Machine Learning for Patient Risk Stratification for ARDS
ncbi.nlm.nih.gov
An acute respiratory distress syndrome (ARDS) prediction model based on electronic health record (EHR) data with good discriminative performance has been developed.
The results demonstrate the feasibility of a machine learning approach to risk stratifying patients for ARDS solely from data extracted automatically from the EHR.
A risk stratification model was trained for ARDS using a cohort of 1,621 patients with moderate hypoxia from a single center in 2016, of which 51 patients developed ARDS.
The model in a temporally distinct cohort of 1,122 patients from 2017, of which 27 patients developed ARDS was tested.
Gold standard diagnosis of ARDS was made by intensive care trained physicians during retrospective chart review.
Related Stories
Related Books
