Machine learning models predict long COVID outcomes based on baseline clinical and immunologic factors.
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Doni Jayavelu Naresh, Samaha Hady, Wimalasena Sonia Tandon, Hoch Annmarie, Gygi Jeremy P, Gabernet Gisela, Ozonoff Al, Liu Shanshan, Milliren Carly E, Levy Ofer, Baden Lindsey R, Melamed Esther, Ehrlich Lauren I R, McComsey Grace A, Sekaly Rafick P, Cairns Charles B, Haddad Elias K, Schaenman Joanna, Shaw Albert C, Hafler David A, Montgomery Ruth R, Corry David B, Kheradmand Farrah, Atkinson Mark A, Brakenridge Scott C, Agudelo Higuit Nelson I, Metcalf Jordan P, Hough Catherine L, Messer William B, Pulendran Bali, Nadeau Kari C, Davis Mark M, Geng Linda N, Fernandez Sesma Ana, Simon Viviana, Krammer Florian, Kraft Monica, Bime Chris, Calfee Carolyn S, Erle David J, Langelier Charles R, IMPACC Network, Guan Leying, Maecker Holden T, Peters Bjoern, Kleinstein Steven H, Reed Elaine F, Augustine Alison D, Diray-Arce Joann, Becker Patrice M, Rouphael Nadine, Altman Matthew C
Аннотация
METHODS: Clinical data, including antibody titers and viral load measurements collected at the time of hospital admission, are used to predict the likelihood of acute COVID-19 progressing to long COVID. Machine learning models are trained and evaluated for predictive performance. Feature importance analysis is performed to identify the most influential predictors.
RESULTS: The machine learning models achieve median AUROC values ranging from 0.64 to 0.66 and AUPRC values between 0.51 and 0.54, demonstrating predictive capabilities. Low antibody titers and high viral loads at hospital admission emerge as the strongest predictors of long COVID outcomes. Comorbidities-such as chronic respiratory, cardiac, and neurologic diseases-and female sex are also identified as significant risk factors.
CONCLUSIONS: Machine learning models identify patients at risk for developing long COVID based on baseline clinical characteristics. These models guide early interventions, improve patient outcomes, and mitigate the long-term public health impacts of SARS-CoV-2.