Predicción precoz de la supervivencia en pacientes ingresados por COVID-19 con una aproximación integrada con variables ómicas

Abstract

Early identification of patients at high risk of COVID-19 mortality could improve their prognosis and optimize resource management in future pandemics. In this study, Big Data tools are used to integrate and analyze 4408 clinical, laboratory, microRNAs and metabolomic variables in a cohort of 95 patients. Through a four-stage cleaning process-which included dimensionality reduction with PCA, LASSO, ELASTICNET and MOFA-75 variables were selected to develop mortality prediction algorithms, subsequently validated in an independent group. The results demonstrated that a reduced set of molecular biomarkers, measured within the first 72 hours of hospitalization, accurately predicts the risk of death in patients with COVID-19. This multi-omics approach, facilitated by Big Data techniques, offers a promising tool for early clinical decision making.

Date of Award	Jul 2025
Original language	Spanish
Supervisor	Remo Suppi Boldrito (Director)