Artificial intelligence can detect muscle loss (sarcopenia) in pediatric brain tumor patients using routine clinical MRI scans, identifying cases that traditional weight measurements miss.

BRIDGE predicts pathological complete response to neoadjuvant breast cancer therapy by analyzing intratumoral molecular subtype composition, outperforming existing clinical predictors.

A fully automated platform rapidly analyzes stroke lesions and predicts long-term cognitive outcomes, potentially transforming personalized acute stroke prognostication.

Standard 24-hour pH tests miss some clinically significant reflux cases. A machine learning framework identifies potential false negatives by analyzing subtle waveform patterns conventional metrics overlook.

An interpretable AI model predicts blood clot risk after endometrial cancer surgery with 82% accuracy, making machine learning decisions transparent to clinicians.

An expert-derived algorithm accurately classifies surgical complications from administrative billing codes, outperforming machine learning and enabling cost-effective, real-time quality surveillance.

New research demonstrates that large language models cannot reliably perform causal reasoning about HIV treatment, drug interactions, and side effects—raising serious safety concerns.

Machine learning models for osteosarcoma often fail when applied to different hospitals. A multi-registry approach dramatically improves their generalizability.

High triglycerides don't reliably predict who develops severe pancreatitis. A novel graph neural network called DeepLipiDecipher reveals why: it's not the quantity of lipids, but their chemical structure…

Researchers developed a deep learning model that predicts lobar-specific emphysema progression from baseline CT scans, significantly outperforming traditional clinical approaches.