{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T15:49:19Z","timestamp":1776872959912,"version":"3.51.2"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,10,10]],"date-time":"2023-10-10T00:00:00Z","timestamp":1696896000000},"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. Artif. Intell."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>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 <jats:italic>K<\/jats:italic>-means clustering. Further evaluation of the algorithms was performed using sensitivity, accuracy, specificity, and Cohen's <jats:italic>K<\/jats:italic> statistics.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>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, FiO<jats:sub>2<\/jats:sub>, 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 <jats:italic>k<\/jats:italic>-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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>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.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2023.1171256","type":"journal-article","created":{"date-parts":[[2023,10,10]],"date-time":"2023-10-10T11:24:53Z","timestamp":1696937093000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Machine learning algorithms for predicting determinants of COVID-19 mortality in South Africa"],"prefix":"10.3389","volume":"6","author":[{"given":"Emmanuel","family":"Chimbunde","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lovemore N.","family":"Sigwadhi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacques L.","family":"Tamuzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elphas L.","family":"Okango","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olawande","family":"Daramola","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Veranyuy D.","family":"Ngah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter S.","family":"Nyasulu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,10,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2833","DOI":"10.1016\/j.csbj.2021.05.010","article-title":"Artificial intelligence in clinical care amidst COVID-19 pandemic: a systematic review","volume":"19","author":"Adamidi","year":"2021","journal-title":"Comp. Struct. Biotechnol. J"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2651","DOI":"10.3390\/jcm12072651","article-title":"Mortality, intensive care unit admission, and intubation among hospitalized patients with COVID-19: a one-year retrospective study in Jordan","volume":"12","author":"Al Oweidat","year":"2023","journal-title":"J. Clin. Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1186\/s13054-021-03749-5","article-title":"Machine-learning-based COVID-19 mortality prediction model and identification of patients at low and high risk of dying","volume":"25","author":"Banoei","year":"2021","journal-title":"Crit. Care"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e2022068","DOI":"10.23750\/abm.v93i3.11880","article-title":"The effect of diabetes mellitus on mortality in patients hospitalized intensive care unit in Covid-19 pandemic","volume":"93","author":"Ba\u015fi","year":"2022","journal-title":"Acta Biomed."},{"key":"B5","doi-asserted-by":"publisher","first-page":"2001875","DOI":"10.1183\/13993003.01875-2020","article-title":"Characteristics and outcomes of asthmatic patients with COVID-19 pneumonia who require hospitalisation","volume":"56","author":"Beurnier","year":"2020","journal-title":"Eur. Respir. J"},{"key":"B6","doi-asserted-by":"publisher","first-page":"18126","DOI":"10.1038\/s41598-022-22547-9","article-title":"A predictive model for hospitalization and survival to COVID-19 in a retrospective population-based study","volume":"12","author":"Cisterna-Garc\u00eda","year":"2022","journal-title":"Sci. Rep"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13098-020-00586-4","article-title":"Severity and mortality of COVID 19 in patients with diabetes, hypertension, and cardiovascular disease: a meta-analysis","volume":"12","author":"de Almeida-Pititto","year":"2020","journal-title":"Diabetol. Metab. Syndr"},{"key":"B8","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1016\/j.jiph.2022.06.008","article-title":"Machine learning decision tree algorithm role for predicting mortality in critically ill adult COVID-19 patients admitted to the ICU","volume":"15","author":"Elhazmi","year":"2022","journal-title":"J. Infect. Public Health"},{"key":"B9","doi-asserted-by":"publisher","first-page":"101741","DOI":"10.1016\/j.techsoc.2021.101741","article-title":"Artificial intelligence, systemic risks, and sustainability","volume":"67","author":"Galaz","year":"2021","journal-title":"Technol. Soc"},{"key":"B10","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1007\/s42399-021-00851-1","article-title":"Diabetes mellitus and hypertension increase risk of death in novel corona virus patients irrespective of age: a prospective observational study of co-morbidities and COVID-19 from India","volume":"3","author":"Gupta","year":"2021","journal-title":"SN Compr. Clin. Med"},{"key":"B11","doi-asserted-by":"publisher","first-page":"e31549","DOI":"10.2196\/31549","article-title":"The development and validation of simplified machine learning algorithms to predict prognosis of hospitalized patients with COVID-19: multicenter, retrospective study","volume":"24","author":"He","year":"2022","journal-title":"J. Med. Int. Res"},{"key":"B12","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s10489-021-02743-2","article-title":"Machine learning techniques to predict different levels of hospital care of Covid-19","volume":"52","author":"Hern\u00e1ndez-Pereira","year":"2022","journal-title":"Appl. Intellig"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e0248029","DOI":"10.1371\/journal.pone.0248029","article-title":"First and second waves of coronavirus disease-19: a comparative study in hospitalized patients in Reus, Spain","volume":"16","author":"Iftimie","year":"2021","journal-title":"PLoS ONE"},{"key":"B14","doi-asserted-by":"publisher","first-page":"12801","DOI":"10.1038\/s41598-021-92146-7","article-title":"Multivariable mortality risk prediction using machine learning for COVID-19 patients at admission (AICOVID)","volume":"11","author":"Kar","year":"2021","journal-title":"Sci. Rep"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v028.i05","article-title":"Building predictive models in R using the caret package","volume":"28","author":"Kuhn","year":"2008","journal-title":"J. Stat. Softw."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.7196\/AJTCCM.2021.v27i4.185","article-title":"Comparison of patients with severe COVID-19 admitted to an intensive care unit in South Africa during the first and second wave of the COVID-19 pandemic","author":"Lalla","year":"2021","journal-title":"Afr. J. Thorac. Crit. Care Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e10337","DOI":"10.7717\/peerj.10337","article-title":"Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variables","volume":"8","author":"Li","year":"2020","journal-title":"PeerJ"},{"key":"B18","first-page":"1822","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw","year":"2002","journal-title":"R news"},{"key":"B19","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":"B20","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s12911-021-01742-0","article-title":"Comparing machine learning algorithms for predicting COVID-19 mortality","volume":"22","author":"Moulaei","year":"2022","journal-title":"BMC Med. Informat. Decis. Making"},{"key":"B21","doi-asserted-by":"publisher","first-page":"n2281","DOI":"10.1136\/bmj.n2281","article-title":"Risk of bias in studies on prediction models developed using supervised machine learning techniques: systematic review","volume":"375","author":"Navarro","year":"2021","journal-title":"BMJ"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e0279565","DOI":"10.1371\/journal.pone.0279565","article-title":"Clinical characteristics associated with mortality of COVID-19 patients admitted to an intensive care unit of a tertiary hospital in South Africa","volume":"17","author":"Nyasulu","year":"2022","journal-title":"PLoS ONE"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1164\/rccm.201810-1844LE","article-title":"Trends in asthma mortality in the United States: 1999 to 2015","volume":"199","author":"Pennington","year":"2019","journal-title":"Am. J. Respir. Crit. Care Med"},{"key":"B24","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.jaip.2021.10.049","article-title":"Impact of allergic rhinitis and asthma on COVID-19 infection, hospitalization, and mortality","volume":"10","author":"Ren","year":"2022","journal-title":"J. Aller. Clin. Immunol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"2","DOI":"10.4103\/jehp.jehp_387_21","article-title":"Developing an artificial neural network for detecting COVID-19 disease","volume":"11","author":"Shanbehzadeh","year":"2022","journal-title":"J. Educ. Health Promot"},{"key":"B26","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1016\/j.ijid.2020.04.085","article-title":"Logistic growth modelling of COVID-19 proliferation in China and its international implications","volume":"96","author":"Shen","year":"2020","journal-title":"Int. J. Infect. Dis"},{"key":"B27","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1038\/s41746-021-00456-x","article-title":"Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19","volume":"4","author":"Subudhi","year":"2021","journal-title":"NPJ Dig. Med"},{"key":"B28","doi-asserted-by":"publisher","first-page":"343","DOI":"10.3390\/jpm11050343","article-title":"Predicting in-hospital mortality of patients with COVID-19 using machine learning techniques","volume":"11","author":"Tezza","year":"2021","journal-title":"J. Pers. Med"},{"key":"B29","unstructured":"WHO's COVID-19 Response2022"},{"key":"B30","unstructured":"Weekly Epidemiological Update on COVID-192023"},{"key":"B31","doi-asserted-by":"publisher","first-page":"838749","DOI":"10.3389\/fcimb.2022.838749","article-title":"Statistical analysis, and machine learning prediction of disease outcomes for COVID-19 and pneumonia patients","volume":"12","author":"Zhao","year":"2022","journal-title":"Front. Cell. Infect. Microbiol"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1171256\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T11:33:27Z","timestamp":1697024007000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1171256\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,10]]},"references-count":31,"alternative-id":["10.3389\/frai.2023.1171256"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1171256","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,10]]},"article-number":"1171256"}}