{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:12:14Z","timestamp":1784301134563,"version":"3.55.0"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T00:00:00Z","timestamp":1734480000000},"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:p>In 2019, COVID-19 began one of the greatest public health challenges in history, reaching pandemic status the following year. Systems capable of predicting individuals at higher risk of progressing to severe forms of the disease could optimize the allocation and direction of resources. In this work, we evaluated the performance of different Machine Learning algorithms when predicting clinical outcomes of patients hospitalized with COVID-19, using clinical data from hospital admission alone. This data was collected during a prospective, multicenter cohort that followed patients with respiratory syndrome during the pandemic. We aimed to predict which patients would present mild cases of COVID-19 and which would develop severe cases. Severe cases were defined as those requiring access to the Intensive Care Unit, endotracheal intubation, or even progressing to death. The system achieved an accuracy of 80%, with Area Under Receiver Operating Characteristic Curve (AUC) of 91%, Positive Predictive Value of 87% and Negative Predictive Value of 82%. Considering that only data from hospital admission was used, and that this data came from low-cost clinical examination and laboratory testing, the low false positive rate and acceptable accuracy observed shows that it is feasible to implement prediction systems based on artificial intelligence as an effective triage method.<\/jats:p>","DOI":"10.3389\/frai.2024.1495074","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T06:46:25Z","timestamp":1734504385000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Artificial intelligence in triage of COVID-19 patients"],"prefix":"10.3389","volume":"7","author":[{"given":"Yuri","family":"Oliveira","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"I\u00eada","family":"Rios","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paula","family":"Ara\u00fajo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alinne","family":"Macambira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcos","family":"Guimar\u00e3es","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"L\u00facia","family":"Sales","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcos","family":"Rosa J\u00fanior","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andr\u00e9","family":"Nicola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mauro","family":"Nakayama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hermeto","family":"Paschoalick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francisco","family":"Nascimento","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos","family":"Castillo-Salgado","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vania Moraes","family":"Ferreira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hervaldo","family":"Carvalho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,12,18]]},"reference":[{"key":"ref1","author":"Abadi","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"11943","DOI":"10.1007\/s11042-020-10340-7","article-title":"Predicting the COVID-19 infection with fourteen clinical features using machine learning classification algorithms","volume":"80","author":"Arpaci","year":"2021","journal-title":"Multimed. Tools Appl."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s10916-020-01597-4","article-title":"Detection of COVID-19 infection from routine blood exams with machine learning: a feasibility study","volume":"44","author":"Brinati","year":"2020","journal-title":"J. Med. Syst."},{"key":"ref4","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Buitinck","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2315","DOI":"10.1007\/s00431-021-03995-3","article-title":"Doctors\u2019 shortage in adults COVID-19 units: a call for pediatricians","volume":"180","author":"Buonsenso","year":"2021","journal-title":"Eur. J. Pediatr."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1081\/JA-120004171","article-title":"A brief overview and introduction to artificial neural networks","volume":"37","author":"Buscema","year":"2002","journal-title":"Subst. Use Misuse"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"12493","DOI":"10.18632\/aging.103579","article-title":"Epidemiological, comorbidity factors with severity and prognosis of COVID-19: a systematic review and meta-analysis","volume":"12","author":"Fang","year":"2020","journal-title":"Aging"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"3343","DOI":"10.1038\/s41598-021-82885-y","article-title":"A multipurpose machine learning approach to predict COVID-19 negative prognosis in S\u00e3o Paulo, Brazil","volume":"11","author":"Fernandes","year":"2021","journal-title":"Sci. Rep."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1097\/MEG.0b013e3282f198a0","article-title":"Introduction to artificial neural networks","volume":"19","author":"Grossi","year":"2007","journal-title":"Eur. J. Gastroenterol. Hepatol."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12553-018-0244-4","article-title":"Artificial neural networks in medicine","volume":"9","author":"Haglin","year":"2019","journal-title":"Health Technol."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1093\/jamia\/ocac062","article-title":"Development and validation of predictive models for COVID-19 outcomes in a safety-net hospital population","volume":"29","author":"Hao","year":"2022","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"4200","DOI":"10.1038\/s41598-021-83784-y","article-title":"Early risk assessment for COVID-19 patients from emergency department data using machine learning","volume":"11","author":"Heldt","year":"2021","journal-title":"Sci. Rep."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1001\/virtualmentor.2006.8.1.cprl1-0601","article-title":"What makes a screening exam \u201cgood\u201d? Ethics","volume":"8","author":"Herman","year":"2006","journal-title":"JAMA J. Am. Med. Assoc."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/RBME.2022.3216531","article-title":"Systematic review of advanced AI methods for improving healthcare data quality in post COVID-19 era","volume":"16","author":"Isgut","year":"2023","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"3246","DOI":"10.1038\/s41598-021-81844-x","article-title":"Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients","volume":"11","author":"Jimenez-Solem","year":"2021","journal-title":"Sci. Rep."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"e50212","DOI":"10.7759\/cureus.50212","article-title":"Machine learning-based prediction of COVID-19 prognosis using clinical and hematologic data","volume":"15","author":"Kamel","year":"2023","journal-title":"Cureus"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1405","DOI":"10.1007\/s12630-020-01713-5","article-title":"Therapeutic alternatives and strategies for drug conservation in the intensive care unit during times of drug shortage: a report of the Ontario COVID-19 ICU drug task force","volume":"67","author":"Kanji","year":"2020","journal-title":"Can. J. Anesth."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/jpm12091522","article-title":"Prediction models for COVID-19 mortality using artificial intelligence","volume":"12","author":"Kim","year":"2022","journal-title":"J. Pers. Med."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"2235","DOI":"10.1007\/s12525-022-00598-0","article-title":"Artificial intelligence and machine learning","volume":"32","author":"K\u00fchl","year":"2022","journal-title":"Electron. Mark."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1186\/s12931-023-02386-6","article-title":"An artificial intelligence approach for predicting death or organ failure after hospitalization for COVID-19: development of a novel risk prediction tool and comparisons with ISARIC-4C, CURB-65, qSOFA, and MEWS scoring systems","volume":"24","author":"Kwok","year":"2023","journal-title":"Respir. Res."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1111\/jebm.12483","article-title":"Clinical manifestations of COVID-19: an overview of 102 systematic reviews with evidence mapping","volume":"15","author":"Luo","year":"2022","journal-title":"J. Evid. Based Med."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"84","DOI":"10.21315\/mjms2023.30.3.7","article-title":"Risk factors associated with the severity of COVID-19. Malaysian","volume":"30","author":"Martono","year":"2023","journal-title":"J. Med. Sci."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1017\/ice.2020.162","article-title":"Borderless collaboration is needed for COVID-19\u2014a disease that knows no borders","volume":"41","author":"Mohamed","year":"2020","journal-title":"Infect. Control Hosp. Epidemiol."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1336","DOI":"10.1002\/jmv.27487","article-title":"COVID-19 vaccinations: the unknowns, challenges, and hopes","volume":"94","author":"Mohamed","year":"2022","journal-title":"J. Med. Virol."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/bib\/bbab456","article-title":"Impact of computational approaches in the fight against COVID-19: an AI guided review of 17 000 studies","volume":"23","author":"Napolitano","year":"2022","journal-title":"Brief. Bioinform."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"e175","DOI":"10.1017\/S095026882000179X","article-title":"Risk factors of severe cases with COVID-19: a Meta-analysis","volume":"148","author":"Ou","year":"2020","journal-title":"Epidemiol. Infect."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"716","DOI":"10.14569\/IJACSA.2023.0140478","article-title":"Integrating dropout regularization technique at different layers to improve the performance of neural networks","volume":"14","author":"Pansambal","year":"2023","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref28","first-page":"1","volume-title":"COVID-19 An\u00e1lise da distribui\u00e7\u00e3o espacial de Tom\u00f3grafos no Brasil em tempos de pandemia","author":"Pereira","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3421725","article-title":"A multimodal, multimedia point-of-care deep learning framework for COVID-19 diagnosis","volume":"17","author":"Rahman","year":"2021","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"912099","DOI":"10.3389\/fpubh.2022.912099","article-title":"Individual factors associated with COVID-19 infection: a machine learning study","volume":"10","author":"Ram\u00edrez-Del Real","year":"2022","journal-title":"Front. Public Health"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1002\/1097-0045(200101)46:1<39::AID-PROS1006>3.0.CO;2-M","article-title":"Introduction to artificial neural networks for physicians: taking the lid off the black box","volume":"46","author":"Rodvold","year":"2001","journal-title":"Prostate"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/electronics12143106","article-title":"A review on dropout regularization approaches for deep neural networks within the scholarly domain","volume":"12","author":"Salehin","year":"2023","journal-title":"Electronics"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1177\/00333549221091781","article-title":"Emergency department and intensive care unit overcrowding and ventilator shortages in US hospitals during the COVID-19 pandemic, 2020-2021","volume":"137","author":"Sandhu","year":"2022","journal-title":"Public Health Rep."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fpubh.2023.1183725","article-title":"Artificial intelligence-driven prediction of COVID-19-related hospitalization and death: a systematic review. Front","volume":"11","author":"Shakibfar","year":"2023","journal-title":"Public Health"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1186\/s12911-022-02016-z","article-title":"Monte Carlo cross-validation for a study with binary outcome and limited sample size","volume":"22","author":"Shan","year":"2022","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1177\/00207314221122658","article-title":"Covid-19 outbreak in Brazil: health, social, political, and economic implications","volume":"52","author":"Sott","year":"2022","journal-title":"Int. J. Health Serv."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"2149","DOI":"10.1038\/s41598-023-50564-9","article-title":"Derivation and validation of novel integrated inpatient mortality prediction score for COVID-19 (IMPACT) using clinical, laboratory, and AI\u2014processed radiological parameter upon admission: a multicentre study","volume":"14","author":"Tenda","year":"2024","journal-title":"Sci. Rep."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3516367","article-title":"Self-supervised transformer for sparse and irregularly sampled multivariate clinical time-series","volume":"16","author":"Tipirneni","year":"2022","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fpubh.2017.00307","article-title":"Sensitivity, specificity, and predictive values: foundations, Pliabilities, and pitfalls in research and practice","volume":"5","author":"Trevethan","year":"2017","journal-title":"Front. Public Health"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1186\/s12911-019-1004-8","article-title":"Comparing different supervised machine learning algorithms for disease prediction","volume":"19","author":"Uddin","year":"2019","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fmed.2021.704256","article-title":"Artificial intelligence for COVID-19: a systematic review","volume":"8","author":"Wang","year":"2021","journal-title":"Front. Med."},{"key":"ref42","article-title":"WHO coronavirus (COVID-19) dashboard","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"2215","DOI":"10.1111\/jan.14409","article-title":"Preventing the dysfunction of public health centres responding to COVID-19 by focusing on public health nurses in Japan","volume":"76","author":"Yoshioka-Maeda","year":"2020","journal-title":"J. Adv. Nurs."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fmicb.2021.729455","article-title":"Artificial intelligence Systems for Diagnosis and Clinical Classification of COVID-19","volume":"12","author":"Yu","year":"2021","journal-title":"Front. Microbiol."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1495074\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T06:46:28Z","timestamp":1734504388000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1495074\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,18]]},"references-count":44,"alternative-id":["10.3389\/frai.2024.1495074"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1495074","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,18]]},"article-number":"1495074"}}