Development and Transportability Assessment of a Parsimonious Machine Learning Model for Predicting In-Hospital Mortality in ICU Patients with Cirrhosis and Sepsis: A MIMIC-IV and Chinese Cohort Study
This study develops and validates an interpretable, parsimonious machine learning model using early ICU data to predict in-hospital mortality in patients with cirrhosis and sepsis, demonstrating its effectiveness and transportability across both MIMIC-IV and Chinese cohorts.