A study, released in August 2025 by BMC Pulmonary Medicine, discusses the development and external validation of a machine learning–based model to predict 30-day in-hospital mortality among ICU patients with asthma. Researchers used data from 4,385 patients in the Medical Information Mart for Intensive Care IV (MIMIC-IV) database to test seven algorithms. Compared with traditional ICU scoring systems, the model showed superior calibration and clinical benefits. The newly developed model offers strong performance, interpretability, and clinical utility, supporting its use for real-time risk stratification and decision-making in critical care settings.
Read the full journal article here.
Read the news article here.