{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T09:24:05Z","timestamp":1781947445310,"version":"3.54.5"},"reference-count":68,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,7,28]],"date-time":"2023-07-28T00:00:00Z","timestamp":1690502400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>The SARS-CoV-2 (COVID-19) pandemic has created substantial health and economic burdens in the US and worldwide. As new variants continuously emerge, predicting critical clinical events in the context of relevant individual risks is a promising option for reducing the overall burden of COVID-19. This study aims to train an AI-driven decision support system that helps build a model to understand the most important features that predict the \u201cmortality\u201d of patients hospitalized with COVID-19.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We conducted a retrospective analysis of \u201c5,371\u201d patients hospitalized for COVID-19-related symptoms from the South Florida Memorial Health Care System between March 14th, 2020, and January 16th, 2021. A data set comprising patients\u2019 sociodemographic characteristics, pre-existing health information, and medication was analyzed. We trained Random Forest classifier to predict \u201cmortality\u201d for patients hospitalized with COVID-19.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Based on the interpretability of the model, age emerged as the primary predictor of \u201cmortality\u201d, followed by diarrhea, diabetes, hypertension, BMI, early stages of kidney disease, smoking status, sex, pneumonia, and race in descending order of importance. Notably, individuals aged over 65 years (referred to as \u201colder adults\u201d), males, Whites, Hispanics, and current smokers were identified as being at higher risk of death. Additionally, BMI, specifically in the overweight and obese categories, significantly predicted \u201cmortality\u201d. These findings indicated that the model effectively learned from various categories, such as patients' sociodemographic characteristics, pre-hospital comorbidities, and medications, with a predominant focus on characterizing pre-hospital comorbidities. Consequently, the model demonstrated the ability to predict \u201cmortality\u201d with transparency and reliability.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>AI can potentially provide healthcare workers with the ability to stratify patients and streamline optimal care solutions when time is of the essence and resources are limited. This work sets the platform for future work that forecasts patient responses to treatments at various levels of disease severity and assesses health disparities and patient conditions that promote improved health care in a broader context. This study contributed to one of the first predictive analyses applying AI\/ML techniques to COVID-19 data using a vast sample from South Florida.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fdgth.2023.1193467","type":"journal-article","created":{"date-parts":[[2023,7,28]],"date-time":"2023-07-28T17:42:10Z","timestamp":1690566130000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Using machine learning to identify patient characteristics to predict mortality of in-patients with COVID-19 in South Florida"],"prefix":"10.3389","volume":"5","author":[{"given":"Debarshi","family":"Datta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Safiya","family":"George Dalmida","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurie","family":"Martinez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Newman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javad","family":"Hashemi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Connor","family":"Shorten","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Candice","family":"Sareli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paula","family":"Eckardt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,7,28]]},"reference":[{"key":"B1","year":""},{"key":"B2","year":""},{"key":"B3","doi-asserted-by":"publisher","first-page":"e0252384","DOI":"10.1371\/journal.pone.0252384","article-title":"A machine learning based exploration of COVID-19 mortality risk","volume":"16","author":"Mahdavi","year":"2021","journal-title":"Plos One"},{"key":"B4","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1002\/ctm2.323","article-title":"Accurate classification of COVID-19 patients with different severity via machine learning","volume":"11","author":"Sun","year":"2021","journal-title":"Clin Transl Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1, 3","DOI":"10.1111\/ijcp.13666","article-title":"Gender differences in the battle against COVID-19: impact of genetics, comorbidities, inflammation and lifestyle on differences in outcomes","volume":"75","author":"Anca","year":"2021","journal-title":"Int J Clin Pract"},{"key":"B6","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jmii.2020.05.001","article-title":"A systematic review of asymptomatic infections with COVID-19. Journal of microbiology","volume":"54","author":"Gao","year":"2021","journal-title":"Immunol Infect"},{"key":"B7","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1159\/000513288","article-title":"The association between presence of comorbidities and COVID-19 severity: a systematic review and meta-analysis","volume":"50","author":"Honardoost","year":"2021","journal-title":"Cerebrovasc Dis"},{"key":"B8","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1159\/000513400","article-title":"The clinical characteristics and risk factors of severe COVID-19","volume":"67","author":"Hu","year":"2021","journal-title":"Gerontology"},{"key":"B9","first-page":"3","volume-title":"Underlying medical conditions associated with higher risk for severe COVID-19: information for healthcare professionals","year":"2022"},{"key":"B10","doi-asserted-by":"publisher","first-page":"759","DOI":"10.15585\/mmwr.mm6924e2","article-title":"Coronavirus disease 2019 case surveillance\u2014united States, January 22\u2013may 30, 2020","volume":"69","author":"Stokes","year":"2020","journal-title":"Morb Mortal Wkly Rep"},{"key":"B11","doi-asserted-by":"publisher","first-page":"458","DOI":"10.15585\/mmwr.mm6915e3","article-title":"Hospitalization rates and characteristics of patients hospitalized with laboratory-confirmed coronavirus disease 2019\u2014cOVID-NET, 14 states, march 1\u201330, 2020","volume":"69","author":"Garg","year":"2020","journal-title":"Morb Mortal Wkly Rep"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1708","DOI":"10.1056\/NEJMoa2002032","article-title":"Clinical characteristics of coronavirus disease 2019 in China","volume":"382","author":"Guan","year":"2020","journal-title":"N Engl J Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"154262","DOI":"10.1016\/j.metabol.2020.154262","article-title":"Severe obesity, increasing age and male sex are independently associated with worse in-hospital outcomes, and higher in-hospital mortality, in a cohort of patients with COVID-19 in the Bronx, New York","volume":"108","author":"Palaiodimos","year":"2020","journal-title":"Metab Clin Exp"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e657","DOI":"10.1002\/hsr2.657","article-title":"COVID-19 mortality and its predictors in the elderly: a systematic review","volume":"5","author":"Dadras","year":"2022","journal-title":"Health Sci Rep"},{"key":"B15","doi-asserted-by":"publisher","first-page":"27","DOI":"10.18632\/aging.202456","article-title":"Mortality risk of COVID-19 in elderly males with comorbidities: a multi-country study","volume":"13","author":"Li","year":"2021","journal-title":"Aging"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e0254066","DOI":"10.1371\/journal.pone.0254066","article-title":"Male gender is a predictor of higher mortality in hospitalized adults with COVID-19","volume":"16","author":"Nguyen","year":"2021","journal-title":"PLoS One"},{"key":"B17","doi-asserted-by":"publisher","first-page":"936","DOI":"10.18553\/jmcp.2022.22050","article-title":"Direct health care costs associated with COVID-19 in the United States","volume":"28","author":"DeMartino","year":"2022","journal-title":"J Manag Care Spec Pharm"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12913-020-05996-8","article-title":"The economic burden of coronavirus disease 2019 (COVID-19): evidence from Iran","volume":"21","author":"Darab M","year":"2021","journal-title":"BMC Health Serv Res"},{"key":"B19","doi-asserted-by":"publisher","first-page":"293","DOI":"10.2147\/CEOR.S338225","article-title":"Economic burden of COVID-19: a systematic review","volume":"14","author":"Richards","year":"2022","journal-title":"Clinicoecon Outcomes Res"},{"key":"B20","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1377\/hlthaff.2020.00426","article-title":"The potential health care costs and resource use associated with COVID-19 in the United States: a simulation estimate of the direct medical costs and health care resource use associated with COVID-19 infections in the United States","volume":"39","author":"Bartsch","year":"2020","journal-title":"Health Aff"},{"key":"B21","doi-asserted-by":"publisher","first-page":"104737","DOI":"10.1016\/j.meegid.2021.104737","article-title":"Machine learning predictive model for severe COVID-19","volume":"90","author":"Kang","year":"2021","journal-title":"Infect Genet Evol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e0236618","DOI":"10.1371\/journal.pone.0236618","article-title":"Prediction model and risk scores of ICU admission and mortality in COVID-19","volume":"15","author":"Zhao","year":"2020","journal-title":"PloS One"},{"key":"B23","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.jpeds.2020.05.006","article-title":"Clinical characteristics and outcomes of hospitalized and critically ill children and adolescents with coronavirus disease 2019 at a tertiary care medical center in New York city","volume":"223","author":"Chao","year":"2020","journal-title":"J Pediatr"},{"key":"B24","doi-asserted-by":"publisher","first-page":"237","DOI":"10.14740\/jocmr4476","article-title":"A simplified comorbidity evaluation predicting clinical outcomes among patients with coronavirus disease 2019","volume":"13","author":"Kirby","year":"2021","journal-title":"J Clin Med Res"},{"key":"B25","doi-asserted-by":"publisher","first-page":"210","DOI":"10.3389\/fdgth.2021.681608","article-title":"Using machine learning to predict mortality for COVID-19 patients on day 0 in the ICU","volume":"3","author":"Jamshidi","year":"2022","journal-title":"Front Digit Health"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1002\/emp2.12205","article-title":"Deep-learning artificial intelligence analysis of clinical variables predicts mortality in COVID-19 patients","volume":"1","author":"Zhu","year":"2020","journal-title":"J Am Coll Emerg Phys Open"},{"key":"B27","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1111\/j.1467-842X.2001.tb00294.x","article-title":"How can I deal with missing data in my study?","volume":"25","author":"Bennett","year":"2001","journal-title":"Aust N Z J Public Health"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.3389\/fcimb.2021.777070","article-title":"Impact of age and sex on COVID-19 severity assessed from radiologic and clinical findings","volume":"11","author":"Statsenko","year":"2022","journal-title":"Front Cell Infect Microbiol"},{"key":"B29","article-title":"BMI classification percentile and cut off points. [Updated 2022 Jun 27]","volume-title":"StatPearls [Internet]","author":"Weir","year":"2023"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0278-0","article-title":"Survey on categorical data for neural networks","volume":"7","author":"Hancock","year":"2020","journal-title":"J Big Data"},{"key":"B31","first-page":"106","article-title":"On artificial results due to using factor analysis for dichotomous variables","volume":"45","author":"Kubinger","year":"2003","journal-title":"Psychol Sci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"629","DOI":"10.3390\/ijgi10090629","article-title":"Application of random forest and SHAP tree explainer in exploring spatial (in) justice to aid urban planning","volume":"10","author":"Deb","year":"2021","journal-title":"ISPRS Int J Geoinf"},{"key":"B33","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"B34","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"B35","volume-title":"Discovering statistics using IBM SPSS statistics","author":"Field","year":"2013"},{"key":"B36","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3462-1","volume-title":"Regression modeling strategies: With applications to linear models, logistic regression, and survival analysis","author":"Harrell","year":"2001"},{"key":"B37","doi-asserted-by":"crossref","DOI":"10.1002\/9781118548387","volume-title":"Applied logistic regression","author":"Hosmer","year":"2013"},{"key":"B38","doi-asserted-by":"publisher","first-page":"935","DOI":"10.1016\/S0895-4356(99)00103-1","article-title":"Stepwise selection in small data sets: a simulation study of bias in logistic regression analysis","volume":"52","author":"Steyerberg","year":"1999","journal-title":"J Clin Epidemiol"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/cc3045","article-title":"Statistics review 14: logistic regression","volume":"9","author":"Bewick","year":"2005","journal-title":"Crit Care"},{"key":"B40","doi-asserted-by":"publisher","first-page":"5438","DOI":"10.3390\/app11125438","article-title":"Classification performance for COVID patient prognosis from automatic AI segmentation\u2014a single-center study","volume":"11","author":"Biondi","year":"2021","journal-title":"Appl Sci"},{"key":"B41","doi-asserted-by":"publisher","first-page":"103677","DOI":"10.1016\/j.scs.2022.103677","article-title":"Explainable heat-related mortality with random forest and SHapley additive exPlanations (SHAP) models","volume":"79","author":"Kim","year":"2022","journal-title":"Sustain Cities Soc"},{"key":"B42","author":"Silva","year":"2021"},{"key":"B43","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1002\/ima.22812","article-title":"A deep learning approach for classification of COVID and pneumonia using DenseNet-201","volume":"33","author":"Sanghvi","year":"2023","journal-title":"Int J Imaging Syst Technol"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3397325","article-title":"Making sense of sleep: multimodal sleep stage classification in a large, diverse population using movement and cardiac sensing","volume":"4","author":"Zhai","year":"2020","journal-title":"Proc ACM interact Mobile Wearable Ubiquitous Technol"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-77296-4","article-title":"Selecting the most important self-assessed features for predicting conversion to mild cognitive impairment with random forest and permutation-based methods","volume":"10","author":"G\u00f3mez-Ram\u00edrez","year":"2020","journal-title":"Sci Rep"},{"key":"B46","doi-asserted-by":"publisher","first-page":"8761","DOI":"10.1021\/acs.jmedchem.9b01101","article-title":"Interpretation of compound activity predictions from complex machine learning models using local approximations and shapley values","volume":"63","author":"Rodr\u00edguez-P\u00e9rez","year":"2019","journal-title":"J Med Chem"},{"key":"B47","doi-asserted-by":"publisher","first-page":"4789","DOI":"10.3390\/en15134789","article-title":"Renewable energy community pairing methodology using statistical learning applied to georeferenced energy profiles","volume":"15","author":"Lucas","year":"2022","journal-title":"Energies"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-99269-x","article-title":"A machine learning model for predicting deterioration of COVID-19 inpatients","volume":"12","author":"Noy","year":"2022","journal-title":"Sci Rep"},{"key":"B49","doi-asserted-by":"publisher","first-page":"119115","DOI":"10.1016\/j.eswa.2022.119115","article-title":"AcME\u2014accelerated model-agnostic explanations: fast whitening of the machine-learning black box","volume":"214","author":"Dandolo","year":"2023","journal-title":"Expert Syst Appl"},{"key":"B50","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1093\/ehjdh\/ztab096","article-title":"Explainable machine learning predictions to support personalized cardiology strategies","volume":"3","author":"Loh","year":"2022","journal-title":"Eur Heart J Digit Health"},{"key":"B51","doi-asserted-by":"publisher","first-page":"e0281666","DOI":"10.1371\/journal.pone.0281666","article-title":"Using machine learning to improve our understanding of COVID-19 infection in children","volume":"18","author":"Piparia","year":"2023","journal-title":"Plos one"},{"key":"B52","volume-title":"Explainable machine learning, game theory, and shapley values: a technical review","author":"Fadel","year":"2022"},{"key":"B53","first-page":"D021S008R006","article-title":"Machine learning model interpretability using SHAP values: application to a seismic facies classification task","volume-title":"SEG international exposition and annual meeting","author":"Lubo-Robles","year":"2020"},{"key":"B54","doi-asserted-by":"publisher","first-page":"6968","DOI":"10.1038\/s41598-021-86327-7","article-title":"Explainable machine learning can outperform cox regression predictions and provide insights in breast cancer survival","volume":"11","author":"Moncada-Torres","year":"2021","journal-title":"Sci Rep"},{"key":"B55","doi-asserted-by":"publisher","first-page":"100323","DOI":"10.1016\/j.smhl.2022.100323","article-title":"Machine learning and comorbidity network analysis for hospitalized patients with COVID-19 in a city in southern Brazil","volume":"26","author":"Passarelli-Araujo","year":"2022","journal-title":"Smart Health"},{"key":"B56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.32473\/flairs.v35i.130670","article-title":"Using SHAP to interpret XGBoost predictions of grassland degradation in Xilingol, China","volume":"2020","author":"Wieland","year":"2020","journal-title":"Geosci Mod Dev Discuss"},{"key":"B57","author":"Shorten","year":""},{"key":"B58","first-page":"1449","author":"Shorten","year":""},{"key":"B59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13054-021-03720-4","article-title":"Machine learning identifies ICU outcome predictors in a multicenter COVID-19 cohort","volume":"25","author":"Magunia","year":"2021","journal-title":"Crit Care"},{"key":"B60","doi-asserted-by":"publisher","first-page":"7097","DOI":"10.1038\/s41598-022-09771-z","article-title":"Machine learning-based model for prediction of clinical deterioration in hospitalized patients by COVID 19","volume":"12","author":"Garcia-Guti\u00e9rrez","year":"2022","journal-title":"Sci Rep"},{"key":"B61","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1016\/j.ajem.2020.09.017","article-title":"Predicting severe outcomes in COVID-19 related illness using only patient demographics, comorbidities and symptoms","volume":"45","author":"Ryan","year":"2021","journal-title":"Am J Emerg Med"},{"key":"B62","doi-asserted-by":"publisher","first-page":"4673","DOI":"10.1038\/s41598-021-83967-7","article-title":"Machine learning based predictors for COVID-19 disease severity","volume":"11","author":"Patel","year":"2021","journal-title":"Sci Rep"},{"key":"B63","doi-asserted-by":"publisher","first-page":"e0239172","DOI":"10.1371\/journal.pone.0239172","article-title":"Machine learning in predicting respiratory failure in patients with COVID-19 pneumonia\u2014challenges, strengths, and opportunities in a global health emergency","volume":"15","author":"Ferrari","year":"2020","journal-title":"PLoS One"},{"key":"B64","doi-asserted-by":"publisher","first-page":"e0245384","DOI":"10.1371\/journal.pone.0245384","article-title":"Machine learning model for predicting severity prognosis in patients infected with COVID-19: study protocol from COVID-AI brasil","volume":"16","author":"Paiva Proen\u00e7a Lobo Lopes","year":"2021","journal-title":"Plos One"},{"key":"B65","doi-asserted-by":"publisher","first-page":"e0236240","DOI":"10.1371\/journal.pone.0236240","article-title":"Pre-existing traits associated with COVID-19 illness severity","volume":"15","author":"Ebinger","year":"2020","journal-title":"PloS One"},{"key":"B66","doi-asserted-by":"publisher","first-page":"21","DOI":"10.14744\/AnatolJCardiol.2020.57431","article-title":"Association between chronic ACE inhibitor exposure and decreased odds of severe disease in patients with COVID-19","volume":"24","author":"\u015eenkal","year":"2020","journal-title":"Anatol J Cardiol"},{"key":"B67","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.ijid.2020.03.040","article-title":"Epidemiological, clinical characteristics of cases of SARS-CoV-2 infection with abnormal imaging findings","volume":"94","author":"Zhang","year":"2020","journal-title":"Int J Infect Dis"},{"key":"B68","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/s00167-022-06896-6","article-title":"Machine learning and conventional statistics: making sense of the differences","volume":"30","author":"Ley","year":"2022","journal-title":"Knee Surg Sports Traumatol Arthrosc"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2023.1193467\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T23:10:37Z","timestamp":1695337837000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2023.1193467\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,28]]},"references-count":68,"alternative-id":["10.3389\/fdgth.2023.1193467"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2023.1193467","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,28]]},"article-number":"1193467"}}