1
|
Askar M, Tafavvoghi M, Småbrekke L, Bongo LA, Svendsen K. Using machine learning methods to predict all-cause somatic hospitalizations in adults: A systematic review. PLoS One 2024; 19:e0309175. [PMID: 39178283 PMCID: PMC11343463 DOI: 10.1371/journal.pone.0309175] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2024] [Accepted: 08/06/2024] [Indexed: 08/25/2024] Open
Abstract
AIM In this review, we investigated how Machine Learning (ML) was utilized to predict all-cause somatic hospital admissions and readmissions in adults. METHODS We searched eight databases (PubMed, Embase, Web of Science, CINAHL, ProQuest, OpenGrey, WorldCat, and MedNar) from their inception date to October 2023, and included records that predicted all-cause somatic hospital admissions and readmissions of adults using ML methodology. We used the CHARMS checklist for data extraction, PROBAST for bias and applicability assessment, and TRIPOD for reporting quality. RESULTS We screened 7,543 studies of which 163 full-text records were read and 116 met the review inclusion criteria. Among these, 45 predicted admission, 70 predicted readmission, and one study predicted both. There was a substantial variety in the types of datasets, algorithms, features, data preprocessing steps, evaluation, and validation methods. The most used types of features were demographics, diagnoses, vital signs, and laboratory tests. Area Under the ROC curve (AUC) was the most used evaluation metric. Models trained using boosting tree-based algorithms often performed better compared to others. ML algorithms commonly outperformed traditional regression techniques. Sixteen studies used Natural language processing (NLP) of clinical notes for prediction, all studies yielded good results. The overall adherence to reporting quality was poor in the review studies. Only five percent of models were implemented in clinical practice. The most frequently inadequately addressed methodological aspects were: providing model interpretations on the individual patient level, full code availability, performing external validation, calibrating models, and handling class imbalance. CONCLUSION This review has identified considerable concerns regarding methodological issues and reporting quality in studies investigating ML to predict hospitalizations. To ensure the acceptability of these models in clinical settings, it is crucial to improve the quality of future studies.
Collapse
Affiliation(s)
- Mohsen Askar
- Faculty of Health Sciences, Department of Pharmacy, UiT-The Arctic University of Norway, Tromsø, Norway
| | - Masoud Tafavvoghi
- Faculty of Science and Technology, Department of Computer Science, UiT-The Arctic University of Norway, Tromsø, Norway
| | - Lars Småbrekke
- Faculty of Health Sciences, Department of Pharmacy, UiT-The Arctic University of Norway, Tromsø, Norway
| | - Lars Ailo Bongo
- Faculty of Science and Technology, Department of Computer Science, UiT-The Arctic University of Norway, Tromsø, Norway
| | - Kristian Svendsen
- Faculty of Health Sciences, Department of Pharmacy, UiT-The Arctic University of Norway, Tromsø, Norway
| |
Collapse
|
2
|
Petrella RJ. The AI Future of Emergency Medicine. Ann Emerg Med 2024; 84:139-153. [PMID: 38795081 DOI: 10.1016/j.annemergmed.2024.01.031] [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: 11/03/2023] [Revised: 01/23/2024] [Accepted: 01/24/2024] [Indexed: 05/27/2024]
Abstract
In the coming years, artificial intelligence (AI) and machine learning will likely give rise to profound changes in the field of emergency medicine, and medicine more broadly. This article discusses these anticipated changes in terms of 3 overlapping yet distinct stages of AI development. It reviews some fundamental concepts in AI and explores their relation to clinical practice, with a focus on emergency medicine. In addition, it describes some of the applications of AI in disease diagnosis, prognosis, and treatment, as well as some of the practical issues that they raise, the barriers to their implementation, and some of the legal and regulatory challenges they create.
Collapse
Affiliation(s)
- Robert J Petrella
- Emergency Departments, CharterCARE Health Partners, Providence and North Providence, RI; Emergency Department, Boston VA Medical Center, Boston, MA; Emergency Departments, Steward Health Care System, Boston and Methuen, MA; Harvard Medical School, Boston, MA; Department of Chemistry and Chemical Biology, Harvard University, Cambridge, MA; Department of Medicine, Brigham and Women's Hospital, Boston, MA.
| |
Collapse
|
3
|
O'Neill M, Cheskes S, Drennan I, Keown-Stoneman C, Lin S, Nolan B. Injury severity bias in missing prehospital vital signs: Prevalence and implications for trauma registries. Injury 2024:111747. [PMID: 39054233 DOI: 10.1016/j.injury.2024.111747] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/07/2024] [Revised: 06/17/2024] [Accepted: 07/16/2024] [Indexed: 07/27/2024]
Abstract
BACKGROUND Vital signs are important factors in assessing injury severity and guiding trauma resuscitation, especially among severely injured patients. Despite this, physiological data are frequently missing from trauma registries. This study aimed to evaluate the extent of missing prehospital data in a hospital-based trauma registry and to assess the associations between prehospital physiological data completeness and indicators of injury severity. METHODS A retrospective review was conducted on all adult trauma patients brought directly to a level 1 trauma center in Toronto, Ontario by paramedics from January 1, 2015, to December 31, 2019. The proportion of missing data was evaluated for each variable and patterns of missingness were assessed. To investigate the associations between prehospital data completeness and injury severity factors, descriptive and unadjusted logistic regression analyses were performed. RESULTS A total of 3,528 patients were included. We considered prehospital data missing if any of heart rate, systolic blood pressure, respiratory rate or oxygen saturation were incomplete. Each individual variable was missing from the registry in approximately 20 % of patients, with oxygen saturation missing most frequently (n = 831; 23.6 %). Over 25 % (n = 909) of patients were missing at least one prehospital vital sign, of which 69.1 % (n = 628) were missing all four of these variables. Patients with incomplete data were more severely injured, had higher mortality, and more frequently received lifesaving interventions such as blood transfusion and intubation. Patients were most likely to have missing prehospital physiological data if they died in the trauma bay (unadjusted OR: 9.79; 95 % CI: 6.35-15.10), did not survive to discharge (unadjusted OR: 3.55; 95 % CI: 2.76-4.55), or had a prehospital GCS less than 9 (OR: 3.24; 95 % CI: 2.59-4.06). CONCLUSION In this single center trauma registry, key prehospital variables were frequently missing, particularly among more severely injured patients. Patients with missing data had higher mortality, more severe injury characteristics and received more life-saving interventions in the trauma bay, suggesting an injury severity bias in prehospital vital sign missingness. To ensure the validity of research based on trauma registry data, patterns of missingness must be carefully considered to ensure missing data is appropriately addressed.
Collapse
Affiliation(s)
- Melissa O'Neill
- Institute of Medical Science, University of Toronto, Toronto, ON, Canada; Li Ka Shing Knowledge Institute, St. Michael's Hospital, Toronto, ON, Canada.
| | - Sheldon Cheskes
- Institute of Medical Science, University of Toronto, Toronto, ON, Canada; Li Ka Shing Knowledge Institute, St. Michael's Hospital, Toronto, ON, Canada; Sunnybrook Centre for Prehospital Medicine, Toronto, ON, Canada; Sunnybrook Research Institute, Sunnybrook Health Science Centre, Toronto, ON, Canada; Department of Family and Community Medicine, Division of Emergency Medicine, University of Toronto, Toronto, ON, Canada
| | - Ian Drennan
- Li Ka Shing Knowledge Institute, St. Michael's Hospital, Toronto, ON, Canada; Sunnybrook Centre for Prehospital Medicine, Toronto, ON, Canada; Sunnybrook Research Institute, Sunnybrook Health Science Centre, Toronto, ON, Canada; Department of Family and Community Medicine, Division of Emergency Medicine, University of Toronto, Toronto, ON, Canada; Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, ON, Canada
| | - Charles Keown-Stoneman
- Li Ka Shing Knowledge Institute, St. Michael's Hospital, Toronto, ON, Canada; Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada
| | - Steve Lin
- Institute of Medical Science, University of Toronto, Toronto, ON, Canada; Li Ka Shing Knowledge Institute, St. Michael's Hospital, Toronto, ON, Canada; Department of Emergency Medicine, St. Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada; Division of Emergency Medicine, Department of Medicine, University of Toronto, Toronto, ON, Canada
| | - Brodie Nolan
- Institute of Medical Science, University of Toronto, Toronto, ON, Canada; Li Ka Shing Knowledge Institute, St. Michael's Hospital, Toronto, ON, Canada; Department of Emergency Medicine, St. Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada; Division of Emergency Medicine, Department of Medicine, University of Toronto, Toronto, ON, Canada
| |
Collapse
|
4
|
Ferri P, Lomonaco V, Passaro LC, Félix-De Castro A, Sánchez-Cuesta P, Sáez C, García-Gómez JM. Deep continual learning for medical call incidents text classification under the presence of dataset shifts. Comput Biol Med 2024; 175:108548. [PMID: 38718666 DOI: 10.1016/j.compbiomed.2024.108548] [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: 09/08/2023] [Revised: 04/11/2024] [Accepted: 04/28/2024] [Indexed: 05/15/2024]
Abstract
The aim of this work is to develop and evaluate a deep classifier that can effectively prioritize Emergency Medical Call Incidents (EMCI) according to their life-threatening level under the presence of dataset shifts. We utilized a dataset consisting of 1982746 independent EMCI instances obtained from the Health Services Department of the Region of Valencia (Spain), with a time span from 2009 to 2019 (excluding 2013). The dataset includes free text dispatcher observations recorded during the call, as well as a binary variable indicating whether the event was life-threatening. To evaluate the presence of dataset shifts, we examined prior probability shifts, covariate shifts, and concept shifts. Subsequently, we designed and implemented four deep Continual Learning (CL) strategies-cumulative learning, continual fine-tuning, experience replay, and synaptic intelligence-alongside three deep CL baselines-joint training, static approach, and single fine-tuning-based on DistilBERT models. Our results demonstrated evidence of prior probability shifts, covariate shifts, and concept shifts in the data. Applying CL techniques had a statistically significant (α=0.05) positive impact on both backward and forward knowledge transfer, as measured by the F1-score, compared to non-continual approaches. We can argue that the utilization of CL techniques in the context of EMCI is effective in adapting deep learning classifiers to changes in data distributions, thereby maintaining the stability of model performance over time. To our knowledge, this study represents the first exploration of a CL approach using real EMCI data.
Collapse
Affiliation(s)
- Pablo Ferri
- Biomedical Data Science Laboratory (BDSLab), Instituto de Aplicaciones de las Tecnologías de la Información y de las Comunicaciones Avanzadas (ITACA), Universitat Politècnica de València (UPV), Valencia, Spain.
| | - Vincenzo Lomonaco
- Department of Computer Science, University of Pisa (Unipi), Pisa, Italy.
| | - Lucia C Passaro
- Department of Computer Science, University of Pisa (Unipi), Pisa, Italy.
| | - Antonio Félix-De Castro
- Conselleria de Sanitat Universal i Salut Pública, Generalitat Valenciana (GVA), Valencia, Spain.
| | | | - Carlos Sáez
- Biomedical Data Science Laboratory (BDSLab), Instituto de Aplicaciones de las Tecnologías de la Información y de las Comunicaciones Avanzadas (ITACA), Universitat Politècnica de València (UPV), Valencia, Spain.
| | - Juan M García-Gómez
- Biomedical Data Science Laboratory (BDSLab), Instituto de Aplicaciones de las Tecnologías de la Información y de las Comunicaciones Avanzadas (ITACA), Universitat Politècnica de València (UPV), Valencia, Spain.
| |
Collapse
|
5
|
Vakili Ojarood M, Yaghoubi T, Farzan R. Machine learning for prehospital care of patients with severe burns. Burns 2024; 50:1041-1043. [PMID: 38461082 DOI: 10.1016/j.burns.2024.02.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2024] [Revised: 02/02/2024] [Accepted: 02/21/2024] [Indexed: 03/11/2024]
Affiliation(s)
| | - Tahereh Yaghoubi
- Traditional and Complementary Medicine Research Center, Addiction Institute, Mazandaran University of Medical Sciences, Sari, Iran.
| | - Ramyar Farzan
- Department of Plastic & Reconstructive Surgery, School of Medicine, Guilan University of Medical Sciences, Rasht, Iran.
| |
Collapse
|
6
|
Levy MJ, Crowe RP, Abraham H, Bailey A, Blue M, Ekl R, Garfinkel E, Holloman JB, Hutchens J, Jacobsen R, Johnson C, Margolis A, Troncoso R, Williams JG, Myers JB. Dispatch Categories as Indicators of Out-of-Hospital Time Critical Interventions and Associated Emergency Department Outcomes. PREHOSP EMERG CARE 2024:1-6. [PMID: 38626286 DOI: 10.1080/10903127.2024.2342015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2024] [Accepted: 04/04/2024] [Indexed: 04/18/2024]
Abstract
OBJECTIVES Emergency medical services (EMS) systems increasingly grapple with rising call volumes and workforce shortages, forcing systems to decide which responses may be delayed. Limited research has linked dispatch codes, on-scene findings, and emergency department (ED) outcomes. This study evaluated the association between dispatch categorizations and time-critical EMS responses defined by prehospital interventions and ED outcomes. Secondarily, we proposed a framework for identifying dispatch categorizations that are safe or unsafe to hold in queue. METHODS This retrospective, multi-center analysis encompassed all 9-1-1 responses from 8 accredited EMS systems between 1/1/2021 and 06/30/2023, utilizing the Medical Priority Dispatch System (MPDS). Independent variables included MPDS Protocol numbers and Determinant levels. EMS treatments and ED diagnoses/dispositions were categorized as time-critical using a multi-round consensus survey. The primary outcome was the proportion of EMS responses categorized as time-critical. A non-parametric test for trend was used to assess the proportion of time-critical responses Determinant levels. Based on group consensus, Protocol/Determinant level combinations with at least 120 responses (∼1 per week) were further categorized as safe to hold in queue (<1% time-critical intervention by EMS and <5% time-critical ED outcome) or unsafe to hold in queue (>10% time-critical intervention by EMS or >10% time-critical ED outcome). RESULTS Of 1,715,612 EMS incidents, 6% (109,250) involved a time-critical EMS intervention. Among EMS transports with linked outcome data (543,883), 12% had time-critical ED outcomes. The proportion of time-critical EMS interventions increased with Determinant level (OMEGA: 1%, ECHO: 38%, p-trend < 0.01) as did time-critical ED outcomes (OMEGA: 3%, ECHO: 31%, p-trend < 0.01). Of 162 unique Protocols/Determinants with at least 120 uses, 30 met criteria for safe to hold in queue, accounting for 8% (142,067) of incidents. Meanwhile, 72 Protocols/Determinants met criteria for unsafe to hold, accounting for 52% (883,683) of incidents. Seven of 32 ALPHA level Protocols and 3/17 OMEGA level Protocols met the proposed criteria for unsafe to hold in queue. CONCLUSIONS In general, Determinant levels aligned with time-critical responses; however, a notable minority of lower acuity Determinant level Protocols met criteria for unsafe to hold. This suggests a more nuanced approach to dispatch prioritization, considering both Protocol and Determinant level factors.
Collapse
Affiliation(s)
| | | | | | - Anna Bailey
- Office of the Medical Director, Metropolitan Oklahoma City and Tulsa, Oklahoma
| | - Matt Blue
- Charleston County EMS, Charleston, South Carolina
| | | | | | | | | | - Ryan Jacobsen
- Office of the Medical Director, Johnson County EMS System, Olathe, Kansas
| | | | | | | | | | | |
Collapse
|
7
|
Costa DB, Pinna FCDA, Joiner AP, Rice B, de Souza JVP, Gabella JL, Andrade L, Vissoci JRN, Néto JC. AI-based approach for transcribing and classifying unstructured emergency call data: A methodological proposal. PLOS DIGITAL HEALTH 2023; 2:e0000406. [PMID: 38055710 PMCID: PMC10699611 DOI: 10.1371/journal.pdig.0000406] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/14/2023] [Accepted: 11/07/2023] [Indexed: 12/08/2023]
Abstract
Emergency care-sensitive conditions (ECSCs) require rapid identification and treatment and are responsible for over half of all deaths worldwide. Prehospital emergency care (PEC) can provide rapid treatment and access to definitive care for many ECSCs and can reduce mortality in several different settings. The objective of this study is to propose a method for using artificial intelligence (AI) and machine learning (ML) to transcribe audio, extract, and classify unstructured emergency call data in the Serviço de Atendimento Móvel de Urgência (SAMU) system in southern Brazil. The study used all "1-9-2" calls received in 2019 by the SAMU Novo Norte Emergency Regulation Center (ERC) call center in Maringá, in the Brazilian state of Paraná. The calls were processed through a pipeline using machine learning algorithms, including Automatic Speech Recognition (ASR) models for transcription of audio calls in Portuguese, and a Natural Language Understanding (NLU) classification model. The pipeline was trained and validated using a dataset of labeled calls, which were manually classified by medical students using LabelStudio. The results showed that the AI model was able to accurately transcribe the audio with a Word Error Rate of 42.12% using Wav2Vec 2.0 for ASR transcription of audio calls in Portuguese. Additionally, the NLU classification model had an accuracy of 73.9% in classifying the calls into different categories in a validation subset. The study found that using AI to categorize emergency calls in low- and middle-income countries is largely unexplored, and the applicability of conventional open-source ML models trained on English language datasets is unclear for non-English speaking countries. The study concludes that AI can be used to transcribe audio and extract and classify unstructured emergency call data in an emergency system in southern Brazil as an initial step towards developing a decision-making support tool.
Collapse
Affiliation(s)
- Dalton Breno Costa
- Department of Psychology, Pontifical Catholic University of Rio Grande do Sul, Rio Grande do Sul, Brazil
| | - Felipe Coelho de Abreu Pinna
- Department of Computer and Digital Systems Engineering, Polytechnic School, University of São Paulo, São Paulo, São Paulo, Brazil
| | - Anjni Patel Joiner
- Department of Emergency Medicine, Duke University School of Medicine, Durham, North Carolina, United States of America
- Global Emergency Medicine Innovation and Implementation Research Center, Duke Global Health Institute, Duke University, Durham, North Carolina, United States of America
| | - Brian Rice
- Department of Emergency Medicine, Stanford University, Palo Alto, California, United States of America
| | - João Vítor Perez de Souza
- Department of Emergency Medicine, Duke University School of Medicine, Durham, North Carolina, United States of America
- Global Emergency Medicine Innovation and Implementation Research Center, Duke Global Health Institute, Duke University, Durham, North Carolina, United States of America
| | | | - Luciano Andrade
- Department of Medicine, State University of Maringá, Marringá, Paraná, Brazil
| | - João Ricardo Nickenig Vissoci
- Department of Emergency Medicine, Duke University School of Medicine, Durham, North Carolina, United States of America
- Global Emergency Medicine Innovation and Implementation Research Center, Duke Global Health Institute, Duke University, Durham, North Carolina, United States of America
| | - João Carlos Néto
- Department of Computer and Digital Systems Engineering, Polytechnic School, University of São Paulo, São Paulo, São Paulo, Brazil
| |
Collapse
|
8
|
de Koning E, van der Haas Y, Saguna S, Stoop E, Bosch J, Beeres S, Schalij M, Boogers M. AI Algorithm to Predict Acute Coronary Syndrome in Prehospital Cardiac Care: Retrospective Cohort Study. JMIR Cardio 2023; 7:e51375. [PMID: 37906226 PMCID: PMC10646678 DOI: 10.2196/51375] [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: 07/31/2023] [Revised: 08/29/2023] [Accepted: 09/19/2023] [Indexed: 11/02/2023] Open
Abstract
BACKGROUND Overcrowding of hospitals and emergency departments (EDs) is a growing problem. However, not all ED consultations are necessary. For example, 80% of patients in the ED with chest pain do not have an acute coronary syndrome (ACS). Artificial intelligence (AI) is useful in analyzing (medical) data, and might aid health care workers in prehospital clinical decision-making before patients are presented to the hospital. OBJECTIVE The aim of this study was to develop an AI model which would be able to predict ACS before patients visit the ED. The model retrospectively analyzed prehospital data acquired by emergency medical services' nurse paramedics. METHODS Patients presenting to the emergency medical services with symptoms suggestive of ACS between September 2018 and September 2020 were included. An AI model using a supervised text classification algorithm was developed to analyze data. Data were analyzed for all 7458 patients (mean 68, SD 15 years, 54% men). Specificity, sensitivity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for control and intervention groups. At first, a machine learning (ML) algorithm (or model) was chosen; afterward, the features needed were selected and then the model was tested and improved using iterative evaluation and in a further step through hyperparameter tuning. Finally, a method was selected to explain the final AI model. RESULTS The AI model had a specificity of 11% and a sensitivity of 99.5% whereas usual care had a specificity of 1% and a sensitivity of 99.5%. The PPV of the AI model was 15% and the NPV was 99%. The PPV of usual care was 13% and the NPV was 94%. CONCLUSIONS The AI model was able to predict ACS based on retrospective data from the prehospital setting. It led to an increase in specificity (from 1% to 11%) and NPV (from 94% to 99%) when compared to usual care, with a similar sensitivity. Due to the retrospective nature of this study and the singular focus on ACS it should be seen as a proof-of-concept. Other (possibly life-threatening) diagnoses were not analyzed. Future prospective validation is necessary before implementation.
Collapse
Affiliation(s)
- Enrico de Koning
- Cardiology Department, Leiden University Medical Center, Leiden, Netherlands
| | | | | | - Esmee Stoop
- Clinical AI and Research lab, Leiden University Medical Center, Leiden, Netherlands
| | - Jan Bosch
- Research and Development, Regional Ambulance Service Hollands-Midden, Leiden, Netherlands
| | - Saskia Beeres
- Cardiology Department, Leiden University Medical Center, Leiden, Netherlands
| | - Martin Schalij
- Cardiology Department, Leiden University Medical Center, Leiden, Netherlands
| | - Mark Boogers
- Cardiology Department, Leiden University Medical Center, Leiden, Netherlands
| |
Collapse
|
9
|
Bakidou A, Caragounis EC, Andersson Hagiwara M, Jonsson A, Sjöqvist BA, Candefjord S. On Scene Injury Severity Prediction (OSISP) model for trauma developed using the Swedish Trauma Registry. BMC Med Inform Decis Mak 2023; 23:206. [PMID: 37814288 PMCID: PMC10561449 DOI: 10.1186/s12911-023-02290-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2022] [Accepted: 09/04/2023] [Indexed: 10/11/2023] Open
Abstract
BACKGROUND Providing optimal care for trauma, the leading cause of death for young adults, remains a challenge e.g., due to field triage limitations in assessing a patient's condition and deciding on transport destination. Data-driven On Scene Injury Severity Prediction (OSISP) models for motor vehicle crashes have shown potential for providing real-time decision support. The objective of this study is therefore to evaluate if an Artificial Intelligence (AI) based clinical decision support system can identify severely injured trauma patients in the prehospital setting. METHODS The Swedish Trauma Registry was used to train and validate five models - Logistic Regression, Random Forest, XGBoost, Support Vector Machine and Artificial Neural Network - in a stratified 10-fold cross validation setting and hold-out analysis. The models performed binary classification of the New Injury Severity Score and were evaluated using accuracy metrics, area under the receiver operating characteristic curve (AUC) and Precision-Recall curve (AUCPR), and under- and overtriage rates. RESULTS There were 75,602 registrations between 2013-2020 and 47,357 (62.6%) remained after eligibility criteria were applied. Models were based on 21 predictors, including injury location. From the clinical outcome, about 40% of patients were undertriaged and 46% were overtriaged. Models demonstrated potential for improved triaging and yielded AUC between 0.80-0.89 and AUCPR between 0.43-0.62. CONCLUSIONS AI based OSISP models have potential to provide support during assessment of injury severity. The findings may be used for developing tools to complement field triage protocols, with potential to improve prehospital trauma care and thereby reduce morbidity and mortality for a large patient population.
Collapse
Affiliation(s)
- Anna Bakidou
- Department of Electrical Engineering, Chalmers University of Technology, 412 96, Gothenburg, Sweden.
- Center for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, 501 90, Borås, Sweden.
| | - Eva-Corina Caragounis
- Department of Surgery, Institute of Clinical Sciences, Sahlgrenska University Hospital, Sahlgrenska Academy, University of Gothenburg, Per Dubbsgatan 15, 413 45, Gothenburg, Sweden
| | - Magnus Andersson Hagiwara
- Center for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, 501 90, Borås, Sweden
| | - Anders Jonsson
- Center for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, 501 90, Borås, Sweden
| | - Bengt Arne Sjöqvist
- Department of Electrical Engineering, Chalmers University of Technology, 412 96, Gothenburg, Sweden
| | - Stefan Candefjord
- Department of Electrical Engineering, Chalmers University of Technology, 412 96, Gothenburg, Sweden
| |
Collapse
|
10
|
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: 0] [Impact Index Per Article: 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
|
11
|
Lee S, Park HJ, Hwang J, Lee SW, Han KS, Kim WY, Jeong J, Kang H, Kim A, Lee C, Kim SJ. Machine Learning-Based Models for Prediction of Critical Illness at Community, Paramedic, and Hospital Stages. Emerg Med Int 2023; 2023:1221704. [PMID: 37404873 PMCID: PMC10317605 DOI: 10.1155/2023/1221704] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2022] [Revised: 05/08/2023] [Accepted: 06/02/2023] [Indexed: 07/06/2023] Open
Abstract
Overcrowding of emergency department (ED) has put a strain on national healthcare systems and adversely affected the clinical outcomes of critically ill patients. Early identification of critically ill patients prior to ED visits can help induce optimal patient flow and allocate medical resources effectively. This study aims to develop ML-based models for predicting critical illness in the community, paramedic, and hospital stages using Korean National Emergency Department Information System (NEDIS) data. Random forest and light gradient boosting machine (LightGBM) were applied to develop predictive models. The predictive model performance based on AUROC in community stage, paramedic stage, and hospital stage was estimated to be 0.870 (95% CI: 0.869-0.871), 0.897 (95% CI: 0.896-0.898), and 0.950 (95% CI: 0.949-0.950) in random forest and 0.877 (95% CI: 0.876-0.878), 0.899 (95% CI: 0.898-0.900), and 0.950 (95% CI: 0.950-0.951) in LightGBM, respectively. The ML models showed high performance in predicting critical illness using variables available at each stage, which can be helpful in guiding patients to appropriate hospitals according to their severity of illness. Furthermore, a simulation model can be developed for proper allocation of limited medical resources.
Collapse
Affiliation(s)
- Sijin Lee
- Department of Emergency Medicine, Korea University, College of Medicine, Seoul, Republic of Korea
| | - Hyun Ji Park
- Department of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea
| | - Jumi Hwang
- Department of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea
| | - Sung Woo Lee
- Department of Emergency Medicine, Korea University, College of Medicine, Seoul, Republic of Korea
| | - Kap Su Han
- Department of Emergency Medicine, Korea University, College of Medicine, Seoul, Republic of Korea
| | - Won Young Kim
- Department of Emergency Medicine, University of Ulsan, College of Medicine, Asan Medical Center, Seoul, Republic of Korea
| | - Jinwoo Jeong
- Department of Emergency Medicine, Dong-A University, College of Medicine, Busan, Republic of Korea
| | - Hyunggoo Kang
- Department of Emergency Medicine, Hanyang University, College of Medicine, Seoul, Republic of Korea
| | - Armi Kim
- Department of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea
| | - Chulung Lee
- School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea
| | - Su Jin Kim
- Department of Emergency Medicine, Korea University, College of Medicine, Seoul, Republic of Korea
| |
Collapse
|
12
|
Rees N, Holding K, Sujan M. Information governance as a socio-technical process in the development of trustworthy healthcare AI. FRONTIERS IN COMPUTER SCIENCE 2023. [DOI: 10.3389/fcomp.2023.1134818] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/19/2023] Open
Abstract
In this paper we describe our experiences of managing information governance (IG) processes for the assurance of healthcare AI, using the example of an out-of-hospital-cardiac-arrest recognition software within the context of the Welsh Ambulance Service. We frame IG as a socio-technical process. IG processes for the development of trustworthy healthcare AI rely on information governance work, which entails dialogue, negotiation, and trade-offs around the legal basis for data sharing, data requirements and data control. Information governance work should start early in the design life cycle and will likely continue throughout. This includes a focus on establishing and building relationships, as well as a focus on organizational readiness and deeper understanding of both AI technologies as well as their safety assurance requirements.
Collapse
|
13
|
Johansson A, Ekwall A, Forberg JL, Ekelund U. Development of outcomes for evaluating emergency care triage: a Delphi approach. Scand J Trauma Resusc Emerg Med 2023; 31:10. [PMID: 36841783 PMCID: PMC9958312 DOI: 10.1186/s13049-023-01073-1] [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: 12/21/2022] [Accepted: 02/13/2023] [Indexed: 02/27/2023] Open
Abstract
BACKGROUND Triage is used as standard of care for prioritization and identification of time-critical patients in the emergency department (ED) globally, but it is unclear what outcomes should be used to evaluate triage. Currently used outcomes do not include important time-critical diagnoses and conditions. METHOD We used 18 Swedish triage experts to collect and assess outcomes for the evaluation of 5-level triage systems. The experts suggested 68 outcomes which were then tested through a modified Delphi approach in three rounds. The outcomes aimed to identify correctly prioritized red patients (in need of a resuscitation team), and orange patients (other time critical conditions). Consensus was pre-defined as 70% dichotomized (positive/negative) concordance. RESULTS Diagnoses, interventions, mortality, level of care and lab results were included in the outcomes. Positive consensus was reached for 49 outcomes and negative consensus for 7 outcomes, with an 83% response rate. The five most approved outcomes were the interventions Percutaneous coronary intervention, Surgical airway and Massive transfusion together with the diagnoses Tension pneumothorax and Intracerebral hemorrhage that received specific interventions. The outcomes with the clearest disapproval included Admittance to a ward, Treatment with antihistamines and The ordering of a head computed tomography scan. The outcomes were considered valid only if occurring in or from the ED. CONCLUSION This study proposes a standard of 49 outcomes divided into two sets tied to red and orange priority respectively, to be used when evaluating 5-level priority triage systems; Lund Outcome Set for Evaluation of Triage (LOSET). The proposed outcomes include diagnoses, interventions and laboratory results. Before widespread implementation of LOSET, prospective testing is needed, preferably at multiple sites.
Collapse
Affiliation(s)
- André Johansson
- Department of Health Sciences, Faculty of Medicine, Lund University, Box 157, 221 00, Lund, Sweden.
| | - Anna Ekwall
- grid.4514.40000 0001 0930 2361Department of Health Sciences, Faculty of Medicine, Lund University, Box 157, 221 00 Lund, Sweden
| | - Jakob Lundager Forberg
- grid.413823.f0000 0004 0624 046XDepartment of Emergency Medicine, Helsingborg Hospital, Helsingborg, Sweden ,grid.4514.40000 0001 0930 2361Emergency Medicine, Department of Clinical Sciences Lund, Lund University, Skane University Hospital, Lund, Sweden
| | - Ulf Ekelund
- grid.4514.40000 0001 0930 2361Emergency Medicine, Department of Clinical Sciences Lund, Lund University, Skane University Hospital, Lund, Sweden
| |
Collapse
|
14
|
Adebayo O, Bhuiyan ZA, Ahmed Z. Exploring the effectiveness of artificial intelligence, machine learning and deep learning in trauma triage: A systematic review and meta-analysis. Digit Health 2023; 9:20552076231205736. [PMID: 37822960 PMCID: PMC10563501 DOI: 10.1177/20552076231205736] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2023] [Accepted: 09/18/2023] [Indexed: 10/13/2023] Open
Abstract
Background The development of artificial intelligence (AI), machine learning (ML) and deep learning (DL) has advanced rapidly in the medical field, notably in trauma medicine. We aimed to systematically appraise the efficacy of AI, ML and DL models for predicting outcomes in trauma triage compared to conventional triage tools. Methods We searched PubMed, MEDLINE, ProQuest, Embase and reference lists for studies published from 1 January 2010 to 9 June 2022. We included studies which analysed the use of AI, ML and DL models for trauma triage in human subjects. Reviews and AI/ML/DL models used for other purposes such as teaching, or diagnosis were excluded. Data was extracted on AI/ML/DL model type, comparison tools, primary outcomes and secondary outcomes. We performed meta-analysis on studies reporting our main outcomes of mortality, hospitalisation and critical care admission. Results One hundred and fourteen studies were identified in our search, of which 14 studies were included in the systematic review and 10 were included in the meta-analysis. All studies performed external validation. The best-performing AI/ML/DL models outperformed conventional trauma triage tools for all outcomes in all studies except two. For mortality, the mean area under the receiver operating characteristic (AUROC) score difference between AI/ML/DL models and conventional trauma triage was 0.09, 95% CI (0.02, 0.15), favouring AI/ML/DL models (p = 0.008). The mean AUROC score difference for hospitalisation was 0.11, 95% CI (0.10, 0.13), favouring AI/ML/DL models (p = 0.0001). For critical care admission, the mean AUROC score difference was 0.09, 95% CI (0.08, 0.10) favouring AI/ML/DL models (p = 0.00001). Conclusions This review demonstrates that the predictive ability of AI/ML/DL models is significantly better than conventional trauma triage tools for outcomes of mortality, hospitalisation and critical care admission. However, further research and in particular randomised controlled trials are required to evaluate the clinical and economic impacts of using AI/ML/DL models in trauma medicine.
Collapse
Affiliation(s)
- Oluwasemilore Adebayo
- Institute of Inflammation and Ageing, College of Medical and Dental Sciences, University of Birmingham, Edgbaston, Birmingham, UK
| | - Zunira Areeba Bhuiyan
- Institute of Inflammation and Ageing, College of Medical and Dental Sciences, University of Birmingham, Edgbaston, Birmingham, UK
| | - Zubair Ahmed
- Institute of Inflammation and Ageing, College of Medical and Dental Sciences, University of Birmingham, Edgbaston, Birmingham, UK
- Centre for Trauma Sciences Research, University of Birmingham, Edgbaston, Birmingham, UK
| |
Collapse
|
15
|
Development of a machine-learning algorithm to predict in-hospital cardiac arrest for emergency department patients using a nationwide database. Sci Rep 2022; 12:21797. [PMID: 36526686 PMCID: PMC9758227 DOI: 10.1038/s41598-022-26167-1] [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: 07/21/2022] [Accepted: 12/12/2022] [Indexed: 12/23/2022] Open
Abstract
In this retrospective observational study, we aimed to develop a machine-learning model using data obtained at the prehospital stage to predict in-hospital cardiac arrest in the emergency department (ED) of patients transferred via emergency medical services. The dataset was constructed by attaching the prehospital information from the National Fire Agency and hospital factors to data from the National Emergency Department Information System. Machine-learning models were developed using patient variables, with and without hospital factors. We validated model performance and used the SHapley Additive exPlanation model interpretation. In-hospital cardiac arrest occurred in 5431 of the 1,350,693 patients (0.4%). The extreme gradient boosting model showed the best performance with area under receiver operating curve of 0.9267 when incorporating the hospital factor. Oxygen supply, age, oxygen saturation, systolic blood pressure, the number of ED beds, ED occupancy, and pulse rate were the most influential variables, in that order. ED occupancy and in-hospital cardiac arrest occurrence were positively correlated, and the impact of ED occupancy appeared greater in small hospitals. The machine-learning predictive model using the integrated information acquired in the prehospital stage effectively predicted in-hospital cardiac arrest in the ED and can contribute to the efficient operation of emergency medical systems.
Collapse
|
16
|
An external validation study of the Score for Emergency Risk Prediction (SERP), an interpretable machine learning-based triage score for the emergency department. Sci Rep 2022; 12:17466. [PMID: 36261457 PMCID: PMC9580414 DOI: 10.1038/s41598-022-22233-w] [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: 08/02/2022] [Accepted: 10/11/2022] [Indexed: 01/12/2023] Open
Abstract
Emergency departments (EDs) are experiencing complex demands. An ED triage tool, the Score for Emergency Risk Prediction (SERP), was previously developed using an interpretable machine learning framework. It achieved a good performance in the Singapore population. We aimed to externally validate the SERP in a Korean cohort for all ED patients and compare its performance with Korean triage acuity scale (KTAS). This retrospective cohort study included all adult ED patients of Samsung Medical Center from 2016 to 2020. The outcomes were 30-day and in-hospital mortality after the patients' ED visit. We used the area under the receiver operating characteristic curve (AUROC) to assess the performance of the SERP and other conventional scores, including KTAS. The study population included 285,523 ED visits, of which 53,541 were after the COVID-19 outbreak (2020). The whole cohort, in-hospital, and 30 days mortality rates were 1.60%, and 3.80%. The SERP achieved an AUROC of 0.821 and 0.803, outperforming KTAS of 0.679 and 0.729 for in-hospital and 30-day mortality, respectively. SERP was superior to other scores for in-hospital and 30-day mortality prediction in an external validation cohort. SERP is a generic, intuitive, and effective triage tool to stratify general patients who present to the emergency department.
Collapse
|
17
|
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
|
18
|
Sujan M, Thimbleby H, Habli I, Cleve A, Maaløe L, Rees N. Assuring safe artificial intelligence in critical ambulance service response: study protocol. Br Paramed J 2022; 7:36-42. [DOI: 10.29045/14784726.2022.06.7.1.36] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022] Open
Abstract
Introduction: Early recognition of out-of-hospital cardiac arrest (OHCA) by ambulance service call centre operators is important so that cardiopulmonary resuscitation can be delivered immediately, but around 25% of OHCAs are not picked up by call centre operators. An artificial
intelligence (AI) system has been developed to support call centre operators in the detection of OHCA. The study aims to (1) explore ambulance service stakeholder perceptions on the safety of OHCA AI decision support in call centres, and (2) develop a clinical safety case for the OHCA AI decision-support
system.Methods and analysis: The study will be undertaken within the Welsh Ambulance Service. The study is part research and part service evaluation. The research utilises a qualitative study design based on thematic analysis of interview data. The service evaluation consists of
the development of a clinical safety case based on document analysis, analysis of the AI model and its development process and informal interviews with the technology developer.Conclusions: AI presents many opportunities for ambulance services, but safety assurance requirements
need to be understood. The ASSIST project will continue to explore and build the body of knowledge in this area.
Collapse
Affiliation(s)
- Mark Sujan
- Human Factors Everywhere Ltd. ORCID iD:, URL: https://orcid.org/0000-0001-6895-946X
| | | | | | | | | | - Nigel Rees
- Welsh Ambulance Service NHS Trust ORCID iD:, URL: https://orcid.org/0000-0001-8799-5335
| |
Collapse
|
19
|
Magnusson C, Hagiwara MA, Norberg-Boysen G, Kauppi W, Herlitz J, Axelsson C, Packendorff N, Larsson G, Wibring K. Suboptimal prehospital decision- making for referral to alternative levels of care - frequency, measurement, acceptance rate and room for improvement. BMC Emerg Med 2022; 22:89. [PMID: 35606694 PMCID: PMC9125920 DOI: 10.1186/s12873-022-00643-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2021] [Accepted: 05/05/2022] [Indexed: 11/15/2022] Open
Abstract
Background The emergency medical services (EMS) have undergone dramatic changes during the past few decades. Increased utilisation, changes in care-seeking behaviour and competence among EMS clinicians have given rise to a shift in EMS strategies in many countries. From transport to the emergency department to at the scene deciding on the most appropriate level of care and mode of transport. Among the non-conveyed patients some may suffer from “time-sensitive conditions” delaying diagnosis and treatment. Thus, four questions arise:How often are time-sensitive cases referred to primary care or self-care advice? How can we measure and define the level of inappropriate clinical decision-making? What is acceptable? How to increase patient safety?
Main text To what extent time-sensitive cases are non-conveyed varies. About 5–25% of referred patients visit the emergency department within 72 hours, 5% are hospitalised, 1–3% are reported to have a time-sensitive condition and seven-day mortality rates range from 0.3 to 6%. The level of inappropriate clinical decision-making can be measured using surrogate measures such as emergency department attendances, hospitalisation and short-term mortality. These measures do not reveal time-sensitive conditions. Defining a scoring system may be one alternative, where misclassifications of time-sensitive cases are rated based on how severely they affected patient outcome. In terms of what is acceptable there is no general agreement. Although a zero-vision approach does not seem to be realistic unless under-triage is split into different levels of severity with zero-vision in the most severe categories. There are several ways to reduce the risk of misclassifications. Implementation of support systems for decision-making using machine learning to improve the initial assessment is one approach. Using a trigger tool to identify adverse events is another. Conclusion A substantial number of patients are non-conveyed, including a small portion with time-sensitive conditions. This poses a threat to patient safety. No general agreement on how to define and measure the extent of such EMS referrals and no agreement of what is acceptable exists, but we conclude an overall zero-vision is not realistic. Developing specific tools supporting decision making regarding EMS referral may be one way to reduce misclassification rates.
Collapse
Affiliation(s)
- Carl Magnusson
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, SE-405 30, Gothenburg, Sweden. .,Department of Prehospital Emergency Care , Sahlgrenska University Hospital, SE-411 04, Gothenburg, Sweden.
| | - Magnus Andersson Hagiwara
- Prehospen-Centre for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, SE-501 90, Borås, Sweden
| | - Gabriella Norberg-Boysen
- Prehospen-Centre for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, SE-501 90, Borås, Sweden
| | - Wivica Kauppi
- Prehospen-Centre for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, SE-501 90, Borås, Sweden
| | - Johan Herlitz
- Prehospen-Centre for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, SE-501 90, Borås, Sweden
| | - Christer Axelsson
- Department of Prehospital Emergency Care , Sahlgrenska University Hospital, SE-411 04, Gothenburg, Sweden.,Prehospen-Centre for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, SE-501 90, Borås, Sweden
| | - Niclas Packendorff
- Prehospen-Centre for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, SE-501 90, Borås, Sweden
| | - Glenn Larsson
- Prehospen-Centre for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, SE-501 90, Borås, Sweden
| | - Kristoffer Wibring
- Department of Ambulance and Prehospital Care, Region Halland, SE-302 49, Halmstad, Sweden
| |
Collapse
|
20
|
Scholz ML, Collatz-Christensen H, Blomberg SNF, Boebel S, Verhoeven J, Krafft T. Artificial intelligence in Emergency Medical Services dispatching: assessing the potential impact of an automatic speech recognition software on stroke detection taking the Capital Region of Denmark as case in point. Scand J Trauma Resusc Emerg Med 2022; 30:36. [PMID: 35549978 PMCID: PMC9097123 DOI: 10.1186/s13049-022-01020-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2022] [Accepted: 04/24/2022] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND AND PURPOSE Stroke recognition at the Emergency Medical Services (EMS) impacts the stroke treatment and thus the related health outcome. At the EMS Copenhagen 66.2% of strokes are detected by the Emergency Medical Dispatcher (EMD) and in Denmark approximately 50% of stroke patients arrive at the hospital within the time-to-treatment. An automatic speech recognition software (ASR) can increase the recognition of Out-of-Hospital cardiac arrest (OHCA) at the EMS by 16%. This research aims to analyse the potential impact an ASR could have on stroke recognition at the EMS Copenhagen and the related treatment. METHODS Stroke patient data (n = 9049) from the years 2016-2018 were analysed retrospectively, regarding correlations between stroke detection at the EMS and stroke specific, as well as personal characteristics such as stroke type, sex, age, weekday, time of day, year, EMS number contacted, and treatment. The possible increase in stroke detection through an ASR and the effect on stroke treatment was calculated based on the impact of an existing ASR to detect OHCA from CORTI AI. RESULTS The Chi-Square test with the respective post-hoc test identified a negative correlation between stroke detection and females, the 1813-Medical Helpline, as well as weekends, and a positive correlation between stroke detection and treatment and thrombolysis. While the association analysis showed a moderate correlation between stroke detection and treatment the correlation to the other treatment options was weak or very weak. A potential increase in stroke detection to 61.19% with an ASR and hence an increase of thrombolysis by 5% in stroke patients calling within time-to-treatment was predicted. CONCLUSIONS An ASR can potentially improve stroke recognition by EMDs and subsequent stroke treatment at the EMS Copenhagen. Based on the analysis results improvement of stroke recognition is particularly relevant for females, younger stroke patients, calls received through the 1813-Medical Helpline, and on weekends. TRIAL REGISTRATION This study was registered at the Danish Data Protection Agency (PVH-2014-002) and the Danish Patient Safety Authority (R-21013122).
Collapse
Affiliation(s)
- Mirjam Lisa Scholz
- Emergency Medical Services, Capital Region of Denmark, Telegrafvej 5, 2750 Ballerup, Denmark
- Department of Health, Ethics and Society, Care and Public Health Research Institute (CAPHRI), Faculty of Health, Medicine and Life Sciences, Maastricht University, P.O. Box 616, 6200 MD Maastricht, Netherlands
| | | | | | - Simone Boebel
- Emergency Medical Services, Capital Region of Denmark, Telegrafvej 5, 2750 Ballerup, Denmark
- Department of Health, Ethics and Society, Care and Public Health Research Institute (CAPHRI), Faculty of Health, Medicine and Life Sciences, Maastricht University, P.O. Box 616, 6200 MD Maastricht, Netherlands
| | - Jeske Verhoeven
- Emergency Medical Services, Capital Region of Denmark, Telegrafvej 5, 2750 Ballerup, Denmark
- Department of Health, Ethics and Society, Care and Public Health Research Institute (CAPHRI), Faculty of Health, Medicine and Life Sciences, Maastricht University, P.O. Box 616, 6200 MD Maastricht, Netherlands
| | - Thomas Krafft
- Department of Health, Ethics and Society, Care and Public Health Research Institute (CAPHRI), Faculty of Health, Medicine and Life Sciences, Maastricht University, P.O. Box 616, 6200 MD Maastricht, Netherlands
| |
Collapse
|
21
|
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: 2] [Impact Index Per Article: 1.0] [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
|
22
|
Alagaratnam J, De Francesco D, Zetterberg H, Heslegrave A, Toombs J, Kootstra NA, Underwood J, Gisslen M, Reiss P, Fidler S, Sabin CA, Winston A. Correlation between cerebrospinal fluid and plasma neurofilament light protein in treated HIV infection: results from the COBRA study. J Neurovirol 2022; 28:54-63. [PMID: 34874540 PMCID: PMC9076742 DOI: 10.1007/s13365-021-01026-3] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2020] [Revised: 03/24/2021] [Accepted: 10/27/2021] [Indexed: 11/27/2022]
Abstract
Cerebrospinal fluid (CSF) neurofilament light protein (NfL) is a marker of central nervous system neuro-axonal injury. A novel, ultra-sensitive assay can determine plasma NfL. In untreated people-with-HIV (PWH), CSF and plasma NfL are strongly correlated. We aimed to assess this correlation in PWH on suppressive antiretroviral treatment (ART) and lifestyle-similar HIV-negative individuals enrolled into the COmorBidity in Relation to AIDS (COBRA) study. Differences in paired CSF (sandwich ELISA, UmanDiagnostics) and plasma (Simoa digital immunoassay, Quanterix™) NfL between PWH and HIV-negative participants were tested using Wilcoxon's test; associations were assessed using Pearson's correlation. CSF and plasma NfL, standardised to Z-scores, were included as dependent variables in linear regression models to identify factors independently associated with values in PWH and HIV-negative participants. Overall, 132 PWH (all with plasma HIV RNA < 50 copies/mL) and 79 HIV-negative participants were included. Neither CSF (median 570 vs 568 pg/mL, p = 0.37) nor plasma (median 10.7 vs 9.9 pg/mL, p = 0.15) NfL differed significantly between PWH and HIV-negative participants, respectively. CSF and plasma NfL correlated moderately, with no significant difference by HIV status (PWH: rho = 0.52; HIV-negative participants: rho = 0.47, p (interaction) = 0.63). In multivariable regression analysis, higher CSF NfL Z-score was statistically significantly associated with older age and higher CSF protein, and higher plasma NfL Z-score with older age, higher serum creatinine and lower bodyweight. In conclusion, in PWH on ART, the correlation between CSF and plasma NfL is moderate and similar to that observed in lifestyle-similar HIV-negative individuals. Consideration of renal function and bodyweight may be required when utilising plasma NfL.
Collapse
Affiliation(s)
- Jasmini Alagaratnam
- Department of Infectious Disease, Faculty of Medicine, Imperial College London, London, UK.
- Department of Genitourinary Medicine &, HIV, St Mary's Hospital, Imperial College Healthcare NHS Trust, London, UK.
| | | | - Henrik Zetterberg
- UK Dementia Research Institute at University College London, London, UK
- Department of Neurodegenerative Disease, UCL Institute of Neurology, Queen Square, University College London, London, UK
- Department of Psychiatry and Neurochemistry, Institute of Neuroscience and Physiology, the Sahlgrenska Academy at the University of Gothenburg, Mölndal, Sweden
- Clinical Neurochemistry Laboratory, Sahlgrenska University Hospital, Mölndal, Sweden
| | - Amanda Heslegrave
- UK Dementia Research Institute at University College London, London, UK
| | - Jamie Toombs
- UK Dementia Research Institute at University College London, London, UK
| | - Neeltje A Kootstra
- Department of Experimental Immunology, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands
| | - Jonathan Underwood
- Department of Infectious Disease, Faculty of Medicine, Imperial College London, London, UK
- Division of Infection and Immunity, Cardiff University, Cardiff, UK
- Department of Infectious Diseases, Cardiff and Vale University Health Board, Cardiff, UK
| | - Magnus Gisslen
- Department of Infectious Diseases, Institute of Biomedicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Infectious Diseases, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Peter Reiss
- Department of Global Health, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, The Netherlands
- Amsterdam Institute for Global Health and Development, Amsterdam, The Netherlands
- Stichting HIV Monitoring, Amsterdam, The Netherlands
| | - Sarah Fidler
- Department of Infectious Disease, Faculty of Medicine, Imperial College London, London, UK
- Department of Genitourinary Medicine &, HIV, St Mary's Hospital, Imperial College Healthcare NHS Trust, London, UK
| | - Caroline A Sabin
- Institute for Global Health, University College London, London, UK
| | - Alan Winston
- Department of Infectious Disease, Faculty of Medicine, Imperial College London, London, UK
- Department of Genitourinary Medicine &, HIV, St Mary's Hospital, Imperial College Healthcare NHS Trust, London, UK
| |
Collapse
|
23
|
van Rooij D, Zhang-James Y, Buitelaar J, Faraone SV, Reif A, Grimm O. Structural brain morphometry as classifier and predictor of ADHD and reward-related comorbidities. Front Psychiatry 2022; 13:869627. [PMID: 36172513 PMCID: PMC9512052 DOI: 10.3389/fpsyt.2022.869627] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/04/2022] [Accepted: 08/01/2022] [Indexed: 11/30/2022] Open
Abstract
Attention deficit/hyperactivity disorder (ADHD) is one of the most common neurodevelopmental disorders, and around two-thirds of affected children report persisting problems in adulthood. This negative trajectory is associated with high comorbidity with disorders like obesity, depression, or substance use disorder (SUD). Decreases in cortical volume and thickness have also been reported in depression, SUD, and obesity, but it is unclear whether structural brain alterations represent unique disorder-specific profiles. A transdiagnostic exploration of ADHD and typical comorbid disorders could help to understand whether specific morphometric brain changes are due to ADHD or, alternatively, to the comorbid disorders. In the current study, we studied the brain morphometry of 136 subjects with ADHD with and without comorbid depression, SUD, and obesity to test whether there are unique or common brain alterations. We employed a machine-learning-algorithm trained to classify subjects with ADHD in the large ENIGMA-ADHD dataset and used it to predict the diagnostic status of subjects with ADHD and/or comorbidities. The parcellation analysis demonstrated decreased cortical thickness in medial prefrontal areas that was associated with presence of any comorbidity. However, these results did not survive correction for multiple comparisons. Similarly, the machine learning analysis indicated that the predictive algorithm grouped most of our ADHD participants as belonging to the ADHD-group, but no systematic differences between comorbidity status came up. In sum, neither a classical comparison of segmented structural brain metrics nor an ML model based on the ADHD ENIGMA data differentiate between ADHD with and without comorbidities. As the ML model is based in part on adolescent brains, this might indicate that comorbid disorders and their brain changes are not captured by the ML model because it represents a different developmental brain trajectory.
Collapse
Affiliation(s)
- Daan van Rooij
- Department of Cognitive Neuroscience, Donders Institute for Brain, Cognition and Behavior, Radboud University Medical Center, Nijmegen, Netherlands
| | - Yanli Zhang-James
- Department of Psychiatry and Behavioral Sciences, SUNY Upstate Medical University, Syracuse, NY, United States
| | - Jan Buitelaar
- Department of Cognitive Neuroscience, Donders Institute for Brain, Cognition and Behavior, Radboud University Medical Center, Nijmegen, Netherlands
| | - Stephen V Faraone
- Department of Psychiatry and Behavioral Sciences, SUNY Upstate Medical University, Syracuse, NY, United States
| | - Andreas Reif
- Department of Psychiatry, Psychosomatic Medicine and Psychotherapy, University Hospital, Goethe University, Frankfurt, Germany
| | - Oliver Grimm
- Department of Psychiatry, Psychosomatic Medicine and Psychotherapy, University Hospital, Goethe University, Frankfurt, Germany
| |
Collapse
|
24
|
Ikezawa K, Hirose M, Maruyama T, Yuji K, Yabe Y, Kanamori T, Kaide N, Tsuchiya Y, Hara S, Suzuki H. Effect of early nutritional initiation on post-cerebral infarction discharge destination: A propensity-matched analysis using machine learning. Nutr Diet 2021; 79:247-254. [PMID: 34927343 DOI: 10.1111/1747-0080.12718] [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] [Received: 09/11/2021] [Revised: 11/11/2021] [Accepted: 11/15/2021] [Indexed: 11/26/2022]
Abstract
AIM Malnutrition is associated with poor outcomes in cerebral infarction patients, with research indicating that early nutritional initiation may improve the short-term prognosis of patients. However, evidence supported by big data is lacking. Here, to determine the effect of nutritional initiation during the first 3 days after hospital admission on home discharge rates, propensity score matching was conducted in patients with acute cerebral infarction. METHODS This retrospective observational study, using the Diagnosis Procedure Combination anonymised database in Japan, included 41 477 ischaemic cerebral infarction patients hospitalised between 2016 and 2019. The patients were divided into two groups: those who received oral or enteral nutrition during the first 3 days of hospital admission (early nutrition group, n = 37 318) and those who did not (control group, n = 4159). One-to-one pair-matching was performed using propensity scores calculated via extreme gradient boosting to limit the confounding variables of the two groups. RESULTS After propensity score matching, 3541 pairs of patients were selected. The dependence of home discharge rates on early nutrition was significant (p < 0.05), and the effectiveness of early nutrition for home discharge showed an odds ratio of 1.79 (95% confidence interval of 1.59-2.03 in Fisher's exact test). CONCLUSIONS Our findings revealed that early nutritional initiation during the first 3 days of admission resulted in higher home discharge rates.
Collapse
Affiliation(s)
- Kazuto Ikezawa
- Division of Gastroenterology, Tsukuba Memorial Hospital, Tsukuba, Japan
| | - Mitsuaki Hirose
- Department of Gastroenterology, Institute of Clinical Medicine, University of Tsukuba, Tsukuba, Japan
| | | | - Koichiro Yuji
- The Institute of Medical Science, The University of Tokyo, Tokyo, Japan
| | - Yoshito Yabe
- Department of Nutrition, Tsukuba Memorial Hospital, Tsukuba, Japan
| | | | | | | | | | - Hideo Suzuki
- Department of Gastroenterology, Institute of Clinical Medicine, University of Tsukuba, Tsukuba, Japan
| |
Collapse
|
25
|
Yun H, Choi J, Park JH. XGBoost Algorithm Prediction of Critical Care Outcome for Adult Patients Presenting to Emergency Department Using Initial Triage Information. JMIR Med Inform 2021; 9:e30770. [PMID: 34346889 PMCID: PMC8491120 DOI: 10.2196/30770] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/28/2021] [Revised: 06/27/2021] [Accepted: 07/27/2021] [Indexed: 12/23/2022] Open
Abstract
Background The emergency department (ED) triage system to classify and prioritize patients from high risk to less urgent continues to be a challenge. Objective This study, comprising 80,433 patients, aims to develop a machine learning algorithm prediction model of critical care outcomes for adult patients using information collected during ED triage and compare the performance with that of the baseline model using the Korean Triage and Acuity Scale (KTAS). Methods To predict the need for critical care, we used 13 predictors from triage information: age, gender, mode of ED arrival, the time interval between onset and ED arrival, reason of ED visit, chief complaints, systolic blood pressure, diastolic blood pressure, pulse rate, respiratory rate, body temperature, oxygen saturation, and level of consciousness. The baseline model with KTAS was developed using logistic regression, and the machine learning model with 13 variables was generated using extreme gradient boosting (XGB) and deep neural network (DNN) algorithms. The discrimination was measured by the area under the receiver operating characteristic (AUROC) curve. The ability of calibration with Hosmer–Lemeshow test and reclassification with net reclassification index were evaluated. The calibration plot and partial dependence plot were used in the analysis. Results The AUROC of the model with the full set of variables (0.833-0.861) was better than that of the baseline model (0.796). The XGB model of AUROC 0.861 (95% CI 0.848-0.874) showed a higher discriminative performance than the DNN model of 0.833 (95% CI 0.819-0.848). The XGB and DNN models proved better reclassification than the baseline model with a positive net reclassification index. The XGB models were well-calibrated (Hosmer-Lemeshow test; P>.05); however, the DNN showed poor calibration power (Hosmer-Lemeshow test; P<.001). We further interpreted the nonlinear association between variables and critical care prediction. Conclusions Our study demonstrated that the performance of the XGB model using initial information at ED triage for predicting patients in need of critical care outperformed the conventional model with KTAS.
Collapse
Affiliation(s)
- Hyoungju Yun
- Interdisciplinary Program of Medical Informatics, College of Medicine, Seoul National University, Seoul, KR
| | - Jinwook Choi
- Interdisciplinary Program of Medical Informatics, College of Medicine, Seoul National University, Seoul, KR.,Department of Biomedical Engineering, College of Medicine, Seoul National University, Seoul, KR.,Institute of Medical and Biological Engineering,, Seoul National University Medical Research Center, 103 Daehak-Ro, Jongno-Gu, Seoul, KR
| | - Jeong Ho Park
- Department of Emergency Medicine, College of Medicine, Seoul National University, Seoul, KR.,Laboratory of Emergency Medical Services, Seoul National University Hospital Biomedical Research Institute, Seoul, KR
| |
Collapse
|
26
|
Kaminsky E, Lindberg Y, Spangler D, Winblad U, K Holmström I. Registered nurses' understandings of emergency medical dispatch center work: A qualitative phenomenographic interview study. Nurs Health Sci 2021; 23:430-438. [PMID: 33665977 DOI: 10.1111/nhs.12824] [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] [Received: 10/31/2020] [Accepted: 02/23/2021] [Indexed: 11/26/2022]
Abstract
Non-urgent and urgent telephone nursing services are increasing globally, and phenomenographic research has shown that how work is understood may influence work performance. This descriptive study makes a qualitative inductive investigation of understandings of emergency medical dispatch center work among registered nurses. Twenty-four registered nurses at three mid Swedish emergency medical dispatch centers were interviewed. Analysis based on phenomenographic principles identified five categories in the interviews: (i) Assess, prioritize, direct, or refer; (ii) Facilitate ambulance nursing work; (iii) Perform nursing care; (iv) Always be available for the public; and (v) Have the person behind the patient in mind. The first constitutes the basis of the work. The second emphasizes cooperation with and support for the ambulance staff. The third entails remotely providing nursing care, whilst the fourth stresses serving the entire population. The fifth and most comprehensive way of understanding work involves having a holistic view of the person in need, including person-centered care. Provision of high-quality emergency medical dispatch center work involves all categories. Combined, they constitute a "work map," valuable for reflection, competence development, and introduction of new staff.
Collapse
Affiliation(s)
- Elenor Kaminsky
- Department of Public Health and Caring Sciences, Uppsala University, Uppsala, Sweden
| | - Ylva Lindberg
- Department of Public Health and Caring Sciences, Uppsala University, Uppsala, Sweden
| | - Douglas Spangler
- Department of Public Health and Caring Sciences, Uppsala University, Uppsala, Sweden.,Uppsala Center for Prehospital Research, Department of Surgical Sciences - Anesthesia and Intensive Care, Uppsala University, Uppsala, Sweden
| | - Ulrika Winblad
- Department of Public Health and Caring Sciences, Uppsala University, Uppsala, Sweden
| | - Inger K Holmström
- Department of Public Health and Caring Sciences, Uppsala University, Uppsala, Sweden.,School of Health, Care and Social Welfare, Mälardalen University, Västerås, Sweden
| |
Collapse
|
27
|
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
|
28
|
Spangler D, Blomberg H, Smekal D. Prehospital identification of Covid-19: an observational study. Scand J Trauma Resusc Emerg Med 2021; 29:3. [PMID: 33407750 PMCID: PMC7786859 DOI: 10.1186/s13049-020-00826-6] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/05/2020] [Accepted: 12/13/2020] [Indexed: 02/06/2023] Open
Abstract
Background The novel coronavirus disease 2019 (Covid-19) pandemic has affected prehospital care systems across the world, but the prehospital presentation of affected patients and the extent to which prehospital care providers are able to identify them is not well characterized. In this study, we describe the presentation of Covid-19 patients in a Swedish prehospital care system, and asses the predictive value of Covid-19 suspicion as documented by dispatch and ambulance nurses. Methods Data for all patients with dispatch, ambulance, and hospital records between January 1–August 31, 2020 were extracted. A descriptive statistical analysis of patients with and without hospital-confirmed Covid-19 was performed. In a subset of records beginning from April 14, we assessed the sensitivity and specificity of documented Covid-19 suspicion in dispatch and ambulance patient care records. Results A total of 11,894 prehospital records were included, of which 481 had a primary hospital diagnosis code related to-, or positive test results for Covid-19. Covid-19-positive patients had considerably worse outcomes than patients with negative test results, with 30-day mortality rates of 24% vs 11%, but lower levels of prehospital acuity (e.g. emergent transport rates of 14% vs 22%). About half (46%) of Covid-19-positive patients presented to dispatchers with primary complaints typically associated with Covid-19. Six thousand seven hundred seventy-six records were included in the assessment of predictive value. Sensitivity was 76% (95% CI 71–80) and 82% (78–86) for dispatch and ambulance suspicion respectively, while specificities were 86% (85–87) and 78% (77–79). Conclusions While prehospital suspicion was strongly indicative of hospital-confirmed Covid-19, based on the sensitivity identified in this study, prehospital suspicion should not be relied upon as a single factor to rule out the need for isolation precautions. The data provided may be used to develop improved guidelines for identifying Covid-19 patients in the prehospital setting.
Collapse
Affiliation(s)
- Douglas Spangler
- Uppsala Center for Prehospital Research, Department of Surgical Sciences - Anesthesiology and Intensive care, Uppsala University, 751 85, Uppsala, Sweden.
| | - Hans Blomberg
- Uppsala Center for Prehospital Research, Department of Surgical Sciences - Anesthesiology and Intensive care, Uppsala University, 751 85, Uppsala, Sweden
| | - David Smekal
- Uppsala Center for Prehospital Research, Department of Surgical Sciences - Anesthesiology and Intensive care, Uppsala University, 751 85, Uppsala, Sweden
| |
Collapse
|
29
|
Pirneskoski J, Tamminen J, Kallonen A, Nurmi J, Kuisma M, Olkkola KT, Hoppu S. Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality: A retrospective study. Resusc Plus 2020; 4:100046. [PMID: 34223321 PMCID: PMC8244434 DOI: 10.1016/j.resplu.2020.100046] [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: 05/15/2020] [Revised: 09/25/2020] [Accepted: 10/27/2020] [Indexed: 12/23/2022] Open
Abstract
Aim of the study The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality. Thus, we aimed to compare the mortality prediction accuracy of NEWS and random forest machine learning using prehospital vital signs. Methods In this retrospective study, all electronic ambulance mission reports between 2008 and 2015 in a single EMS system were collected. Adult patients (≥ 18 years) were included in the analysis. Random forest models with and without blood glucose were compared to the traditional NEWS for predicting one-day mortality. A ten-fold cross-validation method was applied to train and validate the random forest models. Results A total of 26,458 patients were included in the study of whom 278 (1.0%) died within one day of ambulance mission. The area under the receiver operating characteristic curve for one-day mortality was 0.836 (95% CI, 0.810−0.860) for NEWS, 0.858 (95% CI, 0.832−0.883) for a random forest trained with NEWS variables only and 0.868 (0.843−0.892) for a random forest trained with NEWS variables and blood glucose. Conclusion A random forest algorithm trained with NEWS variables was superior to traditional NEWS for predicting one-day mortality in adult prehospital patients, although the risk of selection bias must be acknowledged. The inclusion of blood glucose in the model further improved its predictive performance.
Collapse
Affiliation(s)
- Jussi Pirneskoski
- Department of Emergency Medicine and Services, University of Helsinki and HUS Helsinki University Hospital, Helsinki, Finland
| | - Joonas Tamminen
- Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland.,Emergency Medical Services, Tampere University Hospital, Tampere, Finland
| | - Antti Kallonen
- Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland
| | - Jouni Nurmi
- Department of Emergency Medicine and Services, University of Helsinki and HUS Helsinki University Hospital, Helsinki, Finland
| | - Markku Kuisma
- Department of Emergency Medicine and Services, University of Helsinki and HUS Helsinki University Hospital, Helsinki, Finland
| | - Klaus T Olkkola
- Department of Anaesthesiology, Intensive Care and Pain Medicine, University of Helsinki and HUS Helsinki University Hospital, Helsinki, Finland
| | - Sanna Hoppu
- Emergency Medical Services, Tampere University Hospital, Tampere, Finland
| |
Collapse
|
30
|
Kirubarajan A, Taher A, Khan S, Masood S. Artificial intelligence in emergency medicine: A scoping review. J Am Coll Emerg Physicians Open 2020; 1:1691-1702. [PMID: 33392578 PMCID: PMC7771825 DOI: 10.1002/emp2.12277] [Citation(s) in RCA: 25] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2020] [Revised: 09/04/2020] [Accepted: 09/22/2020] [Indexed: 01/08/2023] Open
Abstract
INTRODUCTION Despite the growing investment in and adoption of artificial intelligence (AI) in medicine, the applications of AI in an emergency setting remain unclear. This scoping review seeks to identify available literature regarding the applications of AI in emergency medicine. METHODS The scoping review was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for scoping reviews using Medline-OVID, EMBASE, CINAHL, and IEEE, with a double screening and extraction process. The search included articles published until February 28, 2020. Articles were excluded if they did not self-classify as studying an AI intervention, were not relevant to the emergency department (ED), or did not report outcomes or evaluation. RESULTS Of the 1483 original database citations, 395 were eligible for full-text evaluation. Of these articles, a total of 150 were included in the scoping review. The majority of included studies were retrospective in nature (n = 124, 82.7%), with only 3 (2.0%) prospective controlled trials. We found 37 (24.7%) interventions aimed at improving diagnosis within the ED. Among the 150 studies, 19 (12.7%) focused on diagnostic imaging within the ED. A total of 16 (10.7%) studies were conducted in the out-of-hospital environment (eg, emergency medical services, paramedics) with the remainder occurring either in the ED or the trauma bay. Of the 24 (16%) studies that had human comparators, there were 12 (8%) studies in which AI interventions outperformed clinicians in at least 1 measured outcome. CONCLUSION AI-related research is rapidly increasing in emergency medicine. There are several promising AI interventions that can improve emergency care, particularly for acute radiographic imaging and prediction-based diagnoses. Higher quality evidence is needed to further assess both short- and long-term clinical outcomes.
Collapse
Affiliation(s)
- Abirami Kirubarajan
- Faculty of MedicineUniversity of TorontoTorontoOntarioCanada
- Institute of Health Policy Management and EvaluationUniversity of TorontoTorontoOntarioCanada
| | - Ahmed Taher
- Division of Emergency Medicine, Department of MedicineUniversity of TorontoTorontoOntarioCanada
| | - Shawn Khan
- Faculty of MedicineUniversity of TorontoTorontoOntarioCanada
| | - Sameer Masood
- Division of Emergency Medicine, Department of MedicineUniversity of TorontoTorontoOntarioCanada
- Toronto General Hospital Research InstituteUniversity Health NetworkTorontoOntarioCanada
| |
Collapse
|
31
|
Shirakawa T, Sonoo T, Ogura K, Fujimori R, Hara K, Goto T, Hashimoto H, Takahashi Y, Naraba H, Nakamura K. Institution-Specific Machine Learning Models for Prehospital Assessment to Predict Hospital Admission: Prediction Model Development Study. JMIR Med Inform 2020; 8:e20324. [PMID: 33107830 PMCID: PMC7655472 DOI: 10.2196/20324] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2020] [Revised: 08/24/2020] [Accepted: 09/16/2020] [Indexed: 12/23/2022] Open
Abstract
Background Although multiple prediction models have been developed to predict hospital admission to emergency departments (EDs) to address overcrowding and patient safety, only a few studies have examined prediction models for prehospital use. Development of institution-specific prediction models is feasible in this age of data science, provided that predictor-related information is readily collectable. Objective We aimed to develop a hospital admission prediction model based on patient information that is commonly available during ambulance transport before hospitalization. Methods Patients transported by ambulance to our ED from April 2018 through March 2019 were enrolled. Candidate predictors were age, sex, chief complaint, vital signs, and patient medical history, all of which were recorded by emergency medical teams during ambulance transport. Patients were divided into two cohorts for derivation (3601/5145, 70.0%) and validation (1544/5145, 30.0%). For statistical models, logistic regression, logistic lasso, random forest, and gradient boosting machine were used. Prediction models were developed in the derivation cohort. Model performance was assessed by area under the receiver operating characteristic curve (AUROC) and association measures in the validation cohort. Results Of 5145 patients transported by ambulance, including deaths in the ED and hospital transfers, 2699 (52.5%) required hospital admission. Prediction performance was higher with the addition of predictive factors, attaining the best performance with an AUROC of 0.818 (95% CI 0.792-0.839) with a machine learning model and predictive factors of age, sex, chief complaint, and vital signs. Sensitivity and specificity of this model were 0.744 (95% CI 0.716-0.773) and 0.745 (95% CI 0.709-0.776), respectively. Conclusions For patients transferred to EDs, we developed a well-performing hospital admission prediction model based on routinely collected prehospital information including chief complaints.
Collapse
Affiliation(s)
- Toru Shirakawa
- Department of Public Health, Graduate School of Medicine, Osaka University, Suita, Japan.,TXP Medical Co, Ltd, Chuo-ku, Japan
| | - Tomohiro Sonoo
- TXP Medical Co, Ltd, Chuo-ku, Japan.,Department of Emergency Medicine, Hitachi General Hospital, Hitachi, Japan
| | - Kentaro Ogura
- TXP Medical Co, Ltd, Chuo-ku, Japan.,Faculty of Medicine, The University of Tokyo, Bunkyo-ku, Japan
| | - Ryo Fujimori
- TXP Medical Co, Ltd, Chuo-ku, Japan.,Faculty of Medicine, The University of Tokyo, Bunkyo-ku, Japan
| | - Konan Hara
- TXP Medical Co, Ltd, Chuo-ku, Japan.,Department of Public Health, The University of Tokyo, Bunkyo-ku, Japan
| | - Tadahiro Goto
- TXP Medical Co, Ltd, Chuo-ku, Japan.,Department of Clinical Epidemiology and Health Economics, School of Public Health, The University of Tokyo, Bunkyo-ku, Japan
| | - Hideki Hashimoto
- Department of Emergency Medicine, Hitachi General Hospital, Hitachi, Japan
| | - Yuji Takahashi
- Department of Emergency Medicine, Hitachi General Hospital, Hitachi, Japan
| | - Hiromu Naraba
- Department of Emergency Medicine, Hitachi General Hospital, Hitachi, Japan
| | - Kensuke Nakamura
- Department of Emergency Medicine, Hitachi General Hospital, Hitachi, Japan.,Department of Emergency Medicine, The University of Tokyo, Bunkyo-ku, Japan
| |
Collapse
|
32
|
Xie F, Chakraborty B, Ong MEH, Goldstein BA, Liu N. AutoScore: A Machine Learning-Based Automatic Clinical Score Generator and Its Application to Mortality Prediction Using Electronic Health Records. JMIR Med Inform 2020; 8:e21798. [PMID: 33084589 PMCID: PMC7641783 DOI: 10.2196/21798] [Citation(s) in RCA: 49] [Impact Index Per Article: 12.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2020] [Revised: 07/25/2020] [Accepted: 07/27/2020] [Indexed: 01/01/2023] Open
Abstract
BACKGROUND Risk scores can be useful in clinical risk stratification and accurate allocations of medical resources, helping health providers improve patient care. Point-based scores are more understandable and explainable than other complex models and are now widely used in clinical decision making. However, the development of the risk scoring model is nontrivial and has not yet been systematically presented, with few studies investigating methods of clinical score generation using electronic health records. OBJECTIVE This study aims to propose AutoScore, a machine learning-based automatic clinical score generator consisting of 6 modules for developing interpretable point-based scores. Future users can employ the AutoScore framework to create clinical scores effortlessly in various clinical applications. METHODS We proposed the AutoScore framework comprising 6 modules that included variable ranking, variable transformation, score derivation, model selection, score fine-tuning, and model evaluation. To demonstrate the performance of AutoScore, we used data from the Beth Israel Deaconess Medical Center to build a scoring model for mortality prediction and then compared the data with other baseline models using the receiver operating characteristic analysis. A software package in R 3.5.3 (R Foundation) was also developed to demonstrate the implementation of AutoScore. RESULTS Implemented on the data set with 44,918 individual admission episodes of intensive care, the AutoScore-created scoring models performed comparably well as other standard methods (ie, logistic regression, stepwise regression, least absolute shrinkage and selection operator, and random forest) in terms of predictive accuracy and model calibration but required fewer predictors and presented high interpretability and accessibility. The nine-variable, AutoScore-created, point-based scoring model achieved an area under the curve (AUC) of 0.780 (95% CI 0.764-0.798), whereas the model of logistic regression with 24 variables had an AUC of 0.778 (95% CI 0.760-0.795). Moreover, the AutoScore framework also drives the clinical research continuum and automation with its integration of all necessary modules. CONCLUSIONS We developed an easy-to-use, machine learning-based automatic clinical score generator, AutoScore; systematically presented its structure; and demonstrated its superiority (predictive performance and interpretability) over other conventional methods using a benchmark database. AutoScore will emerge as a potential scoring tool in various medical applications.
Collapse
Affiliation(s)
- Feng Xie
- Programme in Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
| | - Bibhas Chakraborty
- Programme in Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
- Department of Statistics and Applied Probability, National University of Singapore, Singapore, Singapore
- Department of Biostatistics & Bioinformatics, Duke University, Durham, NC, United States
| | - 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
| | - Benjamin Alan Goldstein
- Programme in Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
- Department of Biostatistics & Bioinformatics, Duke University, Durham, NC, United States
| | - Nan Liu
- Programme in Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
- Health Services Research Centre, Singapore Health Services, Singapore, Singapore
- Institute of Data Science, National University of Singapore, Singapore, Singapore
| |
Collapse
|
33
|
Holmström IK, Kaminsky E, Lindberg Y, Spangler D, Winblad U. Registered Nurses' experiences of using a clinical decision support system for triage of emergency calls: A qualitative interview study. J Adv Nurs 2020; 76:3104-3112. [DOI: 10.1111/jan.14542] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2020] [Revised: 07/23/2020] [Accepted: 07/29/2020] [Indexed: 11/28/2022]
Affiliation(s)
- Inger K. Holmström
- School of Health, Care and Social Welfare Mälardalen University Västerås Sweden
- Department of Public Health and Caring Sciences Uppsala University Uppsala Sweden
| | - Elenor Kaminsky
- Department of Public Health and Caring Sciences Uppsala University Uppsala Sweden
| | - Ylva Lindberg
- Department of Public Health and Caring Sciences Uppsala University Uppsala Sweden
| | - Douglas Spangler
- Department of Public Health and Caring Sciences Uppsala University Uppsala Sweden
- Uppsala Center for Prehospital Research Department of Surgical Sciences—Anesthesia and Intensive Care Uppsala University Uppsala Sweden
| | - Ulrika Winblad
- Department of Public Health and Caring Sciences Uppsala University Uppsala Sweden
| |
Collapse
|
34
|
Tollinton L, Metcalf AM, Velupillai S. Enhancing predictions of patient conveyance using emergency call handler free text notes for unconscious and fainting incidents reported to the London Ambulance Service. Int J Med Inform 2020; 141:104179. [PMID: 32663739 DOI: 10.1016/j.ijmedinf.2020.104179] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2020] [Revised: 04/28/2020] [Accepted: 05/13/2020] [Indexed: 11/29/2022]
Abstract
OBJECTIVE Pre-hospital emergency medical services use clinical decision support systems (CDSS) to triage calls. Call handlers often supplement this by making free text notes covering key incident information. We investigate whether machine learning approaches using features from such free text notes can improve prediction of unconscious patients who require conveyance. MATERIALS AND METHODS We analysed a subset of all London Ambulance Service calls that were triaged through the Medical Priority Dispatch System (MPDS) as involving an unconscious or fainting patient in 2018. We use and compare two machine learning algorithms: random forest (RF) and gradient boosting machine (GBM). For each incident, we predict whether the patient will be conveyed to a hospital emergency department or equivalent using as features 1) the MPDS code, 2) the free text notes and 3) the two together. We evaluate model performance using the area under the curve (AUC) metric. Given the imbalance of outcomes (patient conveyed 71 %, not conveyed 29 %), we also consider sensitivity and specificity. RESULTS Using only the MPDS code resulted in an AUC of 0.57. Using the text notes gave an improved AUC score of 0.63 and combining the two gave an AUC score of 0.64 (scores were similar for RF and GBM). GBM models scored better on sensitivity (0.93 vs 0.62 for RF in the combined model), but specificity was lower (0.17 vs. 0.56 for RF in the combined model). CONCLUSIONS Using information contained in the free text notes made by call handlers in combination with MPDS improves prediction of unconscious and fainting patients requiring conveyance to a hospital emergency department (or equivalent) when compared with machine learning models using MPDS codes only. This suggests there is some useful information in unstructured data captured by emergency call handlers that complements MPDS codes. Quantifying this gain can help inform emergency medical service policy when evaluating the decision to expand or augment existing CDSS.
Collapse
Affiliation(s)
- Liam Tollinton
- Centre for Urban Science and Progress Studies, King's College London, UK
| | | | - Sumithra Velupillai
- Centre for Urban Science and Progress Studies, King's College London, UK; Institute for Psychiatry, Psychology & Neuroscience, King's College London, UK.
| |
Collapse
|