Turning Failed Clinical Trials Into AI Models
Biotech companies are finding a second life for failed drug data, but recycling bad trials into predictive algorithms carries hidden risks.
AI reconstructs baby heart signals without skin damage
A new AI model reconstructs missing neonatal heart signals using light-based sensors, bypassing the need for irritating skin adhesives in intensive care.
Federal Health Agencies Are Rushing Into AI
Federal health agencies are rapidly adopting artificial intelligence, but their rush to deploy these tools is outpacing their willingness to govern them.
AI tackles the prostate MRI bottleneck
Doubling scanning capacity is useless if there are no radiologists left to read the scans.
Automated Disease Activity Assessment in Systemic Lupus Erythematosus Using Privacy-Preserving Large Language Models
Automating lupus tracking with open-source language models could finally bring standardized disease monitoring to busy clinics.
AI Exposes Hidden Veteran Self-Harm Data
Electronic health records are failing vulnerable patients because standard billing codes ignore the messy reality of clinical notes.
LLMs Fail Local Speech in Nigerian Clinical Test
A new clinical benchmark reveals that large language models fail frontline health workers unless their queries are translated into English first.
AI discharge summaries target doctor burnout
A new pilot shows that automating clinical notes saves little time but dramatically lowers cognitive fatigue.
Matching blood by DNA, not just type
A mismatch between the genetic makeup of blood donors and recipients is driving a silent crisis in sickle cell care.
AI agent runs biomedical research tasks autonomously
A new AI agent named Biomni can design and run its own lab experiments, shifting the bottleneck of medical discovery from human labor to machine execution.