{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T13:53:30Z","timestamp":1781272410831,"version":"3.54.1"},"posted":{"date-parts":[[2025,2,13]]},"group-title":"Health Informatics","reference-count":34,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T00:00:00Z","timestamp":1739404800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,2,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>The post-acute sequelae of SARS-CoV-2 (PASC), also known as long COVID, remain a significant health issue that is incompletely understood. Predicting which acutely infected individuals will go on to develop long COVID is challenging due to the lack of established biomarkers, clear disease mechanisms, or well-defined sub-phenotypes. Machine learning (ML) models offer the potential to address this by leveraging clinical data to enhance diagnostic precision. We utilized clinical data, including antibody titers and viral load measurements collected at the time of hospital admission, to predict the likelihood of acute COVID-19 progressing to long COVID. Our machine learning models achieved median AUROC values ranging from 0.64 to 0.66 and AUPRC values between 0.51 and 0.54, demonstrating their predictive capabilities. Feature importance analysis revealed that low antibody titers and high viral loads at hospital admission were the strongest predictors of long COVID outcomes. Comorbidities, including chronic respiratory, cardiac, and neurologic diseases, as well as female sex, were also identified as significant risk factors for long COVID. Our findings suggest that ML models have the potential to identify patients at risk for developing long COVID based on baseline clinical characteristics. These models can help guide early interventions, improving patient outcomes and mitigating the long-term public health impacts of SARS-CoV-2.<\/jats:p>","DOI":"10.1101\/2025.02.12.25322164","type":"posted-content","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T16:45:14Z","timestamp":1739465114000},"source":"Crossref","is-referenced-by-count":3,"title":["Machine learning models predict long COVID outcomes based on baseline clinical and immunologic factors"],"prefix":"10.64898","author":[{"given":"Naresh Doni","family":"Jayavelu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hady","family":"Samaha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sonia Tandon","family":"Wimalasena","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annmarie","family":"Hoch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeremy P","family":"Gygi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gisela","family":"Gabernet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Al","family":"Ozonoff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carly E.","family":"Milliren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ofer","family":"Levy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lindsey R.","family":"Baden","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esther","family":"Melamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lauren I. R.","family":"Ehrlich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Grace A.","family":"McComsey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rafick P.","family":"Sekaly","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles B.","family":"Cairns","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elias K.","family":"Haddad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joanna","family":"Schaenman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Albert C.","family":"Shaw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David A.","family":"Hafler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruth R.","family":"Montgomery","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David B.","family":"Corry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farrah","family":"Kheradmand","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark A.","family":"Atkinson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott C.","family":"Brakenridge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nelson I Agudelo","family":"Higuita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordan P.","family":"Metcalf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catherine L.","family":"Hough","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William B.","family":"Messer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bali","family":"Pulendran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kari C.","family":"Nadeau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark M.","family":"Davis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linda N.","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ana Fernandez","family":"Sesma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viviana","family":"Simon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Krammer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Monica","family":"Kraft","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Bime","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carolyn S.","family":"Calfee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David J.","family":"Erle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles R.","family":"Langelier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"IMPACC Network","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leying","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Holden T.","family":"Maecker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bjoern","family":"Peters","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven H.","family":"Kleinstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elaine F.","family":"Reed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joann","family":"Diray-Arce","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nadine","family":"Rouphael","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew C.","family":"Altman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025031301212752000_2025.02.12.25322164v1.1","unstructured":"Website n.d. https:\/\/www.cdc.gov\/coronavirus\/2019-ncov\/long-term-effects\/index.html."},{"key":"2025031301212752000_2025.02.12.25322164v1.2","unstructured":"National Center for Health Statistics. U.S. Census Bureau HPS, 2022\u2013. Long COVID n.d."},{"key":"2025031301212752000_2025.02.12.25322164v1.3","unstructured":"Office for National Statistics. Prevalence of ongoing symptoms following coronavirus (COVID-19) infection in the UK n.d."},{"key":"2025031301212752000_2025.02.12.25322164v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01292-y"},{"key":"2025031301212752000_2025.02.12.25322164v1.5","doi-asserted-by":"crossref","unstructured":"Antony B , Blau H , Casiraghi E , Loomba JJ , Callahan TJ , Laraway BJ , et al. Predictive models of long COVID. EBioMedicine 2023;96:104777.","DOI":"10.1016\/j.ebiom.2023.104777"},{"key":"2025031301212752000_2025.02.12.25322164v1.6","doi-asserted-by":"crossref","first-page":"e532","DOI":"10.1016\/S2589-7500(22)00048-6","article-title":"Identifying who has long COVID in the USA: a machine learning approach using N3C data","volume":"4","year":"2022","journal-title":"Lancet Digit Health"},{"key":"2025031301212752000_2025.02.12.25322164v1.7","doi-asserted-by":"crossref","unstructured":"Ozonoff A , Jayavelu ND , Liu S , Melamed E , Milliren CE , Qi J , et al. Features of acute COVID-19 associated with post-acute sequelae of SARS-CoV-2 phenotypes: results from the IMPACC study. Nat Commun 2024;15:216.","DOI":"10.1038\/s41467-023-44090-5"},{"key":"2025031301212752000_2025.02.12.25322164v1.8","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01283-z"},{"key":"2025031301212752000_2025.02.12.25322164v1.9","doi-asserted-by":"crossref","first-page":"e235779","DOI":"10.1001\/jamanetworkopen.2023.5779","article-title":"Toward a Universal Definition of Post-COVID-19 Condition-How Do We Proceed?","volume":"6","year":"2023","journal-title":"JAMA Netw Open"},{"key":"2025031301212752000_2025.02.12.25322164v1.10","doi-asserted-by":"crossref","first-page":"103722","DOI":"10.1016\/j.ebiom.2021.103722","article-title":"Characterizing Long COVID: Deep Phenotype of a Complex Condition","volume":"74","year":"2021","journal-title":"EBioMedicine"},{"key":"2025031301212752000_2025.02.12.25322164v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-19057-5"},{"key":"2025031301212752000_2025.02.12.25322164v1.12","first-page":"132","article-title":"SARS-CoV-2 (COVID-19), viral load and clinical outcomes; lessons learned one year into the pandemic: A systematic review","volume":"10","year":"2021","journal-title":"Pediatr Crit Care Med"},{"key":"2025031301212752000_2025.02.12.25322164v1.13","doi-asserted-by":"crossref","first-page":"e70","DOI":"10.1016\/S2213-2600(20)30354-4","article-title":"SARS-CoV-2 viral load predicts COVID-19 mortality","volume":"8","year":"2020","journal-title":"Lancet Respir Med"},{"key":"2025031301212752000_2025.02.12.25322164v1.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2022.01.014"},{"key":"2025031301212752000_2025.02.12.25322164v1.15","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph192215145"},{"key":"2025031301212752000_2025.02.12.25322164v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/nm0696-625"},{"key":"2025031301212752000_2025.02.12.25322164v1.17","doi-asserted-by":"publisher","DOI":"10.1086\/514001"},{"key":"2025031301212752000_2025.02.12.25322164v1.18","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1001\/jamainternmed.2023.0750","article-title":"Risk Factors Associated With Post-COVID-19 Condition: A Systematic Review and Meta-analysis","volume":"183","year":"2023","journal-title":"JAMA Intern Med"},{"key":"2025031301212752000_2025.02.12.25322164v1.19","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0240784"},{"key":"2025031301212752000_2025.02.12.25322164v1.20","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.ijid.2022.03.006","article-title":"Number of initial symptoms is more related to long COVID-19 than acute severity of infection: a prospective cohort of hospitalized patients","volume":"118","year":"2022","journal-title":"Int J Infect Dis"},{"key":"2025031301212752000_2025.02.12.25322164v1.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2007.11.008"},{"key":"2025031301212752000_2025.02.12.25322164v1.22","doi-asserted-by":"publisher","DOI":"10.1126\/sciimmunol.abf3733"},{"key":"2025031301212752000_2025.02.12.25322164v1.23","doi-asserted-by":"publisher","DOI":"10.1007\/S40258-017-0310-5"},{"key":"2025031301212752000_2025.02.12.25322164v1.24","doi-asserted-by":"publisher","DOI":"10.1007\/s11136-013-0452-3"},{"key":"2025031301212752000_2025.02.12.25322164v1.25","doi-asserted-by":"publisher","DOI":"10.1007\/s11136-011-9935-2"},{"key":"2025031301212752000_2025.02.12.25322164v1.26","doi-asserted-by":"publisher","DOI":"10.1007\/s11136-009-9496-9"},{"key":"2025031301212752000_2025.02.12.25322164v1.27","doi-asserted-by":"publisher","DOI":"10.1002\/pon.3522"},{"key":"2025031301212752000_2025.02.12.25322164v1.28","unstructured":"National Institutes of Health. Patient-Reported Oucomes Measurement Information System (PROMIS\u00ae) n.d."},{"key":"2025031301212752000_2025.02.12.25322164v1.29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jval.2010.06.001"},{"key":"2025031301212752000_2025.02.12.25322164v1.30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jval.2010.11.009"},{"key":"2025031301212752000_2025.02.12.25322164v1.31","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1007\/s11136-014-0818-1","article-title":"Correlation of PROMIS scales and clinical measures among chronic obstructive pulmonary disease patients with and without exacerbations","volume":"24","year":"2015","journal-title":"Qual Life Res"},{"key":"2025031301212752000_2025.02.12.25322164v1.32","unstructured":"PROMIS. Dyspnea Scoring Manual n.d."},{"key":"2025031301212752000_2025.02.12.25322164v1.33","unstructured":"Centers for Disease Control and Prevention. Research use only 2019-novel coronavirus (2019-nCoV) real-time RT-PCR primers and probes 2020."},{"key":"2025031301212752000_2025.02.12.25322164v1.34","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-0913-5"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.02.12.25322164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:28:05Z","timestamp":1768508885000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.02.12.25322164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,13]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1101\/2025.02.12.25322164","relation":{},"subject":[],"published":{"date-parts":[[2025,2,13]]},"subtype":"preprint"}}