Grading the Algorithms That Guide Bedside Medicine
Clinical calculators dictate life-or-death medical decisions every day, but doctors have had no objective way to know which algorithms are actually safe to trust.
MedSafe-Dx (v0): A Safety-Focused Benchmark for Evaluating LLMs in Clinical Diagnostic Decision Support
A new benchmark reveals that today's best artificial intelligence models only look safe in the clinic because they constantly cry wolf.
Eli Lilly Bets on Oura Rings
Pharmaceutical giants are realizing that selling a weight-loss drug is only half the battle.
AI detects abnormal child growth years earlier
A new algorithm spots rare growth disorders years before traditional clinical methods, shifting the focus of pediatric screening from reactive tracking to active prediction.
AI Drug Discovery Targets the Factory Floor
A new joint venture is shifting AI's role from designing molecules to actually building them at scale.
AI synthetic patients successfully replace real trial controls
A new study shows AI-generated synthetic patients can replicate cancer trial results, potentially shrinking the need for human control groups.
Brain Implants Are Physically Rewiring Damaged Spines
A new brain-computer interface does more than bypass spinal cord injuries; it might actually help heal them.
Medical AI fails under dynamic safety tests
Medical AI models that ace static exams fall apart when an automated adversary starts asking hard questions.
Medicare Redefines How It Pays For AI
The federal government is finally dismantling the outdated reimbursement models that treated digital algorithms like physical MRI machines.
AI adapts genetic risk scores for diverse ancestries
A new deep learning tool bypasses the need for massive non-European genetic trials by adapting existing risk models to diverse populations.