1
|
Ahmadi SAY, Karimi Y, Abdollahi A, Kabir A. Modeling for Prediction of Mortality Based on past Medical History in Hospitalized COVID-19 Patients: A Secondary Analysis. THE CANADIAN JOURNAL OF INFECTIOUS DISEASES & MEDICAL MICROBIOLOGY = JOURNAL CANADIEN DES MALADIES INFECTIEUSES ET DE LA MICROBIOLOGIE MEDICALE 2024; 2024:3256108. [PMID: 38984269 PMCID: PMC11233185 DOI: 10.1155/2024/3256108] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/12/2023] [Revised: 05/23/2024] [Accepted: 06/21/2024] [Indexed: 07/11/2024]
Abstract
Introduction Although COVID-19 is not currently a public health emergency, it will affect susceptible individuals in the post-COVID-19 era. Hence, the present study aimed to develop a model for Iranian patients to identify at-risk groups based on past medical history (PMHx) and some other factors affecting the death of patients hospitalized with COVID-19. Methods A secondary study was conducted with the existing data of hospitalized COVID-19 adult patients in the hospitals covered by Iran University of Medical Sciences. PMHx was extracted from the registered ICD-10 codes. Stepwise logistic regression was used to predict mortality by PMHx and background covariates such as intensive care unit (ICU) admission. Crude population attributable fraction (PAF) as well as crude and adjusted odds ratio (OR) with 95% confidence interval (CI) were reported. Results A total of 8879 patients were selected with 19.68% mortality. Infectious and parasitic diseases' history showed the greatest association (OR = 5.72, 95% CI: 4.20, 7.82), while the greatest PAF was for cardiovascular system diseases (20.46%). According to logistic regression modeling, the largest effect, other than ICU admission and age, was for history of infectious and parasitic diseases (OR = 3.089, 95% CI: 2.13, 4.47). A good performance was achieved (area under curve = 0.875). Conclusion Considering the prevalence of underlying diseases, many mortality cases of COVID-19 are attributable to the history of cardiovascular disease. Future studies are needed for policy making regarding reduction of COVID-19 mortality in susceptible groups in the post-COVID-19 era.
Collapse
Affiliation(s)
- Seyyed Amir Yasin Ahmadi
- Preventive Medicine and Public Health Research CenterPsychosocial Health Research InstituteIran University of Medical Sciences, Tehran, Iran
| | - Yeganeh Karimi
- Tehran Heart CenterCardiovascular Diseases Research InstituteTehran University of Medical Sciences, Tehran, Iran
| | - Arash Abdollahi
- Minimally Invasive Surgery Research CenterIran University of Medical Sciences, Tehran, Iran
| | - Ali Kabir
- Minimally Invasive Surgery Research CenterIran University of Medical Sciences, Tehran, Iran
| |
Collapse
|
2
|
Hamar Á, Mohammed D, Váradi A, Herczeg R, Balázsfalvi N, Fülesdi B, László I, Gömöri L, Gergely PA, Kovacs GL, Jáksó K, Gombos K. COVID-19 mortality prediction in Hungarian ICU settings implementing random forest algorithm. Sci Rep 2024; 14:11941. [PMID: 38789490 PMCID: PMC11126653 DOI: 10.1038/s41598-024-62791-9] [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: 03/13/2024] [Accepted: 05/19/2024] [Indexed: 05/26/2024] Open
Abstract
The emergence of newer SARS-CoV-2 variants of concern (VOCs) profoundly changed the ICU demography; this shift in the virus's genotype and its correlation to lethality in the ICUs is still not fully investigated. We aimed to survey ICU patients' clinical and laboratory parameters in correlation with SARS-CoV-2 variant genotypes to lethality. 503 COVID-19 ICU patients were included in our study beginning in January 2021 through November 2022 in Hungary. Furthermore, we implemented random forest (RF) as a potential predictor regarding SARS-CoV-2 lethality among 649 ICU patients in two ICU centers. Survival analysis and comparison of hypertension (HT), diabetes mellitus (DM), and vaccination effects were conducted. Logistic regression identified DM as a significant mortality risk factor (OR: 1.55, 95% CI 1.06-2.29, p = 0.025), while HT showed marginal significance. Additionally, vaccination demonstrated protection against mortality (p = 0.028). RF detected lethality with 81.42% accuracy (95% CI 73.01-88.11%, [AUC]: 91.6%), key predictors being PaO2/FiO2 ratio, lymphocyte count, and chest Computed Tomography Severity Score (CTSS). Although a smaller number of patients require ICU treatment among Omicron cases, the likelihood of survival has not proportionately increased for those who are admitted to the ICU. In conclusion, our RF model supports more effective clinical decision-making among ICU COVID-19 patients.
Collapse
Affiliation(s)
- Ágoston Hamar
- Department of Laboratory Medicine, Medical School, University of Pécs, Pécs, Hungary
- Molecular Medicine Research Group, Szentágothai Research Centre, University of Pécs, Pécs, Hungary
| | - Daryan Mohammed
- Molecular Medicine Research Group, Szentágothai Research Centre, University of Pécs, Pécs, Hungary
| | - Alex Váradi
- Molecular Medicine Research Group, Szentágothai Research Centre, University of Pécs, Pécs, Hungary
- Institute of Metagenomics, University of Debrecen, Debrecen, Hungary
| | - Róbert Herczeg
- Molecular Medicine Research Group, Szentágothai Research Centre, University of Pécs, Pécs, Hungary
| | - Norbert Balázsfalvi
- Department of Anaesthesiology and Intensive Care, University of Debrecen, Debrecen, Hungary
| | - Béla Fülesdi
- Department of Anaesthesiology and Intensive Care, University of Debrecen, Debrecen, Hungary
| | - István László
- Department of Anaesthesiology and Intensive Care, University of Debrecen, Debrecen, Hungary
| | - Lídia Gömöri
- Doctoral School of Neuroscience, University of Debrecen, Debrecen, Hungary
| | | | - Gabor Laszlo Kovacs
- Department of Laboratory Medicine, Medical School, University of Pécs, Pécs, Hungary
- Molecular Medicine Research Group, Szentágothai Research Centre, University of Pécs, Pécs, Hungary
| | - Krisztián Jáksó
- Department of Anaesthesiology and Intensive Care, Clinical Centre, University of Pécs, Pécs, Hungary
| | - Katalin Gombos
- Department of Laboratory Medicine, Medical School, University of Pécs, Pécs, Hungary.
- Molecular Medicine Research Group, Szentágothai Research Centre, University of Pécs, Pécs, Hungary.
| |
Collapse
|
3
|
Radomyslsky Z, Kivity S, Alon Y, Saban M. Modeling mortality prediction in older adults with dementia receiving COVID-19 vaccination. BMC Geriatr 2024; 24:454. [PMID: 38789939 PMCID: PMC11127399 DOI: 10.1186/s12877-024-04982-7] [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: 10/21/2023] [Accepted: 04/16/2024] [Indexed: 05/26/2024] Open
Abstract
OBJECTIVE This study compared COVID-19 outcomes between vaccinated and unvaccinated older adults with and without cognitive impairment. METHOD Electronic health records from Israel from March 2020-February 2022 were analyzed for a large cohort (N = 85,288) aged 65 + . Machine learning constructed models to predict mortality risk from patient factors. Outcomes examined were COVID-19 mortality and hospitalization post-vaccination. RESULTS Our study highlights the significant reduction in mortality risk among older adults with cognitive disorders following COVID-19 vaccination, showcasing a survival rate improvement to 93%. Utilizing machine learning for mortality prediction, we found the XGBoost model, enhanced with inverse probability of treatment weighting, to be the most effective, achieving an AUC-PR value of 0.89. This underscores the importance of predictive analytics in identifying high-risk individuals, emphasizing the critical role of vaccination in mitigating mortality and supporting targeted healthcare interventions. CONCLUSIONS COVID-19 vaccination strongly reduced poor outcomes in older adults with cognitive impairment. Predictive analytics can help identify highest-risk cases requiring targeted interventions.
Collapse
Affiliation(s)
- Zorian Radomyslsky
- Maccabi Healthcare Services, 6812509, Tel Aviv-Jaffa, Israel.
- Ariel University, School of Health Sciences, Ariel, Israel.
| | - Sara Kivity
- Maccabi Healthcare Services, 6812509, Tel Aviv-Jaffa, Israel.
| | - Yaniv Alon
- Nursing Department, School of Health Professions, Faculty of Medical & Health Sciences, Tel Aviv University, Ramat Aviv, Tel Aviv, 69978, Israel
| | - Mor Saban
- Nursing Department, School of Health Professions, Faculty of Medical & Health Sciences, Tel Aviv University, Ramat Aviv, Tel Aviv, 69978, Israel
| |
Collapse
|
4
|
Tariq MU, Ismail SB. Deep learning in public health: Comparative predictive models for COVID-19 case forecasting. PLoS One 2024; 19:e0294289. [PMID: 38483948 PMCID: PMC10939212 DOI: 10.1371/journal.pone.0294289] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2023] [Accepted: 10/28/2023] [Indexed: 03/17/2024] Open
Abstract
The COVID-19 pandemic has had a significant impact on both the United Arab Emirates (UAE) and Malaysia, emphasizing the importance of developing accurate and reliable forecasting mechanisms to guide public health responses and policies. In this study, we compared several cutting-edge deep learning models, including Long Short-Term Memory (LSTM), bidirectional LSTM, Convolutional Neural Networks (CNN), hybrid CNN-LSTM, Multilayer Perceptron's, and Recurrent Neural Networks (RNN), to project COVID-19 cases in the aforementioned regions. These models were calibrated and evaluated using a comprehensive dataset that includes confirmed case counts, demographic data, and relevant socioeconomic factors. To enhance the performance of these models, Bayesian optimization techniques were employed. Subsequently, the models were re-evaluated to compare their effectiveness. Analytic approaches, both predictive and retrospective in nature, were used to interpret the data. Our primary objective was to determine the most effective model for predicting COVID-19 cases in the United Arab Emirates (UAE) and Malaysia. The findings indicate that the selected deep learning algorithms were proficient in forecasting COVID-19 cases, although their efficacy varied across different models. After a thorough evaluation, the model architectures most suitable for the specific conditions in the UAE and Malaysia were identified. Our study contributes significantly to the ongoing efforts to combat the COVID-19 pandemic, providing crucial insights into the application of sophisticated deep learning algorithms for the precise and timely forecasting of COVID-19 cases. These insights hold substantial value for shaping public health strategies, enabling authorities to develop targeted and evidence-based interventions to manage the virus spread and its impact on the populations of the UAE and Malaysia. The study confirms the usefulness of deep learning methodologies in efficiently processing complex datasets and generating reliable projections, a skill of great importance in healthcare and professional settings.
Collapse
Affiliation(s)
- Muhammad Usman Tariq
- Abu Dhabi University, Abu Dhabi, United Arab Emirates
- Universiti Tun Hussein Onn Malaysia (UTHM), Parit Raja, Malaysia
| | | |
Collapse
|
5
|
Viderman D, Kotov A, Popov M, Abdildin Y. Machine and deep learning methods for clinical outcome prediction based on physiological data of COVID-19 patients: a scoping review. Int J Med Inform 2024; 182:105308. [PMID: 38091862 DOI: 10.1016/j.ijmedinf.2023.105308] [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: 09/15/2023] [Revised: 11/20/2023] [Accepted: 12/03/2023] [Indexed: 01/07/2024]
Abstract
INTRODUCTION Since the beginning of the COVID-19 pandemic, numerous machine and deep learning (MDL) methods have been proposed in the literature to analyze patient physiological data. The objective of this review is to summarize various aspects of these methods and assess their practical utility for predicting various clinical outcomes. METHODS We searched PubMed, Scopus, and Cochrane Library, screened and selected the studies matching the inclusion criteria. The clinical analysis focused on the characteristics of the patient cohorts in the studies included in this review, the specific tasks in the context of the COVID-19 pandemic that machine and deep learning methods were used for, and their practical limitations. The technical analysis focused on the details of specific MDL methods and their performance. RESULTS Analysis of the 48 selected studies revealed that the majority (∼54 %) of them examined the application of MDL methods for the prediction of survival/mortality-related patient outcomes, while a smaller fraction (∼13 %) of studies also examined applications to the prediction of patients' physiological outcomes and hospital resource utilization. 21 % of the studies examined the application of MDL methods to multiple clinical tasks. Machine and deep learning methods have been shown to be effective at predicting several outcomes of COVID-19 patients, such as disease severity, complications, intensive care unit (ICU) transfer, and mortality. MDL methods also achieved high accuracy in predicting the required number of ICU beds and ventilators. CONCLUSION Machine and deep learning methods have been shown to be valuable tools for predicting disease severity, organ dysfunction and failure, patient outcomes, and hospital resource utilization during the COVID-19 pandemic. The discovered knowledge and our conclusions and recommendations can also be useful to healthcare professionals and artificial intelligence researchers in managing future pandemics.
Collapse
Affiliation(s)
- Dmitriy Viderman
- Department of Surgery, School of Medicine, Nazarbayev University, Astana, Kazakhstan; Department of Anesthesiology, Intensive Care, and Pain Medicine, National Research Oncology Center, Astana, Kazakhstan.
| | - Alexander Kotov
- Department of Computer Science, College of Engineering, Wayne State University, Detroit, USA.
| | - Maxim Popov
- Department of Computer Science, School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan.
| | - Yerkin Abdildin
- Department of Mechanical and Aerospace Engineering, School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan.
| |
Collapse
|
6
|
Nieto-Gutierrez W, Campos-Chambergo J, Gonzalez-Ayala E, Oyola-Garcia O, Alejandro-Mora A, Luis-Aguirre E, Pasquel-Santillan R, Leiva-Aguirre J, Ugarte-Gil C, Loyola S. Prediction models of COVID-19 fatality in nine Peruvian provinces: A secondary analysis of the national epidemiological surveillance system. PLOS GLOBAL PUBLIC HEALTH 2024; 4:e0002854. [PMID: 38285714 PMCID: PMC10824411 DOI: 10.1371/journal.pgph.0002854] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/21/2023] [Accepted: 01/05/2024] [Indexed: 01/31/2024]
Abstract
There are initiatives to promote the creation of predictive COVID-19 fatality models to assist decision-makers. The study aimed to develop prediction models for COVID-19 fatality using population data recorded in the national epidemiological surveillance system of Peru. A retrospective cohort study was conducted (March to September of 2020). The study population consisted of confirmed COVID-19 cases reported in the surveillance system of nine provinces of Lima, Peru. A random sample of 80% of the study population was selected, and four prediction models were constructed using four different strategies to select variables: 1) previously analyzed variables in machine learning models; 2) based on the LASSO method; 3) based on significance; and 4) based on a post-hoc approach with variables consistently included in the three previous strategies. The internal validation was performed with the remaining 20% of the population. Four prediction models were successfully created and validate using data from 22,098 cases. All models performed adequately and similarly; however, we selected models derived from strategy 1 (AUC 0.89, CI95% 0.87-0.91) and strategy 4 (AUC 0.88, CI95% 0.86-0.90). The performance of both models was robust in validation and sensitivity analyses. This study offers insights into estimating COVID-19 fatality within the Peruvian population. Our findings contribute to the advancement of prediction models for COVID-19 fatality and may aid in identifying individuals at increased risk, enabling targeted interventions to mitigate the disease. Future studies should confirm the performance and validate the usefulness of the models described here under real-world conditions and settings.
Collapse
Affiliation(s)
- Wendy Nieto-Gutierrez
- Facultad de Salud Pública, Universidad Peruana Cayetano Heredia, Lima, Perú
- Universidad Científica del Sur, Lima, Perú
| | - Jaid Campos-Chambergo
- Dirección de Epidemiología e Investigación, Dirección Regional de Salud Lima Provincias, Lima, Perú
| | - Enrique Gonzalez-Ayala
- Dirección de Epidemiología e Investigación, Dirección Regional de Salud Lima Provincias, Lima, Perú
| | - Oswaldo Oyola-Garcia
- Dirección de Epidemiología e Investigación, Dirección Regional de Salud Lima Provincias, Lima, Perú
| | - Alberti Alejandro-Mora
- Dirección de Epidemiología e Investigación, Dirección Regional de Salud Lima Provincias, Lima, Perú
| | - Eliana Luis-Aguirre
- Dirección de Epidemiología e Investigación, Dirección Regional de Salud Lima Provincias, Lima, Perú
| | - Roly Pasquel-Santillan
- Dirección de Epidemiología e Investigación, Dirección Regional de Salud Lima Provincias, Lima, Perú
| | - Juan Leiva-Aguirre
- Dirección de Epidemiología e Investigación, Dirección Regional de Salud Lima Provincias, Lima, Perú
| | - Cesar Ugarte-Gil
- Facultad de Medicina, Universidad Peruana Cayetano Heredia, Lima, Perú
- Instituto de Medicina Tropical Alexander von Humboldt, Universidad Peruana Cayetano Heredia, Lima, Perú
- Department of Epidemiology, School of Public and Population Health, University of Texas Medical Branch, Galveston, Texas, United States of America
| | - Steev Loyola
- Dirección de Epidemiología e Investigación, Dirección Regional de Salud Lima Provincias, Lima, Perú
- Facultad de Medicina, Universidad Peruana Cayetano Heredia, Lima, Perú
| |
Collapse
|
7
|
Ferri P, Romero-Garcia N, Badenes R, Lora-Pablos D, Morales TG, Gómez de la Cámara A, García-Gómez JM, Sáez C. Extremely missing numerical data in Electronic Health Records for machine learning can be managed through simple imputation methods considering informative missingness: A comparative of solutions in a COVID-19 mortality case study. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 242:107803. [PMID: 37703700 DOI: 10.1016/j.cmpb.2023.107803] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/21/2023] [Revised: 08/28/2023] [Accepted: 09/05/2023] [Indexed: 09/15/2023]
Abstract
BACKGROUND AND OBJECTIVE Reusing Electronic Health Records (EHRs) for Machine Learning (ML) leads on many occasions to extremely incomplete and sparse tabular datasets, which can hinder the model development processes and limit their performance and generalization. In this study, we aimed to characterize the most effective data imputation techniques and ML models for dealing with highly missing numerical data in EHRs, in the case where only a very limited number of data are complete, as opposed to the usual case of having a reduced number of missing values. METHODS We used a case study including full blood count laboratory data, demographic and survival data in the context of COVID-19 hospital admissions and evaluated 30 processing pipelines combining imputation methods with ML classifiers. The imputation methods included missing mask, translation and encoding, mean imputation, k-nearest neighbors' imputation, Bayesian ridge regression imputation and generative adversarial imputation networks. The classifiers included k-nearest neighbors, logistic regression, random forest, gradient boosting and deep multilayer perceptron. RESULTS Our results suggest that in the presence of highly missing data, combining translation and encoding imputation-which considers informative missingness-with tree ensemble classifiers-random forest and gradient boosting-is a sensible choice when aiming to maximize performance, in terms of area under curve. CONCLUSIONS Based on our findings, we recommend the consideration of this imputer-classifier configuration when constructing models in the presence of extremely incomplete numerical data in EHR.
Collapse
Affiliation(s)
- Pablo Ferri
- Biomedical Data Science Lab, Instituto Universitario de Tecnologías de la Información y Comunicaciones, Universitat Politècnica de València, Camino de Vera s/n, Valencia 46022, Spain.
| | | | - Rafael Badenes
- Departament de Cirugia, Universitat de València, Spain; Instituto INCLIVA, Hospital Clínico Universitario de Valencia, Spain; Department Anesthesiology, Surgical-Trauma Intensive Care and Pain Clinic, Hospital Clínic Universitari, Valencia, Spain
| | - David Lora-Pablos
- Instituto de Investigación imas12, Hospital 12 de Octubre, Madrid, Spain; Facultad de Estudios Estadísticos, Universidad Complutense de Madrid, Spain
| | | | | | - Juan M García-Gómez
- Biomedical Data Science Lab, Instituto Universitario de Tecnologías de la Información y Comunicaciones, Universitat Politècnica de València, Camino de Vera s/n, Valencia 46022, Spain
| | - Carlos Sáez
- Biomedical Data Science Lab, Instituto Universitario de Tecnologías de la Información y Comunicaciones, Universitat Politècnica de València, Camino de Vera s/n, Valencia 46022, Spain
| |
Collapse
|
8
|
Liu L, Song W, Patil N, Sainlaire M, Jasuja R, Dykes PC. Predicting COVID-19 severity: Challenges in reproducibility and deployment of machine learning methods. Int J Med Inform 2023; 179:105210. [PMID: 37769368 DOI: 10.1016/j.ijmedinf.2023.105210] [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: 03/27/2023] [Revised: 08/29/2023] [Accepted: 08/30/2023] [Indexed: 09/30/2023]
Abstract
The increasing use of electronic health records (EHR) based computable phenotypes in clinical research is providing new opportunities for development of data-driven medical applications. Adopted widely in the United States and globally, EHRs facilitate systematic collection of patients' longitudinal information, which serves as one of the important foundations for artificial intelligence applications in medicine. Harmonization of input variables and outcome definitions is critically important for wider clinical applicability of artificial intelligence (AI) methodologies. In this review, we focused on Coronavirus Disease 2019 (COVID-19) severity machine learning prediction models and explored the pipeline for standardizing future disease severity model development using EHR information. We identified 2,967 studies published between 01/01/2020 and 02/15/2022 and selected 135 independent studies that had built machine learning prediction models to predict severity related outcomes of COVID-19 patients based on EHR data for the final review. These 135 studies spanning across 27 counties covered a broad range of severity related prediction outcomes. We observed substantial inconsistency in COVID-19 severity phenotype definitions among models in these studies. Moreover, there was a gap between the outcome of these models and clinician-recognized clinical concepts. Accordingly, we recommend that robust clinical input metrics, with outcome definitions which eliminate ambiguity in interpretation, to reduce algorithmic bias, mitigate model brittleness and improve generalizability of a universal model for COVID-19 severity. This framework can potentially be extended to broader clinical application.
Collapse
Affiliation(s)
- Luwei Liu
- Department of Medicine, Brigham & Women's Hospital, Boston, MA, USA
| | - Wenyu Song
- Department of Medicine, Brigham & Women's Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA
| | - Namrata Patil
- Department of Surgery, Brigham & Women's Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA
| | | | - Ravi Jasuja
- Department of Medicine, Brigham & Women's Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA.
| | - Patricia C Dykes
- Department of Medicine, Brigham & Women's Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA
| |
Collapse
|
9
|
Natanov D, Avihai B, McDonnell E, Lee E, Cook B, Altomare N, Ko T, Chaia A, Munoz C, Ouellette S, Nyalakonda S, Cederbaum V, Parikh PD, Blaser MJ. Predicting COVID-19 prognosis in hospitalized patients based on early status. mBio 2023; 14:e0150823. [PMID: 37681966 PMCID: PMC10653946 DOI: 10.1128/mbio.01508-23] [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: 07/12/2023] [Accepted: 07/17/2023] [Indexed: 09/09/2023] Open
Abstract
IMPORTANCE COVID-19 remains the fourth leading cause of death in the United States. Predicting COVID-19 patient prognosis is essential to help efficiently allocate resources, including ventilators and intensive care unit beds, particularly when hospital systems are strained. Our PLABAC and PRABLE models are unique because they accurately assess a COVID-19 patient's risk of death from only age and five commonly ordered laboratory tests. This simple design is important because it allows these models to be used by clinicians to rapidly assess a patient's risk of decompensation and serve as a real-time aid when discussing difficult, life-altering decisions for patients. Our models have also shown generalizability to external populations across the United States. In short, these models are practical, efficient tools to assess and communicate COVID-19 prognosis.
Collapse
Affiliation(s)
- David Natanov
- Rutgers Robert Wood Johnson Medical School, Piscataway, New Jersey, USA
| | - Byron Avihai
- Rutgers Robert Wood Johnson Medical School, Piscataway, New Jersey, USA
| | - Erin McDonnell
- Rutgers Robert Wood Johnson Medical School, Piscataway, New Jersey, USA
| | - Eileen Lee
- Rutgers Robert Wood Johnson Medical School, Piscataway, New Jersey, USA
| | - Brennan Cook
- Rutgers Robert Wood Johnson Medical School, Piscataway, New Jersey, USA
| | - Nicole Altomare
- Rutgers Robert Wood Johnson Medical School, Piscataway, New Jersey, USA
| | - Tomohiro Ko
- Rutgers Robert Wood Johnson Medical School, Piscataway, New Jersey, USA
| | - Angelo Chaia
- Rutgers Robert Wood Johnson Medical School, Piscataway, New Jersey, USA
| | - Carolayn Munoz
- Rutgers Robert Wood Johnson Medical School, Piscataway, New Jersey, USA
| | | | - Suraj Nyalakonda
- Rutgers Robert Wood Johnson Medical School, Piscataway, New Jersey, USA
| | - Vanessa Cederbaum
- Rutgers Robert Wood Johnson Medical School, Piscataway, New Jersey, USA
| | - Payal D. Parikh
- Department of Medicine, Robert Wood Johnson Medical School, New Brunswick, New Jersey, USA
| | - Martin J. Blaser
- Center for Advanced Biotechnology and Medicine, Rutgers University, New Brunswick, New Jersey, USA
| |
Collapse
|
10
|
Chimbunde E, Sigwadhi LN, Tamuzi JL, Okango EL, Daramola O, Ngah VD, Nyasulu PS. Machine learning algorithms for predicting determinants of COVID-19 mortality in South Africa. Front Artif Intell 2023; 6:1171256. [PMID: 37899965 PMCID: PMC10600470 DOI: 10.3389/frai.2023.1171256] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2023] [Accepted: 08/15/2023] [Indexed: 10/31/2023] Open
Abstract
Background COVID-19 has strained healthcare resources, necessitating efficient prognostication to triage patients effectively. This study quantified COVID-19 risk factors and predicted COVID-19 intensive care unit (ICU) mortality in South Africa based on machine learning algorithms. Methods Data for this study were obtained from 392 COVID-19 ICU patients enrolled between 26 March 2020 and 10 February 2021. We used an artificial neural network (ANN) and random forest (RF) to predict mortality among ICU patients and a semi-parametric logistic regression with nine covariates, including a grouping variable based on K-means clustering. Further evaluation of the algorithms was performed using sensitivity, accuracy, specificity, and Cohen's K statistics. Results From the semi-parametric logistic regression and ANN variable importance, age, gender, cluster, presence of severe symptoms, being on the ventilator, and comorbidities of asthma significantly contributed to ICU death. In particular, the odds of mortality were six times higher among asthmatic patients than non-asthmatic patients. In univariable and multivariate regression, advanced age, PF1 and 2, FiO2, severe symptoms, asthma, oxygen saturation, and cluster 4 were strongly predictive of mortality. The RF model revealed that intubation status, age, cluster, diabetes, and hypertension were the top five significant predictors of mortality. The ANN performed well with an accuracy of 71%, a precision of 83%, an F1 score of 100%, Matthew's correlation coefficient (MCC) score of 100%, and a recall of 88%. In addition, Cohen's k-value of 0.75 verified the most extreme discriminative power of the ANN. In comparison, the RF model provided a 76% recall, an 87% precision, and a 65% MCC. Conclusion Based on the findings, we can conclude that both ANN and RF can predict COVID-19 mortality in the ICU with accuracy. The proposed models accurately predict the prognosis of COVID-19 patients after diagnosis. The models can be used to prioritize COVID-19 patients with a high mortality risk in resource-constrained ICUs.
Collapse
Affiliation(s)
- Emmanuel Chimbunde
- Division of Epidemiology and Biostatistics, Department of Global Health, Faculty of Medicine and Health Sciences, Stellenbosch University, Cape Town, South Africa
| | - Lovemore N. Sigwadhi
- Division of Epidemiology and Biostatistics, Department of Global Health, Faculty of Medicine and Health Sciences, Stellenbosch University, Cape Town, South Africa
| | - Jacques L. Tamuzi
- Division of Epidemiology and Biostatistics, Department of Global Health, Faculty of Medicine and Health Sciences, Stellenbosch University, Cape Town, South Africa
| | | | - Olawande Daramola
- Department of Information Technology, Faculty of Informatics and Design, Cape Peninsula University of Technology, Cape Town, South Africa
| | - Veranyuy D. Ngah
- Division of Epidemiology and Biostatistics, Department of Global Health, Faculty of Medicine and Health Sciences, Stellenbosch University, Cape Town, South Africa
| | - Peter S. Nyasulu
- Division of Epidemiology and Biostatistics, Department of Global Health, Faculty of Medicine and Health Sciences, Stellenbosch University, Cape Town, South Africa
- Division of Epidemiology and Biostatistics, School of Public Health, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa
| |
Collapse
|
11
|
Alkhammash EH, Assiri SA, Nemenqani DM, Althaqafi RMM, Hadjouni M, Saeed F, Elshewey AM. Application of Machine Learning to Predict COVID-19 Spread via an Optimized BPSO Model. Biomimetics (Basel) 2023; 8:457. [PMID: 37887588 PMCID: PMC10604133 DOI: 10.3390/biomimetics8060457] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2023] [Revised: 09/21/2023] [Accepted: 09/21/2023] [Indexed: 10/28/2023] Open
Abstract
During the pandemic of the coronavirus disease (COVID-19), statistics showed that the number of affected cases differed from one country to another and also from one city to another. Therefore, in this paper, we provide an enhanced model for predicting COVID-19 samples in different regions of Saudi Arabia (high-altitude and sea-level areas). The model is developed using several stages and was successfully trained and tested using two datasets that were collected from Taif city (high-altitude area) and Jeddah city (sea-level area) in Saudi Arabia. Binary particle swarm optimization (BPSO) is used in this study for making feature selections using three different machine learning models, i.e., the random forest model, gradient boosting model, and naive Bayes model. A number of predicting evaluation metrics including accuracy, training score, testing score, F-measure, recall, precision, and receiver operating characteristic (ROC) curve were calculated to verify the performance of the three machine learning models on these datasets. The experimental results demonstrated that the gradient boosting model gives better results than the random forest and naive Bayes models with an accuracy of 94.6% using the Taif city dataset. For the dataset of Jeddah city, the results demonstrated that the random forest model outperforms the gradient boosting and naive Bayes models with an accuracy of 95.5%. The dataset of Jeddah city achieved better results than the dataset of Taif city in Saudi Arabia using the enhanced model for the term of accuracy.
Collapse
Affiliation(s)
- Eman H. Alkhammash
- Department of Computer Science, College of Computers and Information Technology, Taif University, P.O. Box 11099, Taif 21944, Saudi Arabia;
| | - Sara Ahmad Assiri
- Otolaryngology-Head and Neck Surgert Department, King Faisal Hospital, P.O. Box 11099, Taif 21944, Saudi Arabia;
| | - Dalal M. Nemenqani
- College of Medicine, Taif University, P.O. Box 11099, Taif 21944, Saudi Arabia; (D.M.N.); (R.M.M.A.)
| | - Raad M. M. Althaqafi
- College of Medicine, Taif University, P.O. Box 11099, Taif 21944, Saudi Arabia; (D.M.N.); (R.M.M.A.)
| | - Myriam Hadjouni
- Department of Computer Sciences, College of Computer and Information Science, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
| | - Faisal Saeed
- DAAI Research Group, Department of Computing and Data Science, School of Computing and Digital Technology, Birmingham City University, Birmingham B4 7XG, UK;
| | - Ahmed M. Elshewey
- Faculty of Computers and Information, Computer Science Department, Suez University, Suez 43533, Egypt;
| |
Collapse
|
12
|
Merzah MA, Sulaiman D, Karim AA, Khalil ME, Gupta S, Almuzaini Y, Hashemi S, Mathew S, Khatoon S, Hoque MB. A systematic review and meta-analysis on the prevalence and impact of coronary artery disease in hospitalized COVID-19 patients. Heliyon 2023; 9:e19493. [PMID: 37681130 PMCID: PMC10480662 DOI: 10.1016/j.heliyon.2023.e19493] [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: 12/13/2022] [Revised: 08/22/2023] [Accepted: 08/24/2023] [Indexed: 09/09/2023] Open
Abstract
Background COVID-19 accounts for more than half a billion deaths globally. The clinical manifestations may vary in due course. Despite several studies aimed at determining the extent to which the disease's severity and mortality remain high when combined with other comorbidities, more research is required. Therefore, this review aimed to measure the pooled prevalence of coronary artery disease (CAD) among COVID-19 patients, specifically those with a history of CAD. Additionally, we aim to assess the association between mortality due to CAD and the severity of COVID-19 among hospitalized patients. Method A comprehensive search in PubMed, Web of Science, the Cochrane Library, and the WHO COVID-19 database was conducted. English studies with original data on CAD, mortality, and ARDS among COVID-19 patients were included. PRISMA guidelines were followed. Results Among the 2007 identified articles, 76 studies met the inclusion criteria. The pooled prevalence of CAD among COVID-19 patients was 14.4%(95% CI: 12.7-16.2). The highest prevalence was observed in European studies at 18.2%(95% CI: 13.3-24.2), while the lowest was in Asian studies at 10.4% (95% CI: 6.4-16.3). Participants with concurrent CAD at the time of hospital admission had twice the odds of mortality due to COVID-19 (2.64 [95% CI: 2.30-3.04]) with moderate heterogeneity (I2 = 45%, p < 0.01). Hospitalized COVID-19 patients with CAD had a 50% higher risk of ARDS (95% CI: 0.62-3.66), but this difference was not statistically significant. Conclusion Although our analysis revealed evidence for a relationship between concurrent CAD at the time of hospital admission and mortality from COVID-19, however, global variation in health infrastructure, limitations of data reporting, and the effects of emerging variants must be considered in future investigations.
Collapse
Affiliation(s)
- Mohammed A. Merzah
- Department of Public Health and Epidemiology, Faculty of General Medicine, University of Debrecen, Debrecen, Hungary
| | - Dahy Sulaiman
- Health Technology Assessment Resource Centre, Department of Public Health, Kalyan Singh Super Specialty Cancer Institute, Lucknow, India
| | | | - Mazin E. Khalil
- School of Medicine, St. George's University, West Indies, Grenada
| | | | - Yasir Almuzaini
- Global Center of Mass Gatherings Medicine, Ministry of Health, Saudi Arabia
| | - Shima Hashemi
- Department of Epidemiology, Faculty of Health, Ilam University of Medical Sciences, Ilam, Iran
| | - Stany Mathew
- Health Technology Assessment Resource Centre, National Centre for Disease Informatics and Research, Bangalore, India
| | | | | |
Collapse
|
13
|
Chen R, Chen J, Yang S, Luo S, Xiao Z, Lu L, Liang B, Liu S, Shi H, Xu J. Prediction of prognosis in COVID-19 patients using machine learning: A systematic review and meta-analysis. Int J Med Inform 2023; 177:105151. [PMID: 37473658 DOI: 10.1016/j.ijmedinf.2023.105151] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2022] [Revised: 07/07/2023] [Accepted: 07/08/2023] [Indexed: 07/22/2023]
Abstract
BACKGROUND Accurate prediction of prognostic outcomes in patients with COVID-19 could facilitate clinical decision-making and medical resource allocation. However, little is known about the ability of machine learning (ML) to predict prognosis in COVID-19 patients. OBJECTIVE This study aimed to systematically examine the prognostic value of ML in patients with COVID-19. METHODS A systematic search was conducted in PubMed, Web of Science, Embase, Cochrane Library, and IEEE Xplore up to December 15, 2021. Studies predicting the prognostic outcomes of COVID-19 patients using ML were eligible for inclusion. Risk of bias was evaluated by a tailored checklist based on Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Pooled sensitivity, specificity, and area under the receiver operating curve (AUC) were calculated to evaluate model performance. RESULTS A total of 33 studies that described 35 models were eligible for inclusion, with 27 models presenting mortality, four intensive care unit (ICU) admission, and four use of ventilation. For predicting mortality, ML gave a pooled sensitivity of 0.86 (95% CI, 0.79-0.90), a specificity of 0.87 (95% CI, 0.80-0.92), and an AUC of 0.93 (95% CI, 0.90-0.95). For the prediction of ICU admission, ML had a sensitivity of 0.86 (95% CI, 0.78-0.92), a specificity of 0.81 (95% CI, 0.66-0.91), and an AUC of 0.91 (95% CI, 0.88-0.93). For the prediction of ventilation, ML had a sensitivity of 0.81 (95% CI, 0.68-0.90), a specificity of 0.78 (95% CI, 0.66-0.87), and an AUC of 0.87 (95% CI, 0.83-0.89). Meta-regression analyses indicated that algorithm, population, study design, and source of dataset influenced the pooled estimate. CONCLUSION This meta-analysis demonstrated the satisfactory performance of ML in predicting prognostic outcomes in patients with COVID-19, suggesting the potential value of ML to support clinical decision-making. However, improvements to methodology and validation are still necessary before its application in routine clinical practice.
Collapse
Affiliation(s)
- Ruiyao Chen
- Shanghai Artificial Intelligence Laboratory, Shanghai, China
| | - Jiayuan Chen
- Shanghai Artificial Intelligence Laboratory, Shanghai, China
| | - Sen Yang
- Shanghai Artificial Intelligence Laboratory, Shanghai, China
| | - Shuqing Luo
- Shanghai Artificial Intelligence Laboratory, Shanghai, China
| | - Zhongzhou Xiao
- Shanghai Artificial Intelligence Laboratory, Shanghai, China
| | - Lu Lu
- Shanghai Artificial Intelligence Laboratory, Shanghai, China
| | - Bilin Liang
- Shanghai Artificial Intelligence Laboratory, Shanghai, China
| | | | - Huwei Shi
- Shanghai Artificial Intelligence Laboratory, Shanghai, China
| | - Jie Xu
- Shanghai Artificial Intelligence Laboratory, Shanghai, China.
| |
Collapse
|
14
|
Xin Y, Li H, Zhou Y, Yang Q, Mu W, Xiao H, Zhuo Z, Liu H, Wang H, Qu X, Wang C, Liu H, Yu K. The accuracy of artificial intelligence in predicting COVID-19 patient mortality: a systematic review and meta-analysis. BMC Med Inform Decis Mak 2023; 23:155. [PMID: 37559062 PMCID: PMC10410953 DOI: 10.1186/s12911-023-02256-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2022] [Accepted: 08/02/2023] [Indexed: 08/11/2023] Open
Abstract
BACKGROUND The purpose of this paper was to systematically evaluate the application value of artificial intelligence in predicting mortality among COVID-19 patients. METHODS The PubMed, Embase, Web of Science, CNKI, Wanfang, China Biomedical Literature, and VIP databases were systematically searched from inception to October 2022 to identify studies that evaluated the predictive effects of artificial intelligence on mortality among COVID-19 patients. The retrieved literature was screened according to the inclusion and exclusion criteria. The quality of the included studies was assessed using the QUADAS-2 tools. Statistical analysis of the included studies was performed using Review Manager 5.3, Stata 16.0, and Meta-DiSc 1.4 statistical software. This meta-analysis was registered in PROSPERO (CRD42022315158). FINDINGS Of 2193 studies, 23 studies involving a total of 25 AI models met the inclusion criteria. Among them, 18 studies explicitly mentioned training and test sets, and 5 studies did not explicitly mention grouping. In the training set, the pooled sensitivity was 0.93 [0.87, 0.96], the pooled specificity was 0.94 [0.87, 0.97], and the area under the ROC curve was 0.98 [0.96, 0.99]. In the validation set, the pooled sensitivity was 0.84 [0.78, 0.88], the pooled specificity was 0.89 [0.85, 0.92], and the area under the ROC curve was 0.93 [1.00, 0.00]. In the subgroup analysis, the areas under the summary receiver operating characteristic (SROC) curves of the artificial intelligence models KNN, SVM, ANN, RF and XGBoost were 0.98, 0.98, 0.94, 0.92, and 0.91, respectively. The Deeks funnel plot indicated that there was no significant publication bias in this study (P > 0.05). INTERPRETATION Artificial intelligence models have high accuracy in predicting mortality among COVID-19 patients and have high prognostic value. Among them, the KNN, SVM, ANN, RF, XGBoost, and other models have the highest levels of accuracy.
Collapse
Affiliation(s)
- Yu Xin
- Department of Critical Care Medicine, the First Affiliated Hospital of Harbin Medical University, Harbin, 150001, Heilongjiang Province, China
- Department of Critical Care Medicine, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China
| | - Hongxu Li
- Department of Critical Care Medicine, the First Affiliated Hospital of Harbin Medical University, Harbin, 150001, Heilongjiang Province, China
- Department of Critical Care Medicine, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China
| | - Yuxin Zhou
- Department of Critical Care Medicine, the First Affiliated Hospital of Harbin Medical University, Harbin, 150001, Heilongjiang Province, China
- Department of Critical Care Medicine, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China
| | - Qing Yang
- Department of Critical Care Medicine, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China
| | - Wenjing Mu
- Department of Critical Care Medicine, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China
| | - Han Xiao
- Departments of Pharmacy and Cardiology, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China
| | - Zipeng Zhuo
- Department of Critical Care Medicine, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China
| | - Hongyu Liu
- Department of Anesthesiology, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China
| | - Hongying Wang
- Department of Critical Care Medicine, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China
| | - Xutong Qu
- Department of Anesthesiology, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China
| | - Changsong Wang
- Department of Critical Care Medicine, the First Affiliated Hospital of Harbin Medical University, Harbin, 150001, Heilongjiang Province, China.
- Department of Critical Care Medicine, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China.
| | - Haitao Liu
- Department of Critical Care Medicine, Harbin Medical University Cancer Hospital, No. 150 Haping Rd, Nangang District, Harbin, 150081, China.
| | - Kaijiang Yu
- Department of Critical Care Medicine, the First Affiliated Hospital of Harbin Medical University, Harbin, 150001, Heilongjiang Province, China.
| |
Collapse
|
15
|
Hernández-Aceituno A, Larumbe Zabala E. [Risk factors for mortality from COVID-19 Omicron variant: Retrospective analysis in elderly from the Canary Islands]. Rev Esp Geriatr Gerontol 2023; 58:101381. [PMID: 37467706 PMCID: PMC10284450 DOI: 10.1016/j.regg.2023.101381] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2023] [Revised: 05/10/2023] [Accepted: 05/29/2023] [Indexed: 07/21/2023]
Abstract
BACKGROUND AND AIMS Since the beginning of the COVID-19 pandemic, the elderly population has had the highest rates of complications and mortality. This study aimed to determine the influence of different risk factors on deaths due to the Omicron variant in the Canary Islands. MATERIALS AND METHODS A retrospective observational study of 16,998 cases of COVID-19 over 40 years of age was conducted in the Canary Islands between August 1, 2022, and January 31, 2023. We extracted sociodemographic data (age and sex) and clinical data (death, vaccination history, hospital admission, previous diseases, and treatments). RESULTS Among the deaths, there was a higher proportion of males aged over 70 years, with diabetes, cardiovascular, renal, respiratory, and systemic diseases, and nursing home residents. Significant differences were observed in the number of doses of the vaccine. The multiple regression model showed that male sex (OR [95% CI]=1.92 [1.42-2.58]), age (70-79 years, 9.11 [4.27-19.43]; 80-89 years, 21.72 [10.40-45.36]; 90-99 years, 66.24 [31.03-141.38]; 100 years or older, 69.22 [12.97-369.33]), being unvaccinated (6.96, [4.01-12.08]), or having the last dose administered at least 12 months before the diagnosis (2.38, [1.48-3.81]) were significantly associated with mortality. CONCLUSIONS Multiple factors may increase the risk of mortality due to COVID-19 in the elderly population. In our study, we found that only three predictors can effectively explain the variability: older age, male sex, and not being vaccinated or last vaccination date prior to one year.
Collapse
Affiliation(s)
- Ana Hernández-Aceituno
- Servicio de Epidemiología y Prevención, Dirección General de Salud Pública, Santa Cruz de Tenerife, España; Hospital Universitario de Canarias, Servicio Canario de Salud, Santa Cruz de Tenerife, España.
| | - Eneko Larumbe Zabala
- Servicio de Epidemiología y Prevención, Dirección General de Salud Pública, Santa Cruz de Tenerife, España; Fundación Canaria Instituto de Investigación Sanitaria de Canarias, FIISC, Santa Cruz de Tenerife, España
| |
Collapse
|
16
|
Shakibfar S, Nyberg F, Li H, Zhao J, Nordeng HME, Sandve GKF, Pavlovic M, Hajiebrahimi M, Andersen M, Sessa M. Artificial intelligence-driven prediction of COVID-19-related hospitalization and death: a systematic review. Front Public Health 2023; 11:1183725. [PMID: 37408750 PMCID: PMC10319067 DOI: 10.3389/fpubh.2023.1183725] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2023] [Accepted: 05/31/2023] [Indexed: 07/07/2023] Open
Abstract
Aim To perform a systematic review on the use of Artificial Intelligence (AI) techniques for predicting COVID-19 hospitalization and mortality using primary and secondary data sources. Study eligibility criteria Cohort, clinical trials, meta-analyses, and observational studies investigating COVID-19 hospitalization or mortality using artificial intelligence techniques were eligible. Articles without a full text available in the English language were excluded. Data sources Articles recorded in Ovid MEDLINE from 01/01/2019 to 22/08/2022 were screened. Data extraction We extracted information on data sources, AI models, and epidemiological aspects of retrieved studies. Bias assessment A bias assessment of AI models was done using PROBAST. Participants Patients tested positive for COVID-19. Results We included 39 studies related to AI-based prediction of hospitalization and death related to COVID-19. The articles were published in the period 2019-2022, and mostly used Random Forest as the model with the best performance. AI models were trained using cohorts of individuals sampled from populations of European and non-European countries, mostly with cohort sample size <5,000. Data collection generally included information on demographics, clinical records, laboratory results, and pharmacological treatments (i.e., high-dimensional datasets). In most studies, the models were internally validated with cross-validation, but the majority of studies lacked external validation and calibration. Covariates were not prioritized using ensemble approaches in most of the studies, however, models still showed moderately good performances with Area under the Receiver operating characteristic Curve (AUC) values >0.7. According to the assessment with PROBAST, all models had a high risk of bias and/or concern regarding applicability. Conclusions A broad range of AI techniques have been used to predict COVID-19 hospitalization and mortality. The studies reported good prediction performance of AI models, however, high risk of bias and/or concern regarding applicability were detected.
Collapse
Affiliation(s)
- Saeed Shakibfar
- Pharmacovigilance Research Center, Department of Drug Design and Pharmacology, University of Copenhagen, Copenhagen, Denmark
| | - Fredrik Nyberg
- School of Public Health and Community Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Huiqi Li
- School of Public Health and Community Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Jing Zhao
- Pharmacoepidemiology and Drug Safety Research Group, Department of Pharmacy, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway
- UiORealArt Convergence Environment, University of Oslo, Oslo, Norway
| | - Hedvig Marie Egeland Nordeng
- Pharmacoepidemiology and Drug Safety Research Group, Department of Pharmacy, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway
- UiORealArt Convergence Environment, University of Oslo, Oslo, Norway
| | - Geir Kjetil Ferkingstad Sandve
- UiORealArt Convergence Environment, University of Oslo, Oslo, Norway
- Department of Informatics, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway
| | - Milena Pavlovic
- UiORealArt Convergence Environment, University of Oslo, Oslo, Norway
- Department of Informatics, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway
| | | | - Morten Andersen
- Pharmacovigilance Research Center, Department of Drug Design and Pharmacology, University of Copenhagen, Copenhagen, Denmark
| | - Maurizio Sessa
- Pharmacovigilance Research Center, Department of Drug Design and Pharmacology, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|
17
|
Zhu Y, Yu B, Tang K, Liu T, Niu D, Zhang L. Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19. Front Public Health 2023; 11:1194349. [PMID: 37304114 PMCID: PMC10254410 DOI: 10.3389/fpubh.2023.1194349] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2023] [Accepted: 05/12/2023] [Indexed: 06/13/2023] Open
Abstract
Background Most existing prognostic models of COVID-19 require imaging manifestations and laboratory results as predictors, which are only available in the post-hospitalization period. Therefore, we aimed to develop and validate a prognostic model to assess the in-hospital death risk in COVID-19 patients using routinely available predictors at hospital admission. Methods We conducted a retrospective cohort study of patients with COVID-19 using the Healthcare Cost and Utilization Project State Inpatient Database in 2020. Patients hospitalized in Eastern United States (Florida, Michigan, Kentucky, and Maryland) were included in the training set, and those hospitalized in Western United States (Nevada) were included in the validation set. Discrimination, calibration, and clinical utility were evaluated to assess the model's performance. Results A total of 17 954 in-hospital deaths occurred in the training set (n = 168 137), and 1,352 in-hospital deaths occurred in the validation set (n = 12 577). The final prediction model included 15 variables readily available at hospital admission, including age, sex, and 13 comorbidities. This prediction model showed moderate discrimination with an area under the curve (AUC) of 0.726 (95% confidence interval [CI]: 0.722-0.729) and good calibration (Brier score = 0.090, slope = 1, intercept = 0) in the training set; a similar predictive ability was observed in the validation set. Conclusion An easy-to-use prognostic model based on predictors readily available at hospital admission was developed and validated for the early identification of COVID-19 patients with a high risk of in-hospital death. This model can be a clinical decision-support tool to triage patients and optimize resource allocation.
Collapse
Affiliation(s)
- Yangjie Zhu
- Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, China
| | - Boyang Yu
- Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, China
- Department of Medical Health Service, General Hospital of Northern Theater Command of PLA, Shenyang, China
| | - Kang Tang
- Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, China
| | - Tongtong Liu
- Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, China
- Department of Medical Health Service, 969th Hospital of PLA Joint Logistics Support Forces, Hohhot, China
| | - Dongjun Niu
- Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, China
| | - Lulu Zhang
- Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, China
| |
Collapse
|
18
|
Smadi M, Kaburis M, Schnapper Y, Reina G, Molero P, Molendijk ML. SARS-CoV-2 susceptibility and COVID-19 illness course and outcome in people with pre-existing neurodegenerative disorders: systematic review with frequentist and Bayesian meta-analyses. Br J Psychiatry 2023:1-14. [PMID: 37183681 DOI: 10.1192/bjp.2023.43] [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] [Indexed: 05/16/2023]
Abstract
BACKGROUND People with neurodegenerative disease and mild cognitive impairment (MCI) may have an elevated risk of acquiring severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and may be disproportionally affected by coronavirus disease 2019 (COVID-19) once infected. AIMS To review all eligible studies and quantify the strength of associations between various pre-existing neurodegenerative disorders and both SARS-CoV-2 susceptibility and COVID-19 illness course and outcome. METHOD Pre-registered systematic review with frequentist and Bayesian meta-analyses. Systematic searches were executed in PubMed, Web of Science and preprint servers. The final search date was 9 January 2023. Odds ratios (ORs) were used as measures of effect. RESULTS In total, 136 primary studies (total sample size n = 97 643 494), reporting on 268 effect-size estimates, met the inclusion criteria. The odds for a positive SARS-CoV-2 test result were increased for people with pre-existing dementia (OR = 1.83, 95% CI 1.16-2.87), Alzheimer's disease (OR = 2.86, 95% CI 1.44-5.66) and Parkinson's disease (OR = 1.65, 95% CI 1.34-2.04). People with pre-existing dementia were more likely to experience a relatively severe COVID-19 course, once infected (OR = 1.43, 95% CI 1.00-2.03). People with pre-existing dementia or Alzheimer's disease were at increased risk for COVID-19-related hospital admission (pooled OR range: 1.60-3.72). Intensive care unit admission rates were relatively low for people with dementia (OR = 0.54, 95% CI 0.40-0.74). All neurodegenerative disorders, including MCI, were at higher risk for COVID-19-related mortality (pooled OR range: 1.56-2.27). CONCLUSIONS Our findings confirm that, in general, people with neurodegenerative disease and MCI are at a disproportionally high risk of contracting COVID-19 and have a poor outcome once infected.
Collapse
Affiliation(s)
- Muhannad Smadi
- Institute of Psychology, Department of Clinical Psychology, Leiden University, Leiden, The Netherlands
| | - Melina Kaburis
- Institute of Psychology, Department of Clinical Psychology, Leiden University, Leiden, The Netherlands
| | - Youval Schnapper
- Institute of Psychology, Department of Clinical Psychology, Leiden University, Leiden, The Netherlands
| | - Gabriel Reina
- Navarra Institute for Health Research (IdiSNA), Pamplona, Spain; and Clínica Universidad de Navarra, Department of Microbiology, Pamplona, Spain
| | - Patricio Molero
- Navarra Institute for Health Research (IdiSNA), Pamplona, Spain; and Clínica Universidad de Navarra, Department of Psychiatry and Medical Psychology, Pamplona, Spain
| | - Marc L Molendijk
- Institute of Psychology, Department of Clinical Psychology, Leiden University, Leiden, The Netherlands; and Leiden Institute for Brain and Cognition, Leiden University Medical Centre, Leiden, The Netherlands
| |
Collapse
|
19
|
Banoei MM, Rafiepoor H, Zendehdel K, Seyyedsalehi MS, Nahvijou A, Allameh F, Amanpour S. Unraveling complex relationships between COVID-19 risk factors using machine learning based models for predicting mortality of hospitalized patients and identification of high-risk group: a large retrospective study. Front Med (Lausanne) 2023; 10:1170331. [PMID: 37215714 PMCID: PMC10192907 DOI: 10.3389/fmed.2023.1170331] [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: 02/20/2023] [Accepted: 04/11/2023] [Indexed: 05/24/2023] Open
Abstract
Background At the end of 2019, the coronavirus disease 2019 (COVID-19) pandemic increased the hospital burden of COVID-19 caused by the SARS-Cov-2 and became the most significant health challenge for nations worldwide. The severity and high mortality of COVID-19 have been correlated with various demographic characteristics and clinical manifestations. Prediction of mortality rate, identification of risk factors, and classification of patients played a crucial role in managing COVID-19 patients. Our purpose was to develop machine learning (ML)-based models for the prediction of mortality and severity among patients with COVID-19. Identifying the most important predictors and unraveling their relationships by classification of patients to the low-, moderate- and high-risk groups might guide prioritizing treatment decisions and a better understanding of interactions between factors. A detailed evaluation of patient data is believed to be important since COVID-19 resurgence is underway in many countries. Results The findings of this study revealed that the ML-based statistically inspired modification of the partial least square (SIMPLS) method could predict the in-hospital mortality among COVID-19 patients. The prediction model was developed using 19 predictors including clinical variables, comorbidities, and blood markers with moderate predictability (Q2 = 0.24) to separate survivors and non-survivors. Oxygen saturation level, loss of consciousness, and chronic kidney disease (CKD) were the top mortality predictors. Correlation analysis showed different correlation patterns among predictors for each non-survivor and survivor cohort separately. The main prediction model was verified using other ML-based analyses with a high area under the curve (AUC) (0.81-0.93) and specificity (0.94-0.99). The obtained data revealed that the mortality prediction model can be different for males and females with diverse predictors. Patients were classified into four clusters of mortality risk and identified the patients at the highest risk of mortality, which accentuated the most significant predictors correlating with mortality. Conclusion An ML model for predicting mortality among hospitalized COVID-19 patients was developed considering the interactions between factors that may reduce the complexity of clinical decision-making processes. The most predictive factors related to patient mortality were identified by assessing and classifying patients into different groups based on their sex and mortality risk (low-, moderate-, and high-risk groups).
Collapse
Affiliation(s)
| | - Haniyeh Rafiepoor
- Cancer Biology Research Center, Cancer Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Kazem Zendehdel
- Cancer Biology Research Center, Cancer Institute, Tehran University of Medical Sciences, Tehran, Iran
- Cancer Research Center, Cancer Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Monireh Sadat Seyyedsalehi
- Cancer Research Center, Cancer Institute, Tehran University of Medical Sciences, Tehran, Iran
- Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy
| | - Azin Nahvijou
- Cancer Research Center, Cancer Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Farshad Allameh
- Gastroenterology Ward, Imam Khomeini Hospital Complex (IKHC), Tehran University of Medical Sciences, Tehran, Iran
| | - Saeid Amanpour
- Cancer Biology Research Center, Cancer Institute, Tehran University of Medical Sciences, Tehran, Iran
| |
Collapse
|
20
|
Kırboğa KK, Küçüksille EU, Naldan ME, Işık M, Gülcü O, Aksakal E. CVD22: Explainable artificial intelligence determination of the relationship of troponin to D-Dimer, mortality, and CK-MB in COVID-19 patients. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 233:107492. [PMID: 36965300 PMCID: PMC10023204 DOI: 10.1016/j.cmpb.2023.107492] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/04/2022] [Revised: 02/06/2023] [Accepted: 03/15/2023] [Indexed: 06/18/2023]
Abstract
BACKGROUND AND PURPOSE COVID-19, which emerged in Wuhan (China), is one of the deadliest and fastest-spreading pandemics as of the end of 2019. According to the World Health Organization (WHO), there are more than 100 million infectious cases worldwide. Therefore, research models are crucial for managing the pandemic scenario. However, because the behavior of this epidemic is so complex and difficult to understand, an effective model must not only produce accurate predictive results but must also have a clear explanation that enables human experts to act proactively. For this reason, an innovative study has been planned to diagnose Troponin levels in the COVID-19 process with explainable white box algorithms to reach a clear explanation. METHODS Using the pandemic data provided by Erzurum Training and Research Hospital (decision number: 2022/13-145), an interpretable explanation of Troponin data was provided in the COVID-19 process with SHApley Additive exPlanations (SHAP) algorithms. Five machine learning (ML) algorithms were developed. Model performances were determined based on training, test accuracies, precision, F1-score, recall, and AUC (Area Under the Curve) values. Feature importance was estimated according to Shapley values by applying the SHApley Additive exPlanations (SHAP) method to the model with high accuracy. The model created with Streamlit v.3.9 was integrated into the interface with the name CVD22. RESULTS Among the five-machine learning (ML) models created with pandemic data, the best model was selected with the values of 1.0, 0.83, 0.86, 0.83, 0.80, and 0.91 in train and test accuracy, precision, F1-score, recall, and AUC values, respectively. As a result of feature selection and SHApley Additive exPlanations (SHAP) algorithms applied to the XGBoost model, it was determined that DDimer mean, mortality, CKMB (creatine kinase myocardial band), and Glucose were the features with the highest importance over the model estimation. CONCLUSIONS Recent advances in new explainable artificial intelligence (XAI) models have successfully made it possible to predict the future using large historical datasets. Therefore, throughout the ongoing pandemic, CVD22 (https://cvd22covid.streamlitapp.com/) can be used as a guide to help authorities or medical professionals make the best decisions quickly.
Collapse
Affiliation(s)
- Kevser Kübra Kırboğa
- Bilecik Seyh Edebali University, Bioengineering Department, 11230, Bilecik, Turkey; Informatics Institute, Istanbul Technical University, Maslak, Istanbul, 34469, Turkey.
| | - Ecir Uğur Küçüksille
- Süleyman Demirel University, Engineering Faculty, Department of Computer Engineering, Isparta 32260, Turkey
| | - Muhammet Emin Naldan
- Bilecik Seyh Edebali University, Faculty of Medicine, Department of Anaesthesiology and Reanimation, 11230, Bilecik, Turkey
| | - Mesut Işık
- Bilecik Seyh Edebali University, Bioengineering Department, 11230, Bilecik, Turkey
| | - Oktay Gülcü
- Health Sciences University, Erzurum City Hospital, Department of Cardiology, Erzurum, Turkey
| | - Emrah Aksakal
- Health Sciences University, Erzurum City Hospital, Department of Cardiology, Erzurum, Turkey
| |
Collapse
|
21
|
Buttia C, Llanaj E, Raeisi-Dehkordi H, Kastrati L, Amiri M, Meçani R, Taneri PE, Ochoa SAG, Raguindin PF, Wehrli F, Khatami F, Espínola OP, Rojas LZ, de Mortanges AP, Macharia-Nimietz EF, Alijla F, Minder B, Leichtle AB, Lüthi N, Ehrhard S, Que YA, Fernandes LK, Hautz W, Muka T. Prognostic models in COVID-19 infection that predict severity: a systematic review. Eur J Epidemiol 2023; 38:355-372. [PMID: 36840867 PMCID: PMC9958330 DOI: 10.1007/s10654-023-00973-x] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2022] [Accepted: 01/28/2023] [Indexed: 02/26/2023]
Abstract
Current evidence on COVID-19 prognostic models is inconsistent and clinical applicability remains controversial. We performed a systematic review to summarize and critically appraise the available studies that have developed, assessed and/or validated prognostic models of COVID-19 predicting health outcomes. We searched six bibliographic databases to identify published articles that investigated univariable and multivariable prognostic models predicting adverse outcomes in adult COVID-19 patients, including intensive care unit (ICU) admission, intubation, high-flow nasal therapy (HFNT), extracorporeal membrane oxygenation (ECMO) and mortality. We identified and assessed 314 eligible articles from more than 40 countries, with 152 of these studies presenting mortality, 66 progression to severe or critical illness, 35 mortality and ICU admission combined, 17 ICU admission only, while the remaining 44 studies reported prediction models for mechanical ventilation (MV) or a combination of multiple outcomes. The sample size of included studies varied from 11 to 7,704,171 participants, with a mean age ranging from 18 to 93 years. There were 353 prognostic models investigated, with area under the curve (AUC) ranging from 0.44 to 0.99. A great proportion of studies (61.5%, 193 out of 314) performed internal or external validation or replication. In 312 (99.4%) studies, prognostic models were reported to be at high risk of bias due to uncertainties and challenges surrounding methodological rigor, sampling, handling of missing data, failure to deal with overfitting and heterogeneous definitions of COVID-19 and severity outcomes. While several clinical prognostic models for COVID-19 have been described in the literature, they are limited in generalizability and/or applicability due to deficiencies in addressing fundamental statistical and methodological concerns. Future large, multi-centric and well-designed prognostic prospective studies are needed to clarify remaining uncertainties.
Collapse
Affiliation(s)
- Chepkoech Buttia
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
- Emergency Department, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 16C, 3010 Bern, Switzerland
- Epistudia, Bern, Switzerland
| | - Erand Llanaj
- Department of Molecular Epidemiology, German Institute of Human Nutrition Potsdam-Rehbrücke, Nuthetal, Germany
- ELKH-DE Public Health Research Group of the Hungarian Academy of Sciences, Department of Public Health and Epidemiology, Faculty of Medicine, University of Debrecen, Debrecen, Hungary
- Epistudia, Bern, Switzerland
- German Center for Diabetes Research (DZD), München-Neuherberg, Germany
| | - Hamidreza Raeisi-Dehkordi
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
- Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands
| | - Lum Kastrati
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
- Graduate School for Health Sciences, University of Bern, Bern, Switzerland
- Department of Diabetes, Endocrinology, Nutritional Medicine and Metabolism, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Mojgan Amiri
- Department of Epidemiology, Erasmus MC University Medical Center, Rotterdam, The Netherlands
| | - Renald Meçani
- Department of Pediatrics, “Mother Teresa” University Hospital Center, Tirana, University of Medicine, Tirana, Albania
- Division of Endocrinology and Diabetology, Department of Internal Medicine, Medical University of Graz, Graz, Austria
| | - Petek Eylul Taneri
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
- HRB-Trials Methodology Research Network College of Medicine, Nursing and Health Sciences University of Galway, Galway, Ireland
| | | | - Peter Francis Raguindin
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
- Swiss Paraplegic Research, Nottwil, Switzerland
- Faculty of Health Sciences, University of Lucerne, Lucerne, Switzerland
| | - Faina Wehrli
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
| | - Farnaz Khatami
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
- Graduate School for Health Sciences, University of Bern, Bern, Switzerland
- Department of Community Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - Octavio Pano Espínola
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
- Department of Preventive Medicine and Public Health, University of Navarre, Pamplona, Spain
- Navarra Institute for Health Research, IdiSNA, Pamplona, Spain
| | - Lyda Z. Rojas
- Research Group and Development of Nursing Knowledge (GIDCEN-FCV), Research Center, Cardiovascular Foundation of Colombia, Floridablanca, Santander, Colombia
| | | | | | - Fadi Alijla
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
- Graduate School for Health Sciences, University of Bern, Bern, Switzerland
| | - Beatrice Minder
- Public Health and Primary Care Library, University Library of Bern, University of Bern, Bern, Switzerland
| | - Alexander B. Leichtle
- University Institute of Clinical Chemistry, Inselspital, Bern University Hospital, and Center for Artificial Intelligence in Medicine (CAIM), University of Bern, Bern, Switzerland
| | - Nora Lüthi
- Emergency Department, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 16C, 3010 Bern, Switzerland
| | - Simone Ehrhard
- Emergency Department, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 16C, 3010 Bern, Switzerland
| | - Yok-Ai Que
- Department of Intensive Care Medicine, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Laurenz Kopp Fernandes
- Deutsches Herzzentrum Berlin (DHZB), Berlin, Germany
- Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Wolf Hautz
- Emergency Department, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 16C, 3010 Bern, Switzerland
| | - Taulant Muka
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
- Epistudia, Bern, Switzerland
| |
Collapse
|
22
|
Emami H, Rabiei R, Sohrabei S, Atashi A. Predicting the mortality of patients with Covid-19: A machine learning approach. Health Sci Rep 2023; 6:e1162. [PMID: 37008820 PMCID: PMC10061284 DOI: 10.1002/hsr2.1162] [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: 12/08/2022] [Revised: 02/20/2023] [Accepted: 03/20/2023] [Indexed: 04/04/2023] Open
Abstract
Background and Aims Infection with Covid-19 disease can lead to mortality in a short time. Early prediction of the mortality during an epidemic disease can save patients' lives through taking timely and necessary care interventions. Therefore, predicting the mortality of patients with Covid-19 using machine learning techniques can be effective in reducing mortality rate in Covid-19. The aim of this study is to compare four machine-learning algorithm for predicting mortality in Covid-19 disease. Methods The data of this study were collected from hospitalized patients with COVID-19 in five hospitals settings in Tehran (Iran). Database contained 4120 records, about 25% of which belonged to patients who died due to Covid-19. Each record contained 38 variables. Four machine-learning techniques, including random forest (RF), regression logistic (RL), gradient boosting tree (GBT), and support vector machine (SVM) were used in modeling. Results GBT model presented higher performance compared to other models (accuracy 70%, sensitivity 77%, specificity 69%, and the ROC area under the curve 0.857). RF, RL, and SVM models with the ROC area under curve 0.836, 0.818, and 0.794 were in the second and third places. Conclusion Considering the combination of multiple influential factors affecting death Covid-19 can help in early prediction and providing a better care plan. In addition, using different modeling on data can be useful for physician in providing appropriate care.
Collapse
Affiliation(s)
- Hassan Emami
- Department of Health Information Technology and Management, School of Allied Medical SciencesShahid Beheshti University of Medical SciencesTehranIran
| | - Reza Rabiei
- Department of Health Information Technology and Management, School of Allied Medical SciencesShahid Beheshti University of Medical SciencesTehranIran
| | - Solmaz Sohrabei
- Department of Health Information Technology and Management, School of Allied Medical SciencesShahid Beheshti University of Medical SciencesTehranIran
| | - Alireza Atashi
- Virtual SchoolTehran University of Medical SciencesTehranIran
| |
Collapse
|
23
|
Barough SS, Safavi-Naini SAA, Siavoshi F, Tamimi A, Ilkhani S, Akbari S, Ezzati S, Hatamabadi H, Pourhoseingholi MA. Generalizable machine learning approach for COVID-19 mortality risk prediction using on-admission clinical and laboratory features. Sci Rep 2023; 13:2399. [PMID: 36765157 PMCID: PMC9911952 DOI: 10.1038/s41598-023-28943-z] [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: 10/11/2022] [Accepted: 01/27/2023] [Indexed: 02/12/2023] Open
Abstract
We aimed to propose a mortality risk prediction model using on-admission clinical and laboratory predictors. We used a dataset of confirmed COVID-19 patients admitted to three general hospitals in Tehran. Clinical and laboratory values were gathered on admission. Six different machine learning models and two feature selection methods were used to assess the risk of in-hospital mortality. The proposed model was selected using the area under the receiver operator curve (AUC). Furthermore, a dataset from an additional hospital was used for external validation. 5320 hospitalized COVID-19 patients were enrolled in the study, with a mortality rate of 17.24% (N = 917). Among 82 features, ten laboratories and 27 clinical features were selected by LASSO. All methods showed acceptable performance (AUC > 80%), except for K-nearest neighbor. Our proposed deep neural network on features selected by LASSO showed AUC scores of 83.4% and 82.8% in internal and external validation, respectively. Furthermore, our imputer worked efficiently when two out of ten laboratory parameters were missing (AUC = 81.8%). We worked intimately with healthcare professionals to provide a tool that can solve real-world needs. Our model confirmed the potential of machine learning methods for use in clinical practice as a decision-support system.
Collapse
Affiliation(s)
- Siavash Shirzadeh Barough
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Seyed Amir Ahmad Safavi-Naini
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Fatemeh Siavoshi
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Atena Tamimi
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Saba Ilkhani
- Department of Surgery, Center for Surgery and Public Health, Brigham and Women's Hospital, Harvard Medical School and Harvard T.H Chan School of Public Health, Boston, MA, USA
| | - Setareh Akbari
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Sadaf Ezzati
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Hamidreza Hatamabadi
- Department of Emergency Medicine, School of Medicine, Safety Promotion and Injury Prevention Research Center, Imam Hossein Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Mohamad Amin Pourhoseingholi
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
| |
Collapse
|
24
|
Amiri P, Montazeri M, Ghasemian F, Asadi F, Niksaz S, Sarafzadeh F, Khajouei R. Prediction of mortality risk and duration of hospitalization of COVID-19 patients with chronic comorbidities based on machine learning algorithms. Digit Health 2023; 9:20552076231170493. [PMID: 37312960 PMCID: PMC10259141 DOI: 10.1177/20552076231170493] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Accepted: 03/31/2023] [Indexed: 06/15/2023] Open
Abstract
Background The severity of coronavirus (COVID-19) in patients with chronic comorbidities is much higher than in other patients, which can lead to their death. Machine learning (ML) algorithms as a potential solution for rapid and early clinical evaluation of the severity of the disease can help in allocating and prioritizing resources to reduce mortality. Objective The objective of this study was to predict the mortality risk and length of stay (LoS) of patients with COVID-19 and history of chronic comorbidities using ML algorithms. Methods This retrospective study was conducted by reviewing the medical records of COVID-19 patients with a history of chronic comorbidities from March 2020 to January 2021 in Afzalipour Hospital in Kerman, Iran. The outcome of patients, hospitalization was recorded as discharge or death. The filtering technique used to score the features and well-known ML algorithms were applied to predict the risk of mortality and LoS of patients. Ensemble Learning methods is also used. To evaluate the performance of the models, different measures including F1, precision, recall, and accuracy were calculated. The TRIPOD guideline assessed transparent reporting. Results This study was performed on 1291 patients, including 900 alive and 391 dead patients. Shortness of breath (53.6%), fever (30.1%), and cough (25.3%) were the three most common symptoms in patients. Diabetes mellitus(DM) (31.3%), hypertension (HTN) (27.3%), and ischemic heart disease (IHD) (14.2%) were the three most common chronic comorbidities of patients. Twenty-six important factors were extracted from each patient's record. Gradient boosting model with 84.15% accuracy was the best model for predicting mortality risk and multilayer perceptron (MLP) with rectified linear unit function (MSE = 38.96) was the best model for predicting the LoS. The most common chronic comorbidities among these patients were DM (31.3%), HTN (27.3%), and IHD (14.2%). The most important factors in predicting the risk of mortality were hyperlipidemia, diabetes, asthma, and cancer, and in predicting LoS was shortness of breath. Conclusion The results of this study showed that the use of ML algorithms can be a good tool to predict the risk of mortality and LoS of patients with COVID-19 and chronic comorbidities based on physiological conditions, symptoms, and demographic information of patients. The Gradient boosting and MLP algorithms can quickly identify patients at risk of death or long-term hospitalization and notify physicians to do appropriate interventions.
Collapse
Affiliation(s)
- Parastoo Amiri
- Student Research Committee, Kerman University of Medical Sciences, Kerman, Iran
| | - Mahdieh Montazeri
- Department of Health Information Sciences, Faculty of Management and Medical Information Sciences, Kerman University of Medical Sciences, Kerman, Iran
| | - Fahimeh Ghasemian
- Computer Engineering Department, Faculty of Engineering, Shahid Bahonar University of Kerman, Kerman, Iran
| | - Fatemeh Asadi
- Student Research Committee, School of Management and Medical Information, Kerman University of Medical Sciences, Kerman, Iran
| | - Saeed Niksaz
- Computer Engineering Department, Faculty of Engineering, Shahid Bahonar University of Kerman, Kerman, Iran
| | - Farhad Sarafzadeh
- Infectious and Internal Medicine Department, Afzalipour Hospital, Kerman University of Medical Sciences, Kerman, Iran
| | - Reza Khajouei
- Department of Health Information Sciences, Faculty of Management and Medical Information Sciences, Kerman University of Medical Sciences, Kerman, Iran
| |
Collapse
|
25
|
Deep Survival Analysis With Clinical Variables for COVID-19. IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE 2023; 11:223-231. [PMID: 36950264 PMCID: PMC10027076 DOI: 10.1109/jtehm.2023.3256966] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/30/2022] [Revised: 01/08/2023] [Accepted: 03/08/2023] [Indexed: 03/18/2023]
Abstract
OBJECTIVE Millions of people have been affected by coronavirus disease 2019 (COVID-19), which has caused millions of deaths around the world. Artificial intelligence (AI) plays an increasing role in all areas of patient care, including prognostics. This paper proposes a novel predictive model based on one dimensional convolutional neural networks (1D CNN) to use clinical variables in predicting the survival outcome of COVID-19 patients. METHODS AND PROCEDURES We have considered two scenarios for survival analysis, 1) uni-variate analysis using the Log-rank test and Kaplan-Meier estimator and 2) combining all clinical variables ([Formula: see text]=44) for predicting the short-term from long-term survival. We considered the random forest (RF) model as a baseline model, comparing to our proposed 1D CNN in predicting survival groups. RESULTS Our experiments using the univariate analysis show that nine clinical variables are significantly associated with the survival outcome with corrected p < 0.05. Our approach of 1D CNN shows a significant improvement in performance metrics compared to the RF and the state-of-the-art techniques (i.e., 1D CNN) in predicting the survival group of patients with COVID-19. CONCLUSION Our model has been tested using clinical variables, where the performance is found promising. The 1D CNN model could be a useful tool for detecting the risk of mortality and developing treatment plans in a timely manner. CLINICAL IMPACT The findings indicate that using both Heparin and Exnox for treatment is typically the most useful factor in predicting a patient's chances of survival from COVID-19. Moreover, our predictive model shows that the combination of AI and clinical data can be applied to point-of-care services through fast-learning healthcare systems.
Collapse
|
26
|
Takada R, Takazawa T, Takahashi Y, Fujizuka K, Akieda K, Saito S. Risk factors for mechanical ventilation and ECMO in COVID-19 patients admitted to the ICU: A multicenter retrospective observational study. PLoS One 2022; 17:e0277641. [PMID: 36374929 PMCID: PMC9662741 DOI: 10.1371/journal.pone.0277641] [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: 09/20/2022] [Accepted: 11/01/2022] [Indexed: 11/16/2022] Open
Abstract
BACKGROUND The primary purpose of this study was to investigate risk factors associated with the need for mechanical ventilation (MV) and extracorporeal membrane oxygenation (ECMO) in COVID-19 patients admitted to the intensive care unit (ICU). METHODS We retrospectively enrolled 66 consecutive COVID-19 patients admitted to the ICUs of three Japanese institutions from February 2020 to January 2021. We performed logistic regression analyses to identify risk factors associated with subsequent MV and ECMO requirements. Further, multivariate analyses were performed following adjustment for Acute Physiology and Chronic Health Evaluation (APACHE) II scores. RESULTS At ICU admission, the risk factors for subsequent MV identified were: higher age (Odds Ratio (OR) 1.04, 95% Confidence Interval (CI) 1.00-1.08, P = 0.03), higher values of APACHE II score (OR 1.20, 95% CI 1.08-1.33, P < 0.001), Sequential Organ Failure Assessment score (OR 1.53, 95% CI 1.18-1.97, P < 0.001), lactate dehydrogenase (LDH) (OR 1.01, 95% CI 1.00-1.02, p<0.001) and C-reactive protein (OR 1.09, 95% CI 1.00-1.19, P = 0.04), and lower values of lymphocytes (OR 1.00, 95% CI 1.00-1.00, P = 0.02) and antithrombin (OR 0.95, 95% CI 0.91-0.95, P < 0.01). Patients who subsequently required ECMO showed lower values of estimated glomerular filtration rate (OR 0.98, 95% CI 0.96-1.00, P = 0.04) and antithrombin (OR 0.94, 95% CI 0.88-1.00, P = 0.03) at ICU admission. Multivariate analysis showed that higher body mass index (OR 1.19, 95% CI 1.00-1.40, P = 0.04) and higher levels of LDH (OR 1.01, 95% CI 1.01-1.02, P < 0.01) were independent risk factors for the need for MV. Lower level of antithrombin (OR 0.94, 95% CI 0.88-1.00, P = 0.03) was a risk factor for the need for ECMO. CONCLUSION We showed that low antithrombin level at ICU admission might be a risk factor for subsequent ECMO requirements, in addition to other previously reported factors.
Collapse
Affiliation(s)
- Ryo Takada
- Intensive Care Unit, Gunma University Hospital, Maebashi, Gunma, Japan
| | - Tomonori Takazawa
- Intensive Care Unit, Gunma University Hospital, Maebashi, Gunma, Japan
- * E-mail:
| | - Yoshihiko Takahashi
- Advanced Medical Emergency Department and Critical Care Center, Japan Red Cross Maebashi Hospital, Maebashi, Gunma, Japan
| | - Kenji Fujizuka
- Advanced Medical Emergency Department and Critical Care Center, Japan Red Cross Maebashi Hospital, Maebashi, Gunma, Japan
| | - Kazuki Akieda
- Department of Emergency Medicine, Subaru Health Insurance Society Ota Memorial Hospital, Ota, Gunma, Japan
| | - Shigeru Saito
- Department of Anesthesiology, Gunma University Graduate School of Medicine, Maebashi, Gunma, Japan
| |
Collapse
|
27
|
Bradic M, Taleb S, Thomas B, Chidiac O, Robay A, Hassan N, Malek J, Ait Hssain A, Abi Khalil C. DNA methylation predicts the outcome of COVID-19 patients with acute respiratory distress syndrome. J Transl Med 2022; 20:526. [PMID: 36371196 PMCID: PMC9652914 DOI: 10.1186/s12967-022-03737-5] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2022] [Accepted: 10/30/2022] [Indexed: 11/15/2022] Open
Abstract
BACKGROUND COVID-19 infections could be complicated by acute respiratory distress syndrome (ARDS), increasing mortality risk. We sought to assess the methylome of peripheral blood mononuclear cells in COVID-19 with ARDS. METHODS We recruited 100 COVID-19 patients with ARDS under mechanical ventilation and 33 non-COVID-19 controls between April and July 2020. COVID-19 patients were followed at four time points for 60 days. DNA methylation and immune cell populations were measured at each time point. A multivariate cox proportional risk regression analysis was conducted to identify predictive signatures according to survival. RESULTS The comparison of COVID-19 to controls at inclusion revealed the presence of a 14.4% difference in promoter-associated CpGs in genes that control immune-related pathways such as interferon-gamma and interferon-alpha responses. On day 60, 24% of patients died. The inter-comparison of baseline DNA methylation to the last recorded time point in both COVID-19 groups or the intra-comparison between inclusion and the end of follow-up in every group showed that most changes occurred as the disease progressed, mainly in the AIM gene, which is associated with an intensified immune response in those who recovered. The multivariate Cox proportional risk regression analysis showed that higher methylation of the "Apoptotic execution Pathway" genes (ROC1, ZNF789, and H1F0) at inclusion increases mortality risk by over twofold. CONCLUSION We observed an epigenetic signature of immune-related genes in COVID-19 patients with ARDS. Further, Hypermethylation of the apoptotic execution pathway genes predicts the outcome. TRIAL REGISTRATION IMRPOVIE study, NCT04473131.
Collapse
Affiliation(s)
- Martina Bradic
- grid.5386.8000000041936877XDepartment of Genetic Medicine, Weill Cornell Medicine, New York, USA ,grid.51462.340000 0001 2171 9952Marie-Josee and Henry R. Kravis Center for Molecular Oncology, Memorial Sloan Kettering Cancer Center, New York, NY USA
| | - Sarah Taleb
- grid.452146.00000 0004 1789 3191Division of Genomics and Translational Biomedicine, College of Health and Life Sciences- HBKU, Doha, Qatar
| | - Binitha Thomas
- grid.416973.e0000 0004 0582 4340Epigenetics Cardiovascular Lab, Weill Cornell Medicine-Qatar, Doha, Qatar
| | - Omar Chidiac
- grid.416973.e0000 0004 0582 4340Epigenetics Cardiovascular Lab, Weill Cornell Medicine-Qatar, Doha, Qatar
| | - Amal Robay
- grid.416973.e0000 0004 0582 4340Epigenetics Cardiovascular Lab, Weill Cornell Medicine-Qatar, Doha, Qatar
| | - Nessiya Hassan
- grid.413548.f0000 0004 0571 546XNursery and midwifery research department, Hamad Medical Corporation., Doha, Qatar
| | - Joel Malek
- grid.416973.e0000 0004 0582 4340Genomics Core. Weill Cornell Medicine-Qatar., Doha, Qatar
| | - Ali Ait Hssain
- grid.413548.f0000 0004 0571 546XMedical Intensive Care Unit, Hamad Medical Corporation., Doha, Qatar
| | - Charbel Abi Khalil
- Department of Genetic Medicine, Weill Cornell Medicine, New York, USA. .,Epigenetics Cardiovascular Lab, Weill Cornell Medicine-Qatar, Doha, Qatar. .,Joan and Sanford I. Weill Department of Medicine., Weill Cornell Medicine, New York, USA.
| |
Collapse
|
28
|
Tardiveau C, Monneret G, Lukaszewicz AC, Cheynet V, Cerrato E, Imhoff K, Peronnet E, Bodinier M, Kreitmann L, Blein S, Llitjos JF, Conti F, Gossez M, Buisson M, Yonis H, Cour M, Argaud L, Delignette MC, Wallet F, Dailler F, Monard C, Brengel-Pesce K, Venet F. A 9-mRNA signature measured from whole blood by a prototype PCR panel predicts 28-day mortality upon admission of critically ill COVID-19 patients. Front Immunol 2022; 13:1022750. [DOI: 10.3389/fimmu.2022.1022750] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2022] [Accepted: 10/11/2022] [Indexed: 11/07/2022] Open
Abstract
Immune responses affiliated with COVID-19 severity have been characterized and associated with deleterious outcomes. These approaches were mainly based on research tools not usable in routine clinical practice at the bedside. We observed that a multiplex transcriptomic panel prototype termed Immune Profiling Panel (IPP) could capture the dysregulation of immune responses of ICU COVID-19 patients at admission. Nine transcripts were associated with mortality in univariate analysis and this 9-mRNA signature remained significantly associated with mortality in a multivariate analysis that included age, SOFA and Charlson scores. Using a machine learning model with these 9 mRNA, we could predict the 28-day survival status with an Area Under the Receiver Operating Curve (AUROC) of 0.764. Interestingly, adding patients’ age to the model resulted in increased performance to predict the 28-day mortality (AUROC reaching 0.839). This prototype IPP demonstrated that such a tool, upon clinical/analytical validation and clearance by regulatory agencies could be used in clinical routine settings to quickly identify patients with higher risk of death requiring thus early aggressive intensive care.
Collapse
|
29
|
Rauseo M, Perrini M, Gallo C, Mirabella L, Mariano K, Ferrara G, Santoro F, Tullo L, La Bella D, Vetuschi P, Cinnella G. Machine learning and predictive models: 2 years of Sars-CoV-2 pandemic in a single-center retrospective analysis. JOURNAL OF ANESTHESIA, ANALGESIA AND CRITICAL CARE 2022; 2:42. [PMID: 37386654 PMCID: PMC9568961 DOI: 10.1186/s44158-022-00071-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/07/2022] [Accepted: 10/03/2022] [Indexed: 01/08/2023]
Abstract
BACKGROUND Since January 2020, coronavirus disease 19 (COVID-19) has rapidly spread all over the world. An early assessment of illness severity is crucial for the stratification of patients in order to address them to the right intensity path of care. We performed an analysis on a large cohort of COVID-19 patients (n=581) hospitalized between March 2020 and May 2021 in our intensive care unit (ICU) at Policlinico Riuniti di Foggia hospital. Through an integration of the scores, demographic data, clinical history, laboratory findings, respiratory parameters, a correlation analysis, and the use of machine learning our study aimed to develop a model to predict the main outcome. METHODS We deemed eligible for analysis all adult patients (age >18 years old) admitted to our department. We excluded all the patients with an ICU length of stay inferior to 24 h and the ones that declined to participate in our data collection. We collected demographic data, medical history, D-dimers, NEWS2, and MEWS scores on ICU admission and on ED admission, PaO2/FiO2 ratio on ICU admission, and the respiratory support modalities before the orotracheal intubation and the intubation timing (early vs late with a 48-h hospital length of stay cutoff). We further collected the ICU and hospital lengths of stay expressed in days of hospitalization, hospital location (high dependency unit, HDU, ED), and length of stay before and after ICU admission; the in-hospital mortality; and the in-ICU mortality. We performed univariate, bivariate, and multivariate statistical analyses. RESULTS SARS-CoV-2 mortality was positively correlated to age, length of stay in HDU, MEWS, and NEWS2 on ICU admission, D-dimer value on ICU admission, early orotracheal intubation, and late orotracheal intubation. We found a negative correlation between the PaO2/FiO2 ratio on ICU admission and NIV. No significant correlations with sex, obesity, arterial hypertension, chronic obstructive pulmonary disease, chronic kidney disease, cardiovascular disease, diabetes mellitus, dyslipidemia, and neither MEWS nor NEWS on ED admission were observed. Considering all the pre-ICU variables, none of the machine learning algorithms performed well in developing a prediction model accurate enough to predict the outcome although a secondary multivariate analysis focused on the ventilation modalities and the main outcome confirmed how the choice of the right ventilatory support with the right timing is crucial. CONCLUSION In our cohort of COVID patients, the choice of the right ventilatory support at the right time has been crucial, severity scores, and clinical judgment gave support in identifying patients at risk of developing a severe disease, comorbidities showed a lower weight than expected considering the main outcome, and machine learning method integration could be a fundamental statistical tool in the comprehensive evaluation of such complex diseases.
Collapse
Affiliation(s)
- Michela Rauseo
- Department of Anesthesia and Intensive Care Medicine, University Hospital "Policlinico Riuniti di Foggia", University of Foggia, Viale Pinto, 1, 71122, Foggia, Italy.
| | - Marco Perrini
- Department of Anesthesia and Intensive Care Medicine, University Hospital "Policlinico Riuniti di Foggia", University of Foggia, Viale Pinto, 1, 71122, Foggia, Italy
| | - Crescenzio Gallo
- Department of Clinical and Experimental Medicine "InfoLab" Bioinformatics Facility Head, University Hospital "Policlinico Riuniti", Viale Pinto 1, 71122, Foggia, Italy
| | - Lucia Mirabella
- Department of Anesthesia and Intensive Care Medicine, University Hospital "Policlinico Riuniti di Foggia", University of Foggia, Viale Pinto, 1, 71122, Foggia, Italy
| | - Karim Mariano
- Department of Anesthesia and Intensive Care Medicine, University Hospital "Policlinico Riuniti di Foggia", University of Foggia, Viale Pinto, 1, 71122, Foggia, Italy
| | - Giuseppe Ferrara
- Department of Anesthesia and Intensive Care Medicine, University Hospital "Policlinico Riuniti di Foggia", University of Foggia, Viale Pinto, 1, 71122, Foggia, Italy
| | - Filomena Santoro
- Department of Anesthesia and Intensive Care Medicine, University Hospital "Policlinico Riuniti di Foggia", University of Foggia, Viale Pinto, 1, 71122, Foggia, Italy
| | - Livio Tullo
- Department of Anesthesia and Intensive Care Medicine, University Hospital "Policlinico Riuniti di Foggia", University of Foggia, Viale Pinto, 1, 71122, Foggia, Italy
| | - Daniela La Bella
- Department of Anesthesia and Intensive Care Medicine, University Hospital "Policlinico Riuniti di Foggia", University of Foggia, Viale Pinto, 1, 71122, Foggia, Italy
| | - Paolo Vetuschi
- Department of Anesthesia and Intensive Care Medicine, University Hospital "Policlinico Riuniti di Foggia", University of Foggia, Viale Pinto, 1, 71122, Foggia, Italy
| | - Gilda Cinnella
- Department of Anesthesia and Intensive Care Medicine, University Hospital "Policlinico Riuniti di Foggia", University of Foggia, Viale Pinto, 1, 71122, Foggia, Italy
| |
Collapse
|
30
|
Kistenev YV, Vrazhnov DA, Shnaider EE, Zuhayri H. Predictive models for COVID-19 detection using routine blood tests and machine learning. Heliyon 2022; 8:e11185. [PMID: 36311357 PMCID: PMC9595489 DOI: 10.1016/j.heliyon.2022.e11185] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2022] [Revised: 03/25/2022] [Accepted: 10/16/2022] [Indexed: 11/06/2022] Open
Abstract
The problem of accurate, fast, and inexpensive COVID-19 tests has been urgent till now. Standard COVID-19 tests need high-cost reagents and specialized laboratories with high safety requirements, are time-consuming. Data of routine blood tests as a base of SARS-CoV-2 invasion detection allows using the most practical medicine facilities. But blood tests give general information about a patient's state, which is not directly associated with COVID-19. COVID-19-specific features should be selected from the list of standard blood characteristics, and decision-making software based on appropriate clinical data should be created. This review describes the abilities to develop predictive models for COVID-19 detection using routine blood tests and machine learning.
Collapse
Affiliation(s)
- Yury V. Kistenev
- Laboratory of Laser Molecular Imaging and Machine Learning, Tomsk State University, 36 Lenin Av., 634050 Tomsk, Russia
| | - Denis A. Vrazhnov
- Laboratory of Laser Molecular Imaging and Machine Learning, Tomsk State University, 36 Lenin Av., 634050 Tomsk, Russia
| | - Ekaterina E. Shnaider
- Laboratory of Laser Molecular Imaging and Machine Learning, Tomsk State University, 36 Lenin Av., 634050 Tomsk, Russia
| | - Hala Zuhayri
- Laboratory of Laser Molecular Imaging and Machine Learning, Tomsk State University, 36 Lenin Av., 634050 Tomsk, Russia
| |
Collapse
|
31
|
Winston L, McCann M, Onofrei G. Exploring Socioeconomic Status as a Global Determinant of COVID-19 Prevalence, Using Exploratory Data Analytic and Supervised Machine Learning Techniques: Algorithm Development and Validation Study. JMIR Form Res 2022; 6:e35114. [PMID: 36001798 PMCID: PMC9518652 DOI: 10.2196/35114] [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: 11/22/2021] [Revised: 04/12/2022] [Accepted: 04/27/2022] [Indexed: 11/21/2022] Open
Abstract
BACKGROUND The COVID-19 pandemic represents the most unprecedented global challenge in recent times. As the global community attempts to manage the pandemic in the long term, it is pivotal to understand what factors drive prevalence rates and to predict the future trajectory of the virus. OBJECTIVE This study had 2 objectives. First, it tested the statistical relationship between socioeconomic status and COVID-19 prevalence. Second, it used machine learning techniques to predict cumulative COVID-19 cases in a multicountry sample of 182 countries. Taken together, these objectives will shed light on socioeconomic status as a global risk factor of the COVID-19 pandemic. METHODS This research used exploratory data analysis and supervised machine learning methods. Exploratory analysis included variable distribution, variable correlations, and outlier detection. Following this, the following 3 supervised regression techniques were applied: linear regression, random forest, and adaptive boosting (AdaBoost). Results were evaluated using k-fold cross-validation and subsequently compared to analyze algorithmic suitability. The analysis involved 2 models. First, the algorithms were trained to predict 2021 COVID-19 prevalence using only 2020 reported case data. Following this, socioeconomic indicators were added as features and the algorithms were trained again. The Human Development Index (HDI) metrics of life expectancy, mean years of schooling, expected years of schooling, and gross national income were used to approximate socioeconomic status. RESULTS All variables correlated positively with the 2021 COVID-19 prevalence, with R2 values ranging from 0.55 to 0.85. Using socioeconomic indicators, COVID-19 prevalence was predicted with a reasonable degree of accuracy. Using 2020 reported case rates as a lone predictor to predict 2021 prevalence rates, the average predictive accuracy of the algorithms was low (R2=0.543). When socioeconomic indicators were added alongside 2020 prevalence rates as features, the average predictive performance improved considerably (R2=0.721) and all error statistics decreased. Thus, adding socioeconomic indicators alongside 2020 reported case data optimized the prediction of COVID-19 prevalence to a considerable degree. Linear regression was the strongest learner with R2=0.693 on the first model and R2=0.763 on the second model, followed by random forest (0.481 and 0.722) and AdaBoost (0.454 and 0.679). Following this, the second model was retrained using a selection of additional COVID-19 risk factors (population density, median age, and vaccination uptake) instead of the HDI metrics. However, average accuracy dropped to 0.649, which highlights the value of socioeconomic status as a predictor of COVID-19 cases in the chosen sample. CONCLUSIONS The results show that socioeconomic status is an important variable to consider in future epidemiological modeling, and highlights the reality of the COVID-19 pandemic as a social phenomenon and a health care phenomenon. This paper also puts forward new considerations about the application of statistical and machine learning techniques to understand and combat the COVID-19 pandemic.
Collapse
Affiliation(s)
- Luke Winston
- Department of Computing, Atlantic Technological University, Letterkenny, Ireland
| | - Michael McCann
- Department of Computing, Atlantic Technological University, Letterkenny, Ireland
| | - George Onofrei
- Department of Business, Atlantic Technological University, Letterkenny, Ireland
| |
Collapse
|
32
|
Saberi-Movahed F, Mohammadifard M, Mehrpooya A, Rezaei-Ravari M, Berahmand K, Rostami M, Karami S, Najafzadeh M, Hajinezhad D, Jamshidi M, Abedi F, Mohammadifard M, Farbod E, Safavi F, Dorvash M, Mottaghi-Dastjerdi N, Vahedi S, Eftekhari M, Saberi-Movahed F, Alinejad-Rokny H, Band SS, Tavassoly I. Decoding clinical biomarker space of COVID-19: Exploring matrix factorization-based feature selection methods. Comput Biol Med 2022; 146:105426. [PMID: 35569336 PMCID: PMC8979841 DOI: 10.1016/j.compbiomed.2022.105426] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2021] [Revised: 03/01/2022] [Accepted: 03/18/2022] [Indexed: 02/06/2023]
Abstract
One of the most critical challenges in managing complex diseases like COVID-19 is to establish an intelligent triage system that can optimize the clinical decision-making at the time of a global pandemic. The clinical presentation and patients' characteristics are usually utilized to identify those patients who need more critical care. However, the clinical evidence shows an unmet need to determine more accurate and optimal clinical biomarkers to triage patients under a condition like the COVID-19 crisis. Here we have presented a machine learning approach to find a group of clinical indicators from the blood tests of a set of COVID-19 patients that are predictive of poor prognosis and morbidity. Our approach consists of two interconnected schemes: Feature Selection and Prognosis Classification. The former is based on different Matrix Factorization (MF)-based methods, and the latter is performed using Random Forest algorithm. Our model reveals that Arterial Blood Gas (ABG) O2 Saturation and C-Reactive Protein (CRP) are the most important clinical biomarkers determining the poor prognosis in these patients. Our approach paves the path of building quantitative and optimized clinical management systems for COVID-19 and similar diseases.
Collapse
Affiliation(s)
| | | | - Adel Mehrpooya
- School of Mathematical Sciences, Science and Engineering Faculty, Queensland University of Technology (QUT), Brisbane, Australia
| | | | - Kamal Berahmand
- School of Computer Science, Faculty of Science, Queensland University of Technology (QUT), Brisbane, Australia
| | - Mehrdad Rostami
- Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Oulu, Finland
| | - Saeed Karami
- Department of Mathematics, Institute for Advanced Studies in Basic Sciences (IASBS), Zanjan, 45137-66731, Iran
| | - Mohammad Najafzadeh
- Department of Applied Mathematics, Faculty of Sciences and Modern Technologies, Graduate University of Advanced Technology, Kerman, Iran
| | | | - Mina Jamshidi
- Department of Applied Mathematics, Faculty of Sciences and Modern Technologies, Graduate University of Advanced Technology, Kerman, Iran
| | - Farshid Abedi
- Infectious Diseases Research Center, Birjand University of Medical Sciences, Birjand, Iran
| | | | - Elnaz Farbod
- Baruch College, City University of New York, New York, USA
| | - Farinaz Safavi
- Neuroimmunology and Neurovirology Branch, National Institute of Neurological Disorders and Stroke, National Institute of Health, Bethesda, MD, USA
| | - Mohammadreza Dorvash
- Biomedicine Discovery Institute and Department of Biochemistry and Molecular Biology, Monash University, Viewbank, VIC, Australia
| | - Negar Mottaghi-Dastjerdi
- Department of Pharmacognosy and Pharmaceutical Biotechnology, School of Pharmacy, Iran University of Medical Sciences, Tehran, Iran
| | | | - Mahdi Eftekhari
- Department of Computer Engineering, Shahid Bahonar University of Kerman, Kerman, Iran
| | - Farid Saberi-Movahed
- Department of Applied Mathematics, Faculty of Sciences and Modern Technologies, Graduate University of Advanced Technology, Kerman, Iran,Corresponding author
| | - Hamid Alinejad-Rokny
- BioMedical Machine Learning Lab, The Graduate School of Biomedical Engineering, UNSW Sydney, Sydney, NSW, 2052, Australia
| | - Shahab S. Band
- Future Technology Research Center, College of Future, National Yunlin University of Science and Technology, 123 University Road, Section 3, Douliou, Yunlin, 64002, Taiwan
| | - Iman Tavassoly
- Department of Pharmacological Sciences, Icahn School of Medicine at Mount Sinai, New York, NY10029, USA,Corresponding author
| |
Collapse
|
33
|
Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage. Sci Rep 2022; 12:10537. [PMID: 35732641 PMCID: PMC9218081 DOI: 10.1038/s41598-022-14422-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2022] [Accepted: 06/07/2022] [Indexed: 12/05/2022] Open
Abstract
Providing timely intervention to critically ill patients is a challenging task in emergency departments (ED). Our study aimed to predict early critical interventions (CrIs), which can be used as clinical recommendations. This retrospective observational study was conducted in the ED of a tertiary hospital located in a Korean metropolitan city. Patient who visited ED from January 1, 2016, to December 31, 2018, were included. Need of six CrIs were selected as prediction outcomes, namely, arterial line (A-line) insertion, oxygen therapy, high-flow nasal cannula (HFNC), intubation, Massive Transfusion Protocol (MTP), and inotropes and vasopressor. Extreme gradient boosting (XGBoost) prediction model was built by using only data available at the initial stage of ED. Overall, 137,883 patients were included in the study. The areas under the receiver operating characteristic curve for the prediction of A-line insertion was 0·913, oxygen therapy was 0.909, HFNC was 0.962, intubation was 0.945, MTP was 0.920, and inotropes or vasopressor administration was 0.899 in the XGBoost method. In addition, an increase in the need for CrIs was associated with worse ED outcomes. The CrIs model was integrated into the study site's electronic medical record and could be used to suggest early interventions for emergency physicians.
Collapse
|
34
|
Fu Y, Zhong W, Liu T, Li J, Xiao K, Ma X, Xie L, Jiang J, Zhou H, Liu R, Zhang W. Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning Techniques. Front Public Health 2022; 10:880999. [PMID: 35677769 PMCID: PMC9168534 DOI: 10.3389/fpubh.2022.880999] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2022] [Accepted: 04/13/2022] [Indexed: 01/08/2023] Open
Abstract
Motivation Patients with novel coronavirus disease 2019 (COVID-19) worsen into critical illness suddenly is a matter of great concern. Early identification and effective triaging of patients with a high risk of developing critical illness COVID-19 upon admission can aid in improving patient care, increasing the cure rate, and mitigating the burden on the medical care system. This study proposed and extended classical least absolute shrinkage and selection operator (LASSO) logistic regression to objectively identify clinical determination and risk factors for the early identification of patients at high risk of progression to critical illness at the time of hospital admission. Methods In this retrospective multicenter study, data of 1,929 patients with COVID-19 were assessed. The association between laboratory characteristics measured at admission and critical illness was screened with logistic regression. LASSO logistic regression was utilized to construct predictive models for estimating the risk that a patient with COVID-19 will develop a critical illness. Results The development cohort consisted of 1,363 patients with COVID-19 with 133 (9.7%) patients developing the critical illness. Univariate logistic regression analysis revealed 28 variables were prognosis factors for critical illness COVID-19 (p < 0.05). Elevated CK-MB, neutrophils, PCT, α-HBDH, D-dimer, LDH, glucose, PT, APTT, RDW (SD and CV), fibrinogen, and AST were predictors for the early identification of patients at high risk of progression to critical illness. Lymphopenia, a low rate of basophils, eosinophils, thrombopenia, red blood cell, hematocrit, hemoglobin concentration, blood platelet count, and decreased levels of K, Na, albumin, albumin to globulin ratio, and uric acid were clinical determinations associated with the development of critical illness at the time of hospital admission. The risk score accurately predicted critical illness in the development cohort [area under the curve (AUC) = 0.83, 95% CI: 0.78-0.86], also in the external validation cohort (n = 566, AUC = 0.84). Conclusion A risk prediction model based on laboratory findings of patients with COVID-19 was developed for the early identification of patients at high risk of progression to critical illness. This cohort study identified 28 indicators associated with critical illness of patients with COVID-19. The risk model might contribute to the treatment of critical illness disease as early as possible and allow for optimized use of medical resources.
Collapse
Affiliation(s)
- Yacheng Fu
- Department of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Changsha, China
| | - Weijun Zhong
- Department of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Changsha, China
| | - Tao Liu
- Shenzhen Center for Chronic Disease Control, Shenzhen, China
| | - Jianmin Li
- Department of Pulmonary and Critical Care Medicine, Hunan Provincial People's Hospital, The First Affiliated Hospital of Hunan Normal University, Changsha, China
| | - Kui Xiao
- Department of Pulmonary and Critical Care Medicine, The Second Xiangya Hospital, Central South University, Changsha, China
| | - Xinhua Ma
- Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Lihua Xie
- B7 Department, Zhongfa District of Tongji Hospital, Tongji Medical, Huazhong University of Science and Technology, Wuhan, China
| | - Junyi Jiang
- Department of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Changsha, China
| | - Honghao Zhou
- Department of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Changsha, China
| | - Rong Liu
- Department of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Changsha, China
| | - Wei Zhang
- Department of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Changsha, China
| |
Collapse
|
35
|
Scarpa R, Dell'Edera A, Felice C, Buso R, Muscianisi F, Finco Gambier R, Toffolo S, Grossi U, Giobbia M, Barberio G, Landini N, Facchini C, Agostini C, Rattazzi M, Cinetto F. Impact of Hypogammaglobulinemia on the Course of COVID-19 in a Non-Intensive Care Setting: A Single-Center Retrospective Cohort Study. Front Immunol 2022; 13:842643. [PMID: 35359947 PMCID: PMC8960988 DOI: 10.3389/fimmu.2022.842643] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2021] [Accepted: 02/01/2022] [Indexed: 12/11/2022] Open
Abstract
Background Severity and mortality of COVID-19 largely depends on the ability of the immune system to clear the virus. Among various comorbidities potentially impacting on this process, the weight and the consequences of an antibody deficiency have not yet been clarified. Methods We used serum protein electrophoresis to screen for hypogammaglobulinemia in a cohort of consecutive adult patients with COVID-19 pneumonia, hospitalized in non-intensive care setting between December 2020 and January 2021. The disease severity, measured by a validated score and by the need for semi intensive (sICU) or intensive care unit (ICU) admission, and the 30-day mortality was compared between patients presenting hypogammaglobulinemia (HYPO) and without hypogammaglobulinemia (no-HYPO). Demographics, comorbidities, COVID-19 specific treatment during the hospital stay, disease duration, complications and laboratory parameters were also evaluated in both groups. Results We enrolled 374 patients, of which 39 represented the HYPO cohort (10.4%). In 10/39 the condition was previously neglected, while in the other 29/39 hematologic malignancies were common (61.5%); 2/39 were on regular immunoglobulin replacement therapy (IgRT). Patients belonging to the HYPO group more frequently developed a severe COVID-19 and more often required sICU/ICU admission than no-HYPO patients. IgRT were administered in 8/39 during hospitalization; none of them died or needed sICU/ICU. Among HYPO cohort, we observed a significantly higher prevalence of neoplastic affections, of active oncologic treatment and bronchiectasis, together with higher prevalence of viral and bacterial superinfections, mechanical ventilation, convalescent plasma and SARS-CoV-2 monoclonal antibodies administration during hospital stay, and longer disease duration. Multivariate logistic regression analysis and Cox proportional hazard regression confirmed the impact of hypogammaglobulinemia on the COVID-19 severity and the probability of sICU/ICU admission. The analysis of the mortality rate in the whole cohort showed no significant difference between HYPO and no-HYPO. Conclusions Hypogammaglobulinemia, regardless of its cause, in COVID-19 patients hospitalized in a non-intensive care setting was associated to a more severe disease course and more frequent admission to s-ICU/ICU, particularly in absence of IgRT. Our findings emphasize the add-value of routine serum protein electrophoresis evaluation in patients admitted with COVID-19 to support clinicians in patient care and to consider IgRT initiation during hospitalization.
Collapse
Affiliation(s)
- Riccardo Scarpa
- Internal Medicine I, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy.,Department of Medicine, University of Padova, Padua, Italy
| | - Alessandro Dell'Edera
- Internal Medicine I, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy.,Department of Medicine, University of Padova, Padua, Italy
| | - Carla Felice
- Internal Medicine I, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy.,Department of Medicine, University of Padova, Padua, Italy
| | - Roberta Buso
- Internal Medicine I, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy
| | - Francesco Muscianisi
- Internal Medicine I, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy.,Department of Medicine, University of Padova, Padua, Italy
| | - Renato Finco Gambier
- Internal Medicine I, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy.,Department of Medicine, University of Padova, Padua, Italy
| | - Sara Toffolo
- Internal Medicine I, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy.,Department of Medicine, University of Padova, Padua, Italy
| | - Ugo Grossi
- Department of Surgery, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy
| | - Mario Giobbia
- Infectious Diseases Unit, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy
| | - Giuseppina Barberio
- Laboratory Medicine, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy
| | - Nicholas Landini
- Radiology Unit, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy
| | - Cesarina Facchini
- Internal Medicine I, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy
| | - Carlo Agostini
- Internal Medicine I, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy.,Department of Medicine, University of Padova, Padua, Italy
| | - Marcello Rattazzi
- Internal Medicine I, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy.,Department of Medicine, University of Padova, Padua, Italy
| | - Francesco Cinetto
- Internal Medicine I, Ca' Foncello Hospital, Azienda Unità Locale Socio Sanitaria n. 2 (AULSS2) Marca Trevigiana, Treviso, Italy.,Department of Medicine, University of Padova, Padua, Italy
| |
Collapse
|
36
|
Jacob SG, Ali Sulaiman MMB, Bennet B. Deep Reinforcement Learning Framework for Covid Therapy: A Research Perspective. Curr Bioinform 2022. [DOI: 10.2174/1574893617666220329182633] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
|
37
|
Abstract
This article is one of ten reviews selected from the Annual Update in Intensive Care and Emergency Medicine 2022. Other selected articles can be found online at https://www.biomedcentral.com/collections/annualupdate2022 . Further information about the Annual Update in Intensive Care and Emergency Medicine is available from https://link.springer.com/bookseries/8901 .
Collapse
Affiliation(s)
- Joo Heung Yoon
- Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, University of Pittsburgh, Pittsburgh, PA, USA.
| | - Michael R Pinsky
- Department of Critical Care Medicine, University of Pittsburgh, Pittsburgh, PA, USA
| | - Gilles Clermont
- Department of Critical Care Medicine, University of Pittsburgh, Pittsburgh, PA, USA
| |
Collapse
|
38
|
Laza R, Dragomir C, Musta VF, Lazureanu VE, Nicolescu ND, Marinescu AR, Paczeyka R, Porosnicu TM, Bica-Porfir V, Laitin SMD, Dragomir I, Ilie C, Baditoiu LM. Analysis of Deaths and Favorable Developments of Patients with SARS-CoV-2 Hospitalized in the Largest Hospital for Infectious Diseases and Pneumo-Phthisiology in the West of the Country. Int J Gen Med 2022; 15:3417-3431. [PMID: 35378919 PMCID: PMC8976499 DOI: 10.2147/ijgm.s359483] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2022] [Accepted: 03/16/2022] [Indexed: 12/11/2022] Open
Abstract
Purpose Romania is one of the European countries that has been hit the hardest by the severe acute respiratory syndrome caused by the new coronavirus SARS-CoV-2, with over 1.91 million reported cases and over 59,257 deaths. The aim of this study was to identify the main predictors of death in hospitalized patients. Patients and Methods In the period from 1 March 2020 to 30 June 2021, an observational, retrospective, randomized, case-control study was conducted, which included a sample of 139 patients who died in hospital and another sample of 275 patients who had been discharged in an improved or healed condition. Confirmation of COVID-19 cases was performed by RT-PCR from nasopharyngeal and oropharyngeal exudates. Statistical data were analyzed by logistic regression, Cox regression and a comparison of survival curves by the log-rank (Mantel-Cox) test. Results The most powerful logistic regression model identified the following independent predictors of death: history of coagulopathy HR = 30.73 [1.94–487.09], p = 0.015; high percentage of neutrophils HR = 1.09 [1.01–1.19], p = 0.027; and decreased blood-oxygenation HR = 53881.97 [1762.24–1647489.44], p < 0.001. Cox regression identified the following factors that influenced the evolution of cases: history of coagulopathy HR = 2.44 [1.38–4.35], p = 0.000; O2 saturation HR = 0.98 [0.96–0.99], p = 0.043; serum creatinine HR = 1.23 [1.08–1.39], p = 0.001; dyspnea on admission HR = 2.99 [1.42–6.30], p = 0.004; hospitalization directly in the ICU HR = 3.803 [1.97–7.33], p < 0.001; heart damage HR = 16.76 [1.49–188.56], p = 0.022; and decreased blood-oxygenation HR = 35.12 [5.92–208.19], p < 0.001. Conclusion Knowledge of the predictors of death in hospitalized patients allows for the future optimization of triage and therapeutic case management for COVID-19.
Collapse
Affiliation(s)
- Ruxandra Laza
- Department XIII, Discipline of Infectious Diseases, University of Medicine and Pharmacy “Victor Babes”, Timisoara, Romania
- Clinical Hospital of Infectious Diseases and Pneumophtisiology “Doctor Victor Babes”, Timisoara, 300310, Romania
| | - Cristina Dragomir
- Doctoral School, University of Medicine and Pharmacy “Victor Babes”, Timisoara, 300041, Romania
| | - Virgil Filaret Musta
- Department XIII, Discipline of Infectious Diseases, University of Medicine and Pharmacy “Victor Babes”, Timisoara, Romania
- Clinical Hospital of Infectious Diseases and Pneumophtisiology “Doctor Victor Babes”, Timisoara, 300310, Romania
| | - Voichita Elena Lazureanu
- Department XIII, Discipline of Infectious Diseases, University of Medicine and Pharmacy “Victor Babes”, Timisoara, Romania
- Clinical Hospital of Infectious Diseases and Pneumophtisiology “Doctor Victor Babes”, Timisoara, 300310, Romania
| | - Narcisa Daniela Nicolescu
- Department XIII, Discipline of Infectious Diseases, University of Medicine and Pharmacy “Victor Babes”, Timisoara, Romania
- Clinical Hospital of Infectious Diseases and Pneumophtisiology “Doctor Victor Babes”, Timisoara, 300310, Romania
| | - Adelina Raluca Marinescu
- Department XIII, Discipline of Infectious Diseases, University of Medicine and Pharmacy “Victor Babes”, Timisoara, Romania
- Clinical Hospital of Infectious Diseases and Pneumophtisiology “Doctor Victor Babes”, Timisoara, 300310, Romania
- Doctoral School, University of Medicine and Pharmacy “Victor Babes”, Timisoara, 300041, Romania
| | - Roxana Paczeyka
- Clinical Hospital of Infectious Diseases and Pneumophtisiology “Doctor Victor Babes”, Timisoara, 300310, Romania
| | - Tamara Mirela Porosnicu
- Clinical Hospital of Infectious Diseases and Pneumophtisiology “Doctor Victor Babes”, Timisoara, 300310, Romania
- Doctoral School, University of Medicine and Pharmacy “Victor Babes”, Timisoara, 300041, Romania
| | - Valerica Bica-Porfir
- Clinical Hospital of Infectious Diseases and Pneumophtisiology “Doctor Victor Babes”, Timisoara, 300310, Romania
| | - Sorina Maria Denisa Laitin
- Clinical Hospital of Infectious Diseases and Pneumophtisiology “Doctor Victor Babes”, Timisoara, 300310, Romania
- Department XIII, Discipline of Epidemiology, University of Medicine and Pharmacy “Victor Babes”, Timisoara, 300041, Romania
| | - Ion Dragomir
- Individual Family Medical Office, Ostroveni, Dolj, Romania
| | - Constantin Ilie
- Department XII, Discipline of Neonatology and Childcare, University of Medicine and Pharmacy “Victor Babes”, Timisoara, Romania
| | - Luminita Mirela Baditoiu
- Department XIII, Discipline of Epidemiology, University of Medicine and Pharmacy “Victor Babes”, Timisoara, 300041, Romania
- Multidisciplinary Research Centre on Antimicrobial Resistance, University of Medicine and Pharmacy “Victor Babes”, Timisoara, Romania
- Correspondence: Luminita Mirela Baditoiu, Cristina Dragomir Department XIII, Discipline of Epidemiology, Victor Babes University of Medicine and Pharmacy; Doctoral School, University of Medicine and Pharmacy, Eftimie Murgu Square, No. 2, Timisoara, 300041, Romania, Tel +40727746440; +40753036306, Email ;
| |
Collapse
|
39
|
Chiu HYR, Hwang CK, Chen SY, Shih FY, Han HC, King CC, Gilbert JR, Fang CC, Oyang YJ. Machine learning for emerging infectious disease field responses. Sci Rep 2022; 12:328. [PMID: 35013370 PMCID: PMC8748708 DOI: 10.1038/s41598-021-03687-w] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2021] [Accepted: 12/07/2021] [Indexed: 11/08/2022] Open
Abstract
Emerging infectious diseases (EIDs), including the latest COVID-19 pandemic, have emerged and raised global public health crises in recent decades. Without existing protective immunity, an EID may spread rapidly and cause mass casualties in a very short time. Therefore, it is imperative to identify cases with risk of disease progression for the optimized allocation of medical resources in case medical facilities are overwhelmed with a flood of patients. This study has aimed to cope with this challenge from the aspect of preventive medicine by exploiting machine learning technologies. The study has been based on 83,227 hospital admissions with influenza-like illness and we analysed the risk effects of 19 comorbidities along with age and gender for severe illness or mortality risk. The experimental results revealed that the decision rules derived from the machine learning based prediction models can provide valuable guidelines for the healthcare policy makers to develop an effective vaccination strategy. Furthermore, in case the healthcare facilities are overwhelmed by patients with EID, which frequently occurred in the recent COVID-19 pandemic, the frontline physicians can incorporate the proposed prediction models to triage patients suffering minor symptoms without laboratory tests, which may become scarce during an EID disaster. In conclusion, our study has demonstrated an effective approach to exploit machine learning technologies to cope with the challenges faced during the outbreak of an EID.
Collapse
Affiliation(s)
- Han-Yi Robert Chiu
- Department of Emergency Medicine, National Taiwan University Hospital and College of Medicine, National Taiwan University, No. 7 Chung Shan S. Road, Taipei, 100, Taiwan, ROC
| | - Chun-Kai Hwang
- Department of Computer Science and Information Engineering, National Taiwan University, Taipei, 106, Taiwan, ROC
| | - Shey-Ying Chen
- Department of Emergency Medicine, National Taiwan University Hospital and College of Medicine, National Taiwan University, No. 7 Chung Shan S. Road, Taipei, 100, Taiwan, ROC
| | - Fuh-Yuan Shih
- Department of Emergency Medicine, National Taiwan University Hospital and College of Medicine, National Taiwan University, No. 7 Chung Shan S. Road, Taipei, 100, Taiwan, ROC
- National Taiwan University Cancer Center, National Taiwan University, Taipei, 106, Taiwan, ROC
| | - Hsieh-Cheng Han
- Research Center for Applied Sciences, Academia Sinica, Taipei, 115, Taiwan, ROC
| | - Chwan-Chuen King
- Institute of Epidemiology and Preventive Medicine, College of Public Health, National Taiwan University, Taipei, 100, Taiwan, ROC
| | - John Reuben Gilbert
- Department of Computer Science and Information Engineering, National Taiwan University, Taipei, 106, Taiwan, ROC
| | - Cheng-Chung Fang
- Department of Emergency Medicine, National Taiwan University Hospital and College of Medicine, National Taiwan University, No. 7 Chung Shan S. Road, Taipei, 100, Taiwan, ROC.
| | - Yen-Jen Oyang
- Department of Computer Science and Information Engineering, National Taiwan University, Taipei, 106, Taiwan, ROC.
- Institute of Biomedical Electronics and Bioinformatics, College of Electrical Engineering and Computer Science, National Taiwan University, No. 1, Sec. 4, Roosevelt Road, Taipei, 106, Taiwan, ROC.
| |
Collapse
|
40
|
Laatifi M, Douzi S, Bouklouz A, Ezzine H, Jaafari J, Zaid Y, El Ouahidi B, Naciri M. Machine learning approaches in Covid-19 severity risk prediction in Morocco. JOURNAL OF BIG DATA 2022; 9:5. [PMID: 35013702 PMCID: PMC8733912 DOI: 10.1186/s40537-021-00557-0] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/26/2021] [Accepted: 12/22/2021] [Indexed: 05/04/2023]
Abstract
The purpose of this study is to develop and test machine learning-based models for COVID-19 severity prediction. COVID-19 test samples from 337 COVID-19 positive patients at Cheikh Zaid Hospital were grouped according to the severity of their illness. Ours is the first study to estimate illness severity by combining biological and non-biological data from patients with COVID-19. Moreover the use of ML for therapeutic purposes in Morocco is currently restricted, and ours is the first study to investigate the severity of COVID-19. When data analysis approaches were used to uncover patterns and essential characteristics in the data, C-reactive protein, platelets, and D-dimers were determined to be the most associated to COVID-19 severity prediction. In this research, many data reduction algorithms were used, and Machine Learning models were trained to predict the severity of sickness using patient data. A new feature engineering method based on topological data analysis called Uniform Manifold Approximation and Projection (UMAP) shown that it achieves better results. It has 100% accuracy, specificity, sensitivity, and ROC curve in conducting a prognostic prediction using different machine learning classifiers such as X_GBoost, AdaBoost, Random Forest, and ExtraTrees. The proposed approach aims to assist hospitals and medical facilities in determining who should be seen first and who has a higher priority for admission to the hospital.
Collapse
Affiliation(s)
- Mariam Laatifi
- Department of Biology, Faculty of Sciences, Mohammed V University, Rabat, Morocco
| | | | - Abdelaziz Bouklouz
- Laboratory of Pharmacology and Toxicology, Faculty of Medicine and Pharmacy, Rabat, Morocco
| | - Hind Ezzine
- Department of Biology, Faculty of Sciences, Mohammed V University, Rabat, Morocco
| | | | - Younes Zaid
- Department of Biology, Faculty of Sciences, Mohammed V University, Rabat, Morocco
- Research Center of Abulcasis University of Health Sciences, Cheikh Zaïd Hospital, Rabat, Morocco
| | - Bouabid El Ouahidi
- Department of Computer Science, Faculty of Sciences, Mohammed V University, Rabat, Morocco
| | - Mariam Naciri
- Department of Biology, Faculty of Sciences, Mohammed V University, Rabat, Morocco
| |
Collapse
|
41
|
Smit JM, van Genderen ME, Reinders MJT, Gommers DAMPJ, Krijthe JH, Van Bommel J. Demystifying machine learning for mortality prediction. Crit Care 2021; 25:447. [PMID: 34949229 PMCID: PMC8697544 DOI: 10.1186/s13054-021-03868-z] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2021] [Accepted: 11/27/2021] [Indexed: 11/24/2022] Open
Affiliation(s)
- J M Smit
- Department of Intensive Care, Erasmus University Medical Center, Rotterdam, Netherlands. .,EEMCS, Pattern Recognition and Bio-informatics Group, Delft University of Technology, Delft, Netherlands.
| | - M E van Genderen
- Department of Intensive Care, Erasmus University Medical Center, Rotterdam, Netherlands
| | - M J T Reinders
- EEMCS, Pattern Recognition and Bio-informatics Group, Delft University of Technology, Delft, Netherlands
| | - D A M P J Gommers
- Department of Intensive Care, Erasmus University Medical Center, Rotterdam, Netherlands
| | - J H Krijthe
- EEMCS, Pattern Recognition and Bio-informatics Group, Delft University of Technology, Delft, Netherlands
| | - J Van Bommel
- Department of Intensive Care, Erasmus University Medical Center, Rotterdam, Netherlands
| |
Collapse
|
42
|
Predictive Machine Learning Models and Survival Analysis for COVID-19 Prognosis Based on Hematochemical Parameters. SENSORS 2021; 21:s21248503. [PMID: 34960595 PMCID: PMC8705488 DOI: 10.3390/s21248503] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Revised: 12/15/2021] [Accepted: 12/17/2021] [Indexed: 12/26/2022]
Abstract
The coronavirus disease 2019 (COVID-19) pandemic has affected hundreds of millions of individuals and caused millions of deaths worldwide. Predicting the clinical course of the disease is of pivotal importance to manage patients. Several studies have found hematochemical alterations in COVID-19 patients, such as inflammatory markers. We retrospectively analyzed the anamnestic data and laboratory parameters of 303 patients diagnosed with COVID-19 who were admitted to the Polyclinic Hospital of Bari during the first phase of the COVID-19 global pandemic. After the pre-processing phase, we performed a survival analysis with Kaplan–Meier curves and Cox Regression, with the aim to discover the most unfavorable predictors. The target outcomes were mortality or admission to the intensive care unit (ICU). Different machine learning models were also compared to realize a robust classifier relying on a low number of strongly significant factors to estimate the risk of death or admission to ICU. From the survival analysis, it emerged that the most significant laboratory parameters for both outcomes was C-reactive protein min; HR=17.963 (95% CI 6.548–49.277, p < 0.001) for death, HR=1.789 (95% CI 1.000–3.200, p = 0.050) for admission to ICU. The second most important parameter was Erythrocytes max; HR=1.765 (95% CI 1.141–2.729, p < 0.05) for death, HR=1.481 (95% CI 0.895–2.452, p = 0.127) for admission to ICU. The best model for predicting the risk of death was the decision tree, which resulted in ROC-AUC of 89.66%, whereas the best model for predicting the admission to ICU was support vector machine, which had ROC-AUC of 95.07%. The hematochemical predictors identified in this study can be utilized as a strong prognostic signature to characterize the severity of the disease in COVID-19 patients.
Collapse
|
43
|
Linden T, Hanses F, Domingo-Fernández D, DeLong LN, Kodamullil AT, Schneider J, Vehreschild MJGT, Lanznaster J, Ruethrich MM, Borgmann S, Hower M, Wille K, Feldt T, Rieg S, Hertenstein B, Wyen C, Roemmele C, Vehreschild JJ, Jakob CEM, Stecher M, Kuzikov M, Zaliani A, Fröhlich H. Machine Learning Based Prediction of COVID-19 Mortality Suggests Repositioning of Anticancer Drug for Treating Severe Cases. ARTIFICIAL INTELLIGENCE IN THE LIFE SCIENCES 2021; 1:100020. [PMID: 34988543 PMCID: PMC8677630 DOI: 10.1016/j.ailsci.2021.100020] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/08/2021] [Revised: 11/22/2021] [Accepted: 11/22/2021] [Indexed: 02/08/2023]
Abstract
Despite available vaccinations COVID-19 case numbers around the world are still growing, and effective medications against severe cases are lacking. In this work, we developed a machine learning model which predicts mortality for COVID-19 patients using data from the multi-center 'Lean European Open Survey on SARS-CoV-2-infected patients' (LEOSS) observational study (>100 active sites in Europe, primarily in Germany), resulting into an AUC of almost 80%. We showed that molecular mechanisms related to dementia, one of the relevant predictors in our model, intersect with those associated to COVID-19. Most notably, among these molecules was tyrosine kinase 2 (TYK2), a protein that has been patented as drug target in Alzheimer's Disease but also genetically associated with severe COVID-19 outcomes. We experimentally verified that anti-cancer drugs Sorafenib and Regorafenib showed a clear anti-cytopathic effect in Caco2 and VERO-E6 cells and can thus be regarded as potential treatments against COVID-19. Altogether, our work demonstrates that interpretation of machine learning based risk models can point towards drug targets and new treatment options, which are strongly needed for COVID-19.
Collapse
Affiliation(s)
- Thomas Linden
- Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Schloss Birlinghoven, 53757 Sankt Augustin, Germany
- University of Bonn, Bonn-Aachen International Center for IT, Friedrich Hirzebruch-Allee 6, 53115 Bonn, Germany
| | - Frank Hanses
- Emergency Department, University Hospital Regensburg, 93053 Regensburg, Germany
- Department for Infectious Diseases and Infection Control, University Hospital Regensburg, Germany
| | - Daniel Domingo-Fernández
- Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Schloss Birlinghoven, 53757 Sankt Augustin, Germany
| | - Lauren Nicole DeLong
- Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Schloss Birlinghoven, 53757 Sankt Augustin, Germany
- University of Bonn, Bonn-Aachen International Center for IT, Friedrich Hirzebruch-Allee 6, 53115 Bonn, Germany
| | - Alpha Tom Kodamullil
- Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Schloss Birlinghoven, 53757 Sankt Augustin, Germany
| | - Jochen Schneider
- Technical University of Munich, School of Medicine, University Hospital rechts der Isar, Department of Internal Medicine II, 81675 Munich, Germany
| | - Maria J G T Vehreschild
- Department II of Internal Medicine, Infectious Diseases, University Hospital Frankfurt, Goethe University, 60590 Frankfurt, Germany
| | - Julia Lanznaster
- Department of Internal Medicine II, Hospital Passau, Innstraße 76, 94032 Passau, Germany
| | - Maria Madeleine Ruethrich
- Institute for Infection Medicine and Hospital Hygiene, University Hospital Jena, 07743 Jena, Germany
| | - Stefan Borgmann
- Department of Infectious Diseases and Infection Control, Hospital Ingolstadt, 85049 Ingolstadt, Germany
| | - Martin Hower
- Department of Pneumology, Infectious Diseases and Intensive Care, Klinikum Dortmund gGmbH, Hospital of University Witten / Herdecke, 44137 Dortmund, Germany
| | - Kai Wille
- University Clinic for Haematology, Oncology, Haemostaseology and Palliative Care, Johannes Wesling Medical Centre Minden, 32429 Minden, Germany
| | - Torsten Feldt
- Department of Gastroenterology, Hepatology and Infectious Diseases, University Hospital Düsseldorf, Medical Faculty of Heinrich Heine University Düsseldorf, Moorenstrasse 5, 40225 Düsseldorf, Germany
| | - Siegbert Rieg
- Department of Medicine II, University Hospital Freiburg, 79110 Freiburg, Germany
| | - Bernd Hertenstein
- Department of Medicine II, University Hospital Freiburg, 79110 Freiburg, Germany
| | - Christoph Wyen
- Christoph Wyen, Praxis am Ebertplatz Cologne, 50668 Cologne, Germany
| | - Christoph Roemmele
- Internal Medicine III - Gastroenterology and Infectious Diseases, University Hospital Augsburg, 86156 Augsburg, Germany
| | - Jörg Janne Vehreschild
- Department II of Internal Medicine, Infectious Diseases, University Hospital Frankfurt, Goethe University, 60590 Frankfurt, Germany
| | - Carolin E M Jakob
- Department I for Internal Medicine, University Hospital of Cologne, University of Cologne, 50931 Cologne, Germany
| | - Melanie Stecher
- Fraunhofer Institute for Translational Medicine and Pharmacologie (ITMP), VolksparkLabs, Schnackenburgallee 114, 22535 Hamburg, Germany
| | - Maria Kuzikov
- Department for Infectious Diseases and Infection Control, University Hospital Regensburg, Germany
| | - Andrea Zaliani
- Department for Infectious Diseases and Infection Control, University Hospital Regensburg, Germany
| | - Holger Fröhlich
- Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Schloss Birlinghoven, 53757 Sankt Augustin, Germany
- University of Bonn, Bonn-Aachen International Center for IT, Friedrich Hirzebruch-Allee 6, 53115 Bonn, Germany
| |
Collapse
|
44
|
Han X, Xu J, Hou H, Yang H, Wang Y. Impact of asthma on COVID-19 mortality in the United States: Evidence based on a meta-analysis. Int Immunopharmacol 2021; 102:108390. [PMID: 34844871 PMCID: PMC8611693 DOI: 10.1016/j.intimp.2021.108390] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2021] [Revised: 11/18/2021] [Accepted: 11/18/2021] [Indexed: 02/07/2023]
Abstract
OBJECTIVE The aim of this study was to investigate the impact of asthma on the risk for mortality among coronavirus disease 2019 (COVID-19) patients in the United States by a quantitative meta-analysis. METHODS A random-effects model was used to estimate the pooled odds ratio (OR) with corresponding 95% confidence interval (CI). I2 statistic, sensitivity analysis, Begg's test, meta-regression and subgroup analyses were also performed. RESULTS The data based on 56 studies with 426,261 COVID-19 patients showed that there was a statistically significant association between pre-existing asthma and the reduced risk for COVID-19 mortality in the United States (OR: 0.82, 95% CI: 0.74-0.91). Subgroup analyses by age, male proportion, sample size, study design and setting demonstrated that pre-existing asthma was associated with a significantly reduced risk for COVID-19 mortality among studies with age ≥ 60 years old (OR: 0.79, 95% CI: 0.72-0.87), male proportion ≥ 55% (OR: 0.79, 95% CI: 0.72-0.87), male proportion < 55% (OR: 0.81, 95% CI: 0.69-0.95), sample sizes ≥ 700 cases (OR: 0.80, 95% CI: 0.71-0.91), retrospective study/case series (OR: 0.82, 95% CI: 0.75-0.89), prospective study (OR: 0.83, 95% CI: 0.70-0.98) and hospitalized patients (OR: 0.82, 95% CI: 0.74-0.91). Meta-regression did reveal none of factors mentioned above were possible reasons of heterogeneity. Sensitivity analysis indicated the robustness of our findings. No publication bias was detected in Begg's test (P = 0.4538). CONCLUSION Our findings demonstrated pre-existing asthma was significantly associated with a reduced risk for COVID-19 mortality in the United States.
Collapse
Affiliation(s)
- Xueya Han
- Department of Epidemiology, School of Public Health, Zhengzhou University, Zhengzhou 450001, Henan Province, China
| | - Jie Xu
- Department of Epidemiology, School of Public Health, Zhengzhou University, Zhengzhou 450001, Henan Province, China
| | - Hongjie Hou
- Department of Epidemiology, School of Public Health, Zhengzhou University, Zhengzhou 450001, Henan Province, China
| | - Haiyan Yang
- Department of Epidemiology, School of Public Health, Zhengzhou University, Zhengzhou 450001, Henan Province, China.
| | - Yadong Wang
- Department of Toxicology, Henan Center for Disease Control and Prevention, Zhengzhou 450016, Henan Province, China
| |
Collapse
|
45
|
Lynch JB, Davitkov P, Anderson DJ, Bhimraj A, Cheng VCC, Guzman-Cottrill J, Dhindsa J, Duggal A, Jain MK, Lee GM, Liang SY, McGeer A, Varghese J, Lavergne V, Murad MH, Mustafa RA, Sultan S, Falck-Ytter Y, Morgan RL. Infectious Diseases Society of America Guidelines on Infection Prevention for Healthcare Personnel Caring for Patients with Suspected or Known COVID-19. Clin Infect Dis 2021:ciab953. [PMID: 34791102 PMCID: PMC8767890 DOI: 10.1093/cid/ciab953] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2021] [Indexed: 01/08/2023] Open
Abstract
BACKGROUND Since its emergence in late 2019, SARS-CoV-2 continues to pose a risk to healthcare personnel (HCP) and patients in healthcare settings. Although all clinical interactions likely carry some risk of transmission, human actions like coughing and care activities like aerosol-generating procedures likely have a higher risk of transmission. The rapid emergence and global spread of SARS-CoV-2 continues to create significant challenges in healthcare facilities, particularly with shortages of personal protective equipment (PPE) used by HCP. Evidence-based recommendations for what PPE to use in conventional, contingency, and crisis standards of care continue to be needed. Where evidence is lacking, the development of specific research questions can help direct funders and investigators. OBJECTIVE Develop evidence-based rapid guidelines intended to support HCP in their decisions about infection prevention when caring for patients with suspected or known COVID-19. METHODS IDSA formed a multidisciplinary guideline panel including frontline clinicians, infectious disease specialists, experts in infection control, and guideline methodologists with representation from the disciplines of public health, medical microbiology, pediatrics, critical care medicine and gastroenterology. The process followed a rapid recommendation checklist. The panel prioritized questions and outcomes. Then a systematic review of the peer-reviewed and grey literature was conducted. The Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach was used to assess the certainty of evidence and make recommendations. RESULTS The IDSA guideline panel agreed on eight recommendations, including two updated recommendations and one new recommendation added since the first version of the guideline. Narrative summaries of other interventions undergoing evaluations are also included. CONCLUSIONS Using a combination of direct and indirect evidence, the panel was able to provide recommendations for eight specific questions on the use of PPE for HCP providing care for patients with suspected or known COVID-19. Where evidence was lacking, attempts were made to provide potential avenues for investigation. There remain significant gaps in the understanding of the transmission dynamics of SARS-CoV-2 and PPE recommendations may need to be modified in response to new evidence. These recommendations should serve as a minimum for PPE use in healthcare facilities and do not preclude decisions based on local risk assessments or requirements of local health jurisdictions or other regulatory bodies.
Collapse
Affiliation(s)
- John B Lynch
- Department of Medicine, Division of Allergy and Infectious Diseases, University of Washington, Seattle, Washington
| | - Perica Davitkov
- VA Northeast Ohio Healthcare System, Case Western Reserve University School of Medicine, Cleveland, Ohio
| | - Deverick J Anderson
- Duke Center for Antimicrobial Stewardship and Infection Prevention, Duke University School of Medicine, Durham, North Carolina
| | - Adarsh Bhimraj
- Department of Infectious Diseases, Cleveland Clinic, Cleveland, Ohio
| | - Vincent Chi-Chung Cheng
- Queen Mary Hospital, Department of Microbiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China
| | - Judith Guzman-Cottrill
- Department of Pediatrics, Division of Infectious Diseases, Oregon Health and Science University, Portland, Oregon
| | | | - Abhijit Duggal
- Department of Critical Care, Cleveland Clinic, Cleveland, Ohio
| | - Mamta K Jain
- Department of Internal Medicine, Division of Infectious Diseases, UT Southwestern Medical Center, Dallas, Texas
| | - Grace M Lee
- Department of Pediatrics-Infectious Disease, Stanford University School of Medicine, Stanford, California
| | - Stephen Y Liang
- Division of Infectious Diseases and Emergency Medicine, Washington University School of Medicine, St. Louis, Missouri
| | - Allison McGeer
- Department of Microbiology, Sinai Health System, University of Toronto, Toronto, Ontario
| | - Jamie Varghese
- Department of Health Research Methods, Evidence and Impact, McMaster University, Hamilton, Ontario
| | - Valery Lavergne
- Department of Pathology and Laboratory Medicine, Vancouver General Hospital, Vancouver, British Columbia, Canada
| | - M Hassan Murad
- Division of Preventive Medicine, Mayo Clinic, Rochester, Minnesota
| | - Reem A Mustafa
- Division of Nephrology and Hypertension, Department of Internal Medicine, University of Kansas Medical Center, Kansas City, Kansas
| | - Shahnaz Sultan
- Division of Gastroenterology, Hepatology, and Nutrition, University of Minnesota, Minneapolis VA Health Care System, Minneapolis, Minnesota
| | - Yngve Falck-Ytter
- VA Northeast Ohio Healthcare System, Case Western Reserve University School of Medicine, Cleveland, Ohio
| | - Rebecca L Morgan
- Department of Health Research Methods, Evidence and Impact, McMaster University, Hamilton, Ontario
| |
Collapse
|