However, there remain significant research gaps on the utilization of ML models for decision-making and their impact on survival outcomes. The purpose of this study was to develop ML models that effectively predict hospital's practice to perform coronary angiography (CA) in adult patients after OHCA and subsequent neurologic outcomes. METHODS We utilized all (N = 2398) patients treated by the Chicago Fire Department Emergency Medical Services included in the Cardiac Arrest Registry to Enhance Survival (CARES) between 2013 and 2018 who survived to hospital admission to develop, test, and analyze ML models for decisions after return of spontaneous circulation (ROSC) and patient survival. ML classification models, including the Embedded Fully Convolutional Network (EFCN) model, were compared based on their ability to predict post-ROSC decisions and survival. RESULTS The EFCN classification model achieved the best results across tested ML algorithms. The area under the receiver operating characteristic curve (AUROC) for CA and Survival were 0.908 and 0.896 respectively. Through cohort analyses, our model predicts that 18.3% (CI 16.4-20.2) of patients should receive a CA that did not originally, and 30.1% (CI 28.5-31.7) of these would experience improved survival outcomes. CONCLUSION ML modeling effectively predicted hospital decisions and neurologic outcomes. ML modeling may serve as a quality improvement tool to inform system level OHCA policies and treatment protocols.
Collapse
Affiliation(s)
- Samuel Harford
- grid.185648.60000 0001 2175 0319Department of Mechanical and Industrial Engineering, University of Illinois at Chicago, Chicago, IL USA
| | - Marina Del Rios
- Department of Emergency Medicine, University of Iowa - Carver College of Medicine, Iowa City, IA, USA.
| | - Sara Heinert
- grid.430387.b0000 0004 1936 8796Department of Emergency Medicine, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ USA
| | - Joseph Weber
- grid.413120.50000 0004 0459 2250Department of Emergency Medicine, John H. Stroger, Jr. Hospital, Chicago, IL USA
| | - Eddie Markul
- grid.413330.60000 0004 0435 6194Illinois Masonic Medical Center, Chicago, IL USA
| | - Katie Tataris
- grid.170205.10000 0004 1936 7822Department of Emergency Medicine, University of Chicago, Chicago, IL USA
| | - Teri Campbell
- grid.185648.60000 0001 2175 0319Department of Emergency Medicine, University of Illinois at Chicago, Chicago, IL USA
| | - Terry Vanden Hoek
- grid.185648.60000 0001 2175 0319Department of Emergency Medicine, University of Illinois at Chicago, Chicago, IL USA
| | - Houshang Darabi
- grid.185648.60000 0001 2175 0319Department of Mechanical and Industrial Engineering, University of Illinois at Chicago, Chicago, IL USA
| |
Collapse
|
39
|
Wong XY, Ang YK, Li K, Chin YH, Lam SSW, Tan KBK, Chua MCH, Ong MEH, Liu N, Pourghaderi AR, Ho AFW. Development and validation of the SARICA score to predict survival after return of spontaneous circulation in out of hospital cardiac arrest using an interpretable machine learning framework. Resuscitation 2021; 170:126-133. [PMID: 34843878 DOI: 10.1016/j.resuscitation.2021.11.029] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2021] [Revised: 11/19/2021] [Accepted: 11/22/2021] [Indexed: 01/17/2023]
Abstract
BACKGROUND Accurate and timely prognostication of patients with out-of-hospital cardiac arrest (OHCA) who achieved the return of spontaneous circulation (ROSC) is crucial in clinical decision-making, resource allocation, and communications with next-of-kins. We aimed to develop the Survival After ROSC in Cardiac Arrest (SARICA), a practical clinical decision tool to predict survival in OHCA patients who attained ROSC. METHODS We utilized real-world Singapore data from the population-based Pan-Asian Resuscitation Outcomes Study between 2010-2018. We excluded patients without ROSC. The dataset was segmented into training (60%), validation (20%) and testing (20%) cohorts. The primary endpoint was survival (to 30-days or hospital discharge). AutoScore, an interpretable machine-learning based clinical score generation algorithm, was used to develop SARICA. Candidate factors were chosen based on objective demographic and clinical factors commonly available at the time of admission. Performance of SARICA was evaluated based on receiver-operating curve (ROC) analyses. RESULTS 5970 patients were included, of which 855 (14.3%) survived. A three-variable model was determined to be most parsimonious. Prehospital ROSC, age, and initial heart rhythm were identified for inclusion via random forest selection. Finally, SARICA consisted of these 3 variables and ranged from 0 to 10 points, achieving an area under the ROC (AUC) of 0.87 (95% confidence interval: 0.84-0.90) within the testing cohort. CONCLUSION We developed and internally validated the SARICA score to accurately predict survival of OHCA patients with ROSC at the time of admission. SARICA is clinically practical and developed using an interpretable machine-learning framework. SARICA has unknown generalizability pending external validation studies.
Collapse
Affiliation(s)
- Xiang Yi Wong
- Pre-hospital and Emergency Research Centre, Duke-NUS Medical School, Singapore; Singapore Civil Defence Force, Ministry of Home Affairs, Singapore.
| | - Yu Kai Ang
- Pre-hospital and Emergency Research Centre, Duke-NUS Medical School, Singapore
| | - Keqi Li
- Institute of System Science, National University of Singapore, Singapore
| | - Yip Han Chin
- Yong Loo Lin School of Medicine, National University of Singapore, Singapore
| | | | | | | | - Marcus Eng Hock Ong
- Department of Emergency Medicine, Singapore General Hospital, Singapore; Health Services & Systems Research, Duke-NUS Medical School, Singapore
| | - Nan Liu
- Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore
| | - Ahmad Reza Pourghaderi
- Health Services Research Centre, SingHealth, Singapore; Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore
| | - Andrew Fu Wah Ho
- Pre-hospital and Emergency Research Centre, Duke-NUS Medical School, Singapore; Department of Emergency Medicine, Singapore General Hospital, Singapore.
| | | |
Collapse
|
40
|
Elbaz-Greener G, Carasso S, Maor E, Gallimidi L, Yarkoni M, Wijeysundera HC, Abend Y, Dagan Y, Lerman A, Amir O. Clinical Predictors of Mortality in Prehospital Distress Calls by Emergency Medical Service Subscribers. J Clin Med 2021; 10:jcm10225355. [PMID: 34830638 PMCID: PMC8624120 DOI: 10.3390/jcm10225355] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2021] [Revised: 11/02/2021] [Accepted: 11/15/2021] [Indexed: 11/16/2022] Open
Abstract
(1) Introduction: Most studies rely on in-hospital data to predict cardiovascular risk and do not include prehospital information that is substantially important for early decision making. The aim of the study was to define clinical parameters in the prehospital setting, which may affect clinical outcomes. (2) Methods: In this population-based study, we performed a retrospective analysis of emergency calls that were made by patients to the largest private emergency medical services (EMS) in Israel, SHL Telemedicine Ltd., who were treated on-site by the EMS team. Demographics, clinical characteristics, and clinical outcomes were analyzed. Mortality was evaluated at three time points: 1, 3, and 12 months’ follow-up. The first EMS prehospital measurements of the systolic blood pressure (SBP) were recorded and analyzed. Logistic regression analyses were performed. (3) Results: A total of 64,320 emergency calls were included with a follow-up of 12 months post index EMS call. Fifty-five percent of patients were men and the mean age was 70.2 ± 13.1 years. During follow-up of 12 months, 7.6% of patients died. Age above 80 years (OR 3.34; 95% CI 3.03–3.69, p < 0.005), first EMS SBP ≤ 130 mm Hg (OR 2.61; 95% CI 2.36–2.88, p < 0.005), dyspnea at presentation (OR 2.55; 95% CI 2.29–2.83, p < 0001), and chest pain with ischemic ECG changes (OR 1.95; 95% CI 1.71–2.23, p < 0.001) were the highest predictors of 1 month mortality and remained so for mortality at 3 and 12 months. In contrast, history of hypertension and first EMS prehospital SBP ≥ 160 mm Hg were significantly associated with decreased mortality at 1, 3 and 12 months. (4) Conclusions: We identified risk predictors for all-cause mortality in a large cohort of patients during prehospital EMS calls. Age over 80 years, first EMS-documented prehospital SBP < 130 mm Hg, and dyspnea at presentation were the most profound risk predictors for short- and long-term mortality. The current study demonstrates that in prehospital EMS call settings, several parameters can be used to improve prioritization and management of high-risk patients.
Collapse
Affiliation(s)
- Gabby Elbaz-Greener
- Hadassah Medical Center, Cardiology Department, Faculty of Medicine, Hebrew University Jerusalem, Jerusalem 91905, Israel; (M.Y.); (O.A.)
- Correspondence: ; Tel.: +972-(2)6776564; Fax: +972-(2)6411028
| | - Shemy Carasso
- Baruch-Pade Poriya Medical Center, Cardiology Department, Azrieli Faculty of Medicine in the Galilee, Bar-Ilan University, Safed 52100, Israel;
| | - Elad Maor
- Leviev Heart Center, Sheba Medical Center and Sackler School of Medicine, Tel Aviv University, Tel-Aviv 69978, Israel;
| | - Lior Gallimidi
- SHL Telemedicine Ltd., Tel-Aviv 67891, Israel; (L.G.); (Y.A.); (Y.D.); (A.L.)
| | - Merav Yarkoni
- Hadassah Medical Center, Cardiology Department, Faculty of Medicine, Hebrew University Jerusalem, Jerusalem 91905, Israel; (M.Y.); (O.A.)
| | - Harindra C. Wijeysundera
- Schulich Heart Centre, Division of Cardiology, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, ON M5S 1A1, Canada;
| | - Yitzhak Abend
- SHL Telemedicine Ltd., Tel-Aviv 67891, Israel; (L.G.); (Y.A.); (Y.D.); (A.L.)
| | - Yinon Dagan
- SHL Telemedicine Ltd., Tel-Aviv 67891, Israel; (L.G.); (Y.A.); (Y.D.); (A.L.)
| | - Amir Lerman
- SHL Telemedicine Ltd., Tel-Aviv 67891, Israel; (L.G.); (Y.A.); (Y.D.); (A.L.)
- Department of Cardiovascular Disease, Mayo Clinic, Rochester, MN 55902, USA
| | - Offer Amir
- Hadassah Medical Center, Cardiology Department, Faculty of Medicine, Hebrew University Jerusalem, Jerusalem 91905, Israel; (M.Y.); (O.A.)
- Baruch-Pade Poriya Medical Center, Cardiology Department, Azrieli Faculty of Medicine in the Galilee, Bar-Ilan University, Safed 52100, Israel;
| |
Collapse
|
41
|
Petch J, Di S, Nelson W. Opening the black box: the promise and limitations of explainable machine learning in cardiology. Can J Cardiol 2021; 38:204-213. [PMID: 34534619 DOI: 10.1016/j.cjca.2021.09.004] [Citation(s) in RCA: 145] [Impact Index Per Article: 36.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2021] [Revised: 08/23/2021] [Accepted: 09/08/2021] [Indexed: 11/29/2022] Open
Abstract
Many clinicians remain wary of machine learning due to long-standing concerns about "black box" models. "Black box" is shorthand for models that are sufficiently complex that they are not straightforwardly interpretable to humans. Lack of interpretability in predictive models can undermine trust in those models, especially in health care where so many decisions are literally life and death. There has recently been an explosion of research in the field of explainable machine learning aimed at addressing these concerns. The promise of explainable machine learning is considerable, but it is important for cardiologists who may encounter these techniques in clinical decision support tools or novel research papers to have a critical understanding of both their strengths and their limitations. This paper reviews key concepts and techniques in the field of explainable machine learning as they apply to cardiology. Key concepts reviewed include interpretability versus explainability and global versus local explanations. Techniques demonstrated include permutation importance, surrogate decision trees, local interpretable model-agnostic explanations, and partial dependence plots. We discuss several limitations with explainability techniques, focusing on the how the nature of explanations as approximations may omit important information about how black box models work and why they make certain predictions. We conclude by proposing a rule of thumb about when it is appropriate to use black box models with explanations, rather than interpretable models.
Collapse
Affiliation(s)
- Jeremy Petch
- Centre for Data Science and Digital Health, Hamilton Health Sciences; Institute of Health Policy, Management and Evaluation, University of Toronto; Division of Cardiology, Department of Medicine, McMaster University; Population Health Research Institute.
| | - Shuang Di
- Centre for Data Science and Digital Health, Hamilton Health Sciences; Dalla Lana School of Public Health, University of Toronto
| | - Walter Nelson
- Centre for Data Science and Digital Health, Hamilton Health Sciences; Department of Statistical Sciences, University of Toronto
| |
Collapse
|
42
|
Lim D, Park SY, Choi B, Kim SH, Ryu JH, Kim YH, Sung AJ, Bae BK, Kim HB. The Comparison of Emergency Medical Service Responses to and Outcomes of Out-of-hospital Cardiac Arrest before and during the COVID-19 Pandemic in an Area of Korea. J Korean Med Sci 2021; 36:e255. [PMID: 34519188 PMCID: PMC8438185 DOI: 10.3346/jkms.2021.36.e255] [Citation(s) in RCA: 24] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/28/2021] [Accepted: 08/29/2021] [Indexed: 12/20/2022] Open
Abstract
BACKGROUND Since the declaration of the coronavirus disease 2019 (COVID-19) pandemic, COVID-19 has affected the responses of emergency medical service (EMS) systems to cases of out-of-hospital cardiac arrest (OHCA). The purpose of this study was to identify the impact of the COVID-19 pandemic on EMS responses to and outcomes of adult OHCA in an area of South Korea. METHODS This was a retrospective observational study of adult OHCA patients attended by EMS providers comparing the EMS responses to and outcomes of adult OHCA during the COVID-19 pandemic to those during the pre-COVID-19 period. Propensity score matching was used to compare the survival rates, and logistic regression analysis was used to assess the impact of the COVID-19 pandemic on the survival of OHCA patients. RESULTS A total of 891 patients in the pre-COVID-19 group and 1,063 patients in the COVID-19 group were included in the final analysis. During the COVID-19 period, the EMS call time was shifted to a later time period (16:00-24:00, P < 0.001), and the presence of an initial shockable rhythm was increased (pre-COVID-19 vs. COVID-19, 7.97% vs. 11.95%, P = 0.004). The number of tracheal intubations decreased (5.27% vs. 1.22%, P < 0.001), and the use of mechanical chest compression devices (30.53% vs. 44.59%, P < 0.001) and EMS response time (median [quartile 1-quartile 3], 7 [5-10] vs. 8 [6-11], P < 0.001) increased. After propensity score matching, the survival at admission rate (22.52% vs. 18.24%, P = 0.025), survival to discharge rate (7.77% vs. 5.52%, P = 0.056), and favorable neurological outcome (5.97% vs. 3.49%, P < 0.001) decreased. In the propensity score matching analysis of the impact of COVID-19, odds ratios of 0.768 (95% confidence interval [CI], 0.592-0.995) for survival at admission and 0.693 (95% CI, 0.446-1.077) for survival to discharge were found. CONCLUSION During the COVID-19 period, there were significant changes in the EMS responses to OHCA. These changes are considered to be partly due to social distancing measures. As a result, the proportion of patients with an initial shockable rhythm in the COVID-19 period was greater than that in the pre-COVID-19 period, but the final survival rate and favorable neurological outcome were lower.
Collapse
Affiliation(s)
- Daesung Lim
- Department of Emergency Medicine, Gyeongsang National University College of Medicine, Gyeongsang National University Changwon Hospital, Changwon, Korea
| | - Song Yi Park
- Department of Emergency Medicine, Dong-A University College of Medicine, Dong-A University Hospital, Busan, Korea.
| | - Byungho Choi
- Department of Emergency Medicine, University of Ulsan College of Medicine, Ulsan University Hospital, Ulsan, Korea
| | - Sun Hyu Kim
- Department of Emergency Medicine, University of Ulsan College of Medicine, Ulsan University Hospital, Ulsan, Korea
| | - Ji Ho Ryu
- Department of Emergency Medicine, Pusan National University College of Medicine, Pusan National University Yangsan Hospital, Busan, Korea
| | - Yong Hwan Kim
- Department of Emergency Medicine, Samsung Changwon Hospital, Sungkyunkwan University School of Medicine, Changwon, Korea
| | - Ae Jin Sung
- Department of Emergency Medicine, Gyeongsang National University Hospital, Jinju, Korea
| | - Byung Kwan Bae
- Department of Emergency Medicine, Pusan National University College of Medicine, Pusan National University Hospital, Busan, Korea
| | - Han Byeol Kim
- Department of Emergency Medicine, Inje University Haeundae Paik Hospital, Busan, Korea
| |
Collapse
|
43
|
Awad EM, Humphries KH, Grunau BE, Christenson JM. Premenopausal-aged females have no neurological outcome advantage after out-of-hospital cardiac arrest: A multilevel analysis of North American populations. Resuscitation 2021; 166:58-65. [PMID: 34271125 DOI: 10.1016/j.resuscitation.2021.06.024] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2021] [Revised: 05/14/2021] [Accepted: 06/20/2021] [Indexed: 11/28/2022]
Abstract
AIM We investigated the impact of premenopausal age on neurological function at hospital discharge in patients with out-of-hospital cardiac arrest (OHCA). We hypothesized that premenopausal-aged females (18-47 years of age) with OHCA would have a higher probability of survival with favourable neurological function at hospital discharge compared with males of the same age group, older males, and older females (>53 years of age). METHODS Retrospective analyses of data from the Resuscitation Outcomes Consortium multi-center randomized controlled trial (June 2011-May 2015). We included adults with non-traumatic OHCA treated by emergency medical service. We stratified the cohort into four groups by age and sex: premenopausal-aged females (18-47 years of age), older females (≥53 years old), younger males (18-47 years of age), and older male. We used multilevel logistic regression to examine the association between age-sex and favourable neurological outcomes (modified Rankin Scale ≤ 3). RESULTS In total, 23,725 patients were included: 1050 (4.5%) premenopausal females; 1930 (8.1%) younger males; 7569 (31.9%) older females; and 13,176 (55.5%) older males. The multilevel analysis showed no difference in neurological outcome between younger males and younger females (OR 0.95, 95% CI 0.69-1.32, p = 0.75). Both older females (OR 0.36, 95% CI 0. 0.26-0.48, p < 0.001) and older males (OR 0.52, 95% CI 0.39-0.69, p < 0.001) had a significantly lower odds of favourable neurological outcome than younger females. Among all groups, older females had the worst outcomes. CONCLUSIONS We did not detect an association between premenopausal age and survival with good neurological outcome, suggesting females sex hormones do not impact OHCA outcomes. Our findings are not in line with results from other studies. Studies that rigorously evaluate menopausal status are required to definitively assess the impact of female sex hormones on outcomes.
Collapse
Affiliation(s)
- Emad M Awad
- Faculty of Medicine, Experimental Medicine, University of British Columbia, Vancouver, British Columbia, Canada; Centre for Health Evaluation and Outcome Sciences, Vancouver, British Columbia, Canada.
| | - Karin H Humphries
- Division of Cardiology, Faculty of Medicine, University of British Columbia, Vancouver, British Columbia, Canada; BC Centre for Improved Cardiovascular Health, Vancouver, British Columbia, Canada; Centre for Health Evaluation and Outcome Sciences, Vancouver, British Columbia, Canada
| | - Brian E Grunau
- Department of Emergency Medicine, St. Paul's Hospital, Vancouver, British Columbia, Canada; Department of Emergency Medicine, University of British Columbia, Vancouver, British Columbia, Canada; Centre for Health Evaluation and Outcome Sciences, Vancouver, British Columbia, Canada
| | - Jim M Christenson
- Department of Emergency Medicine, St. Paul's Hospital, Vancouver, British Columbia, Canada; Department of Emergency Medicine, University of British Columbia, Vancouver, British Columbia, Canada; Centre for Health Evaluation and Outcome Sciences, Vancouver, British Columbia, Canada
| |
Collapse
|
44
|
Olasveengen TM, Semeraro F, Ristagno G, Castren M, Handley A, Kuzovlev A, Monsieurs KG, Raffay V, Smyth M, Soar J, Svavarsdóttir H, Perkins GD. [Basic life support]. Notf Rett Med 2021; 24:386-405. [PMID: 34093079 PMCID: PMC8170637 DOI: 10.1007/s10049-021-00885-x] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 04/19/2021] [Indexed: 12/13/2022]
Abstract
The European Resuscitation Council has produced these basic life support guidelines, which are based on the 2020 International Consensus on Cardiopulmonary Resuscitation Science with Treatment Recommendations. The topics covered include cardiac arrest recognition, alerting emergency services, chest compressions, rescue breaths, automated external defibrillation (AED), cardiopulmonary resuscitation (CPR) quality measurement, new technologies, safety, and foreign body airway obstruction.
Collapse
Affiliation(s)
- Theresa M. Olasveengen
- Department of Anesthesiology, Oslo University Hospital and Institute of Clinical Medicine, University of Oslo, Oslo, Norwegen
| | - Federico Semeraro
- Department of Anaesthesia, Intensive Care and Emergency Medical Services, Maggiore Hospital, Bologna, Italien
| | - Giuseppe Ristagno
- Department of Anesthesiology, Intensive Care and Emergency, Fondazione IRCCS Ca’ Granda, Ospedale Maggiore Policlinico, Mailand, Italien
- Department of Pathophysiology and Transplantation, University of Milan, Mailand, Italien
| | - Maaret Castren
- Emergency Medicine, Helsinki University and Department of Emergency Medicine and Services, Helsinki University Hospital, Helsinki, Finnland
| | | | - Artem Kuzovlev
- Federal Research and Clinical Center of Intensive Care Medicine and Rehabilitology, V.A. Negovsky Research Institute of General Reanimatology, Moskau, Russland
| | - Koenraad G. Monsieurs
- Department of Emergency Medicine, Antwerp University Hospital and University of Antwerp, Antwerpen, Belgien
| | - Violetta Raffay
- Department of Medicine, School of Medicine, European University Cyprus, Nikosia, Zypern
| | - Michael Smyth
- Warwick Clinical Trials Unit, Warwick Medical School, University of Warwick, CV4 7AL Coventry, Großbritannien
- West Midlands Ambulance Service, DY5 1LX Brierly Hill, West Midlands Großbritannien
| | - Jasmeet Soar
- Southmead Hospital, North Bristol NHS Trust, Bristol, Großbritannien
| | - Hildigunnur Svavarsdóttir
- Akureyri Hospital, Akureyri, Island
- Institute of Health Science Research, University of Akureyri, Akureyri, Island
| | - Gavin D. Perkins
- Warwick Clinical Trials Unit, Warwick Medical School, University of Warwick, CV4 7AL Coventry, Großbritannien
- University Hospitals Birmingham, B9 5SS Birmingham, Großbritannien
| |
Collapse
|
45
|
Olasveengen TM, Semeraro F, Ristagno G, Castren M, Handley A, Kuzovlev A, Monsieurs KG, Raffay V, Smyth M, Soar J, Svavarsdottir H, Perkins GD. European Resuscitation Council Guidelines 2021: Basic Life Support. Resuscitation 2021; 161:98-114. [PMID: 33773835 DOI: 10.1016/j.resuscitation.2021.02.009] [Citation(s) in RCA: 291] [Impact Index Per Article: 72.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/06/2023]
Abstract
The European Resuscitation Council has produced these basic life support guidelines, which are based on the 2020 International Consensus on Cardiopulmonary Resuscitation Science with Treatment Recommendations. The topics covered include cardiac arrest recognition, alerting emergency services, chest compressions, rescue breaths, automated external defibrillation (AED), CPR quality measurement, new technologies, safety, and foreign body airway obstruction.
Collapse
Affiliation(s)
- Theresa M Olasveengen
- Department of Anesthesiology, Oslo University Hospital and Institute of Clinical Medicine, University of Oslo, Norway.
| | - Federico Semeraro
- Department of Anaesthesia, Intensive Care and Emergency Medical Services, Maggiore Hospital, Bologna, Italy
| | - Giuseppe Ristagno
- Department of Anesthesiology, Intensive Care and Emergency, Fondazione IRCCS Ca' Granda, Ospedale Maggiore Policlinico, Milano, Italy; Department of Pathophysiology and Transplantation, University of Milan, Italy
| | - Maaret Castren
- Emergency Medicine, Helsinki University and Department of Emergency Medicine and Services, Helsinki University Hospital, Helsinki, Finland
| | | | - Artem Kuzovlev
- Federal Research and Clinical Center of Intensive Care Medicine and Rehabilitology, V.A. Negovsky Research Institute of General Reanimatology, Moscow, Russia
| | - Koenraad G Monsieurs
- Department of Emergency Medicine, Antwerp University Hospital and University of Antwerp, Belgium
| | - Violetta Raffay
- Department of Medicine, School of Medicine, European University Cyprus, Nicosia, Cyprus
| | - Michael Smyth
- Warwick Clinical Trials Unit, Warwick Medical School, University of Warwick, Coventry CV4 7AL, United Kingdom; West Midlands Ambulance Service and Midlands Air Ambulance, Brierly Hill, West Midlands DY5 1LX, United Kingdom
| | - Jasmeet Soar
- Southmead Hospital, North Bristol NHS Trust, Bristol, United Kingdom
| | - Hildigunnur Svavarsdottir
- Akureyri Hospital, Akureyri, Iceland; Institute of Health Science Research, University of Akureyri, Akureyri, Iceland
| | - Gavin D Perkins
- Warwick Clinical Trials Unit, Warwick Medical School, University of Warwick, Coventry CV4 7AL, United Kingdom; University Hospitals Birmingham, Birmingham B9 5SS, United Kingdom
| |
Collapse
|
46
|
Seo DW, Yi H, Bae HJ, Kim YJ, Sohn CH, Ahn S, Lim KS, Kim N, Kim WY. Prediction of Neurologically Intact Survival in Cardiac Arrest Patients without Pre-Hospital Return of Spontaneous Circulation: Machine Learning Approach. J Clin Med 2021; 10:jcm10051089. [PMID: 33807882 PMCID: PMC7961400 DOI: 10.3390/jcm10051089] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2021] [Revised: 02/28/2021] [Accepted: 03/01/2021] [Indexed: 01/03/2023] Open
Abstract
Current multimodal approaches for the prognostication of out-of-hospital cardiac arrest (OHCA) are based mainly on the prediction of poor neurological outcomes; however, it is challenging to identify patients expected to have a favorable outcome, especially before the return of spontaneous circulation (ROSC). We developed and validated a machine learning-based system to predict good outcome in OHCA patients before ROSC. This prospective, multicenter, registry-based study analyzed non-traumatic OHCA data collected between October 2015 and June 2017. We used information available before ROSC as predictor variables, and the primary outcome was neurologically intact survival at discharge, defined as cerebral performance category 1 or 2. The developed models’ robustness were evaluated and compared with various score metrics to confirm their performance. The model using a voting classifier had the best performance in predicting good neurological outcome (area under the curve = 0.926). We confirmed that the six top-weighted variables predicting neurological outcomes, such as several duration variables after the instant of OHCA and several electrocardiogram variables in the voting classifier model, showed significant differences between the two neurological outcome groups. These findings demonstrate the potential utility of a machine learning model to predict good neurological outcome of OHCA patients before ROSC.
Collapse
Affiliation(s)
- Dong-Woo Seo
- Asan Medical Center, Department of Emergency Medicine, College of Medicine, University of Ulsan, Seoul 05505, Korea; (D.-W.S.); (Y.-J.K.); (C.-H.S.); (S.A.); (K.-S.L.)
- Asan Medical Center, Department of Information Medicine, College of Medicine, University of Ulsan, Seoul 05505, Korea
| | - Hahn Yi
- Asan Medical Center, Asan Institute for Life Sciences, Seoul 05505, Korea;
| | - Hyun-Jin Bae
- Asan Medical Center, Department of Medicine, College of Medicine, University of Ulsan, Seoul 05505, Korea;
| | - Youn-Jung Kim
- Asan Medical Center, Department of Emergency Medicine, College of Medicine, University of Ulsan, Seoul 05505, Korea; (D.-W.S.); (Y.-J.K.); (C.-H.S.); (S.A.); (K.-S.L.)
| | - Chang-Hwan Sohn
- Asan Medical Center, Department of Emergency Medicine, College of Medicine, University of Ulsan, Seoul 05505, Korea; (D.-W.S.); (Y.-J.K.); (C.-H.S.); (S.A.); (K.-S.L.)
| | - Shin Ahn
- Asan Medical Center, Department of Emergency Medicine, College of Medicine, University of Ulsan, Seoul 05505, Korea; (D.-W.S.); (Y.-J.K.); (C.-H.S.); (S.A.); (K.-S.L.)
| | - Kyoung-Soo Lim
- Asan Medical Center, Department of Emergency Medicine, College of Medicine, University of Ulsan, Seoul 05505, Korea; (D.-W.S.); (Y.-J.K.); (C.-H.S.); (S.A.); (K.-S.L.)
| | - Namkug Kim
- Asan Medical Center, Department of Medicine, College of Medicine, University of Ulsan, Seoul 05505, Korea;
- Asan Medical Center, Department of Convergence Medicine, College of Medicine, University of Ulsan, Seoul 05505, Korea
- Correspondence: (N.K.); (W.-Y.K.); Tel.: +82-2-3010-6573 (N.K.); +82-2-3010-5670 (W.-Y.K.)
| | - Won-Young Kim
- Asan Medical Center, Department of Emergency Medicine, College of Medicine, University of Ulsan, Seoul 05505, Korea; (D.-W.S.); (Y.-J.K.); (C.-H.S.); (S.A.); (K.-S.L.)
- Correspondence: (N.K.); (W.-Y.K.); Tel.: +82-2-3010-6573 (N.K.); +82-2-3010-5670 (W.-Y.K.)
| |
Collapse
|
47
|
Bylow H, Rawshani A, Claesson A, Lepp M, Herlitz J. Characteristics and outcome after out-of-hospital cardiac arrest with the emphasis on workplaces: an observational study from the Swedish Registry of Cardiopulmonary Resuscitation. Resusc Plus 2021; 5:100090. [PMID: 34223355 PMCID: PMC8244450 DOI: 10.1016/j.resplu.2021.100090] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2020] [Revised: 12/17/2020] [Accepted: 01/25/2021] [Indexed: 11/19/2022] Open
Abstract
Background Characteristics and outcome in out-of-hospital cardiac arrest (OHCA) occurring at workplaces is sparsely studied. Aim To describe (1) the characteristics and 30-day survival of OHCAs occurring at workplaces in comparison to OHCAs at other places and (2) factors associated with survival after OHCAs at workplaces. Methods Data on OHCAs were obtained from the Swedish Registry of Cardiopulmonary Resuscitation from 1 January 2008 to 31 December 2018. Characteristics and factors associated with survival were analysed with emphasis on the location of OHCAs. Results Among 47,685 OHCAs, 529 cases (1%) occurred at workplaces. Overall, in the fully adjusted model, all locations of OHCA, with the exception of crowded public places, displayed significantly lower probability of survival than workplaces. Exhibiting a shockable rhythm was the strongest predictor of survival among patients with OHCAs at workplaces; odds ratio (95% CI) 5.80 (2.92-12.31). Odds ratio for survival for women was 2.08 (95% CI 1.07-4.03), compared with men. At workplaces other than private offices, odds ratio for survival was 0.41 (95% CI 0.16-0.95) for cases who did not receive bystander CPR, as compared to those who did receive CPR. Among patients who were found in a shockable rhythm were 23% defibrillated before arrival of ambulance, which was more frequent than in any other location. Conclusion Out-of-hospital cardiac arrest occurring at workplaces and crowded public places display the highest probability of survival, as compared with other places outside hospital. An initial shockable cardiac rhythm was the strongest predictor of survival for OHCA at workplaces.
Collapse
Affiliation(s)
- Helene Bylow
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Corresponding author.
| | - Araz Rawshani
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Andreas Claesson
- Department of Medicine, Centre for Resuscitation Science, Karolinska Institute, Stockholm, Sweden
| | - Margret Lepp
- Institute of Health and Care Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Østfold University College, Halden, Norway
- School of Nursing and Midwifery, Griffith University, Brisbane, Australia
| | - Johan Herlitz
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Centre of Registers Västra Götaland, Gothenburg, Sweden
- Prehospen-Centre of Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, Borås, Sweden
| |
Collapse
|
48
|
Tamminen J, Kallonen A, Hoppu S, Kalliomäki J. Machine learning model predicts short-term mortality among prehospital patients: A prospective development study from Finland. Resusc Plus 2021; 5:100089. [PMID: 34223354 PMCID: PMC8244527 DOI: 10.1016/j.resplu.2021.100089] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2020] [Revised: 01/18/2021] [Accepted: 01/20/2021] [Indexed: 10/31/2022] Open
Abstract
Aim To show whether adding blood glucose to the National Early Warning Score (NEWS) parameters in a machine learning model predicts 30-day mortality more precisely than the standard NEWS in a prehospital setting. Methods In this study, vital sign data prospectively collected from 3632 unselected prehospital patients in June 2015 were used to compare the standard NEWS to random forest models for predicting 30-day mortality. The NEWS parameters and blood glucose levels were used to develop the random forest models. Predictive performance on an unknown patient population was estimated with a ten-fold stratified cross-validation method. Results All NEWS parameters and blood glucose levels were reported in 2853 (79%) eligible patients. Within 30 days after contact with ambulance staff, 97 (3.4%) of the analysed patients had died. The area under the receiver operating characteristic curve for the 30-day mortality of the evaluated models was 0.682 (95% confidence interval [CI], 0.619-0.744) for the standard NEWS, 0.735 (95% CI, 0.679-0.787) for the random forest-trained NEWS parameters only and 0.758 (95% CI, 0.705-0.807) for the random forest-trained NEWS parameters and blood glucose. The models predicted secondary outcomes similarly, but adding blood glucose into the random forest model slightly improved its performance in predicting short-term mortality. Conclusions Among unselected prehospital patients, a machine learning model including blood glucose and NEWS parameters had a fair performance in predicting 30-day mortality.
Collapse
Affiliation(s)
- Joonas Tamminen
- Faculty of Medicine and Health Technology, Tampere University, PO Box 2000, FI-33521 Tampere, Finland.,Emergency Medical Services, Tampere University Hospital, PO Box 2000, FI-33521 Tampere, Finland
| | - Antti Kallonen
- Faculty of Medicine and Health Technology, Tampere University, PO Box 2000, FI-33521 Tampere, Finland
| | - Sanna Hoppu
- Emergency Medical Services, Tampere University Hospital, PO Box 2000, FI-33521 Tampere, Finland
| | - Jari Kalliomäki
- Emergency Medical Services, Tampere University Hospital, PO Box 2000, FI-33521 Tampere, Finland.,Intensive Care Medicine, Tampere University Hospital, PO Box 2000, FI-33521 Tampere, Finland
| |
Collapse
|
49
|
Tang KJW, Ang CKE, Constantinides T, Rajinikanth V, Acharya UR, Cheong KH. Artificial Intelligence and Machine Learning in Emergency Medicine. Biocybern Biomed Eng 2021. [DOI: 10.1016/j.bbe.2020.12.002] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
|