Development and evaluation of a machine learning-based in-hospital COVID-19 disease outcome predictor (CODOP): A multicontinental retrospective study

: Klen Riku, Purohit Disha, Gomez-Huelgas Ricardo, Casas-Rojo Jose Manuel, Anton-Santos Juan Miguel, Nunez-Cortes Jesus Millan, Lumbreras Carlos, Ramos-Rincon Jose Manuel, Garcia Barrio Noelia, Pedrera-Jimenez Miguel, Lalueza Blanco Antonio, Martin-Escalante Maria Dolores, Rivas-Ruiz Francisco, Onieva-Garcia Maria angeles, Young Pablo, Ramirez Juan Ignacio, Titto Omonte Estela Edith, Gross Artega Rosmery, Canales Beltran Magdy Teresa, Valdez Pascual Ruben, Pugliese Florencia, Castagna Rosa, Huespe Ivan A., Boietti Bruno, Pollan Javier A., Funke Nico, Leiding Benjamin, Gomez-Varela David

Publisher: eLIFE SCIENCES PUBL LTD

: 2022

: eLife

: ELIFE

: e75985

: 11

: 15

: 2050-084X

DOI: https://doi.org/10.7554/eLife.75985

: https://doi.org/10.7554/eLife.75985

: https://research.utu.fi/converis/portal/detail/Publication/175858188

New SARS-CoV-2 variants, breakthrough infections, waning immunity, and sub-optimal vaccination rates account for surges of hospitalizations and deaths. There is an urgent need for clinically valuable and generalizable triage tools assisting the allocation of hospital resources, particularly in resource-limited countries. We developed and validate CODOP, a machine learning-based tool for predicting the clinical outcome of hospitalized COVID-19 patients. CODOP was trained, tested and validated with six cohorts encompassing 29223 COVID-19 patients from more than 150 hospitals in Spain, the USA and Latin America during 2020-22. CODOP uses 12 clinical parameters commonly measured at hospital admission for reaching high discriminative ability up to 9 days before clinical resolution (AUROC: 0.90-0.96), it is well calibrated, and it enables an effective dynamic risk stratification during hospitalization. Furthermore, CODOP maintains its predictive ability independently of the virus variant and the vaccination status. To reckon with the fluctuating pressure levels in hospitals during the pandemic, we offer two online CODOP calculators, suited for undertriage or overtriage scenarios, validated with a cohort of patients from 42 hospitals in three Latin American countries (78-100% sensitivity and 89-97% specificity). The performance of CODOP in heterogeneous and geographically disperse patient cohorts and the easiness of use strongly suggest its clinical utility, particularly in resource-limited countries.

elife-75985-v2.pdf