Researchers have developed and validated a machine learning tool to predict 28-day mortality in ICU patients with sepsis and acute respiratory failure using early clinical data.
Key Details
- 1Machine learning model predicts 28-day mortality risk for ICU patients with sepsis complicated by acute respiratory failure.
- 2Routinely collected clinical data from the first 24 hours of ICU admission were used as input.
- 3Model was trained using MIMIC-IV (v3.1) and externally validated on eICU-CRD (v2.0) databases.
- 4XGBoost outperformed other algorithms in mortality risk discrimination and generalizability.
- 5Model focused on interpretability using SHapley Additive exPlanations (SHAP) to highlight key clinical predictors.
- 6Study published in Journal of Intensive Medicine on January 10, 2026 (DOI: 10.1016/j.jointm.2025.10.010).
Why It Matters
This development demonstrates how interpretable AI can support early clinical risk stratification, guiding resource allocation and treatment in critical care settings. Such models, leveraging large clinical datasets and interpretability tools, are key for integrating AI decision support into real-world healthcare.
Source
EurekAlert
Related News
•EurekAlert
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
Duke Receives $25M to Lead National Trustworthy AI Hub for Dementia and Aging
Duke University has launched a $25 million national center to make AI for aging and dementia clinically robust and trustworthy.