Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study

• Published in: Annals of medicine (Helsinki) Vol. 53; no. 1; pp. 257 - 266
• Main Authors: Guan, Xin, Zhang, Bo, Fu, Ming, Li, Mengying, Yuan, Xu, Zhu, Yaowu, Peng, Jing, Guo, Huan, Lu, Yanjun
• Format: Journal Article
• Language: English
• Published: England Taylor & Francis 2021; Taylor & Francis Group
• Subjects: Adult; Aged; Aged, 80 and over; C-Reactive Protein - metabolism; Cardiovascular Diseases - epidemiology; China - epidemiology; Clinical Decision Rules; Cohort Studies; Comorbidity; COVID-19; COVID-19 - epidemiology; COVID-19 - metabolism; COVID-19 - mortality; COVID-19 - physiopathology; Diabetes Mellitus - epidemiology; extreme gradient boosting; fatal risk; Female; Ferritins - metabolism; Hospitalization; Humans; Hypertension - epidemiology; Immunology; Interleukin-10 - metabolism; L-Lactate Dehydrogenase - metabolism; Machine Learning; Male; Middle Aged; Prognosis; Reproducibility of Results; Retrospective Studies; SARS-CoV-2; Severity of Illness Index; China; COVID-19; extreme gradient boosting; fatal risk; machine learning

To appraise effective predictors for COVID-19 mortality in a retrospective cohort study. A total of 1270 COVID-19 patients, including 984 admitted in Sino French New City Branch (training and internal validation sets randomly split at 7:3 ratio) and 286 admitted in Optical Valley Branch (external va...