A new foundation model called UniBiomed simultaneously interprets biomedical images and segments corresponding regions, eliminating the need for separate diagnostic and localization steps.

Researchers have successfully deployed a smartphone-based AI system that screens for ocular surface malignancies in the general population, detecting tumors that would otherwise go undiagnosed until advanced stages.

An AI model accurately predicts which advanced rectal cancer patients achieve complete treatment response, potentially allowing them to avoid surgery through watch-and-wait management.

DSimSynergy combines graph deep learning with drug and biological data to predict effective cancer drug combinations.

In GI medicine, AI is moving deeper: real-time procedural guidance, specialty-specific systems, outcome prediction. The trend shows AI shifting from post-hoc analysis to embedded decision support across the…

A landmark randomized controlled trial demonstrates that electroacupuncture provides clinically meaningful symptom relief in knee osteoarthritis, with exploratory evidence suggesting potential anti-inflammatory and cartilage-protective effects.

Familiar names may unlock a window into the brains of comatose patients. A new study shows EEG responses to patients' own names can reliably predict recovery outcomes in…

HOPE, a transformer-based AI model, predicts hyperprogressive disease risk in advanced liver cancer patients on PD-1 inhibitors by combining CT imaging with clinical factors.

A mixed-methods study of 930 Chinese medical students reveals significant GenAI dependence linked to reduced critical thinking, raising urgent questions about responsible integration in medical education.

A systematic review of large language models in clinical practice finds promising early results but reveals alarming gaps in evidence quality and reporting standards that must be addressed…