FDA Accepts AI Model for Liver Toxicity
The regulatory bottleneck for AI in drug development is finally beginning to crack.
Silent Manipulation of Mental Health Treatment Recommendations from a Large Language Model
A new study reveals how bad actors can quietly steer an AI's medical advice without changing its code or prompts.
AI designs new antibiotic for drug-resistant infections
Generative AI just bypassed decades of traditional chemistry to design a viable antibiotic from scratch, but the real test lies in the clinical pipeline.
Wearable ECG AI fails older patients
Smartwatches and rings are marketed as lifesaving heart monitors, but new data shows their single-lead AI systems fail the very patients who need them most.
Hackers steal recipes for blockbuster weight-loss drugs
A massive data breach at Novo Nordisk reveals that the real value of modern pharma is no longer just the chemical formula, but the digital infrastructure behind it.
AI detects autoimmune hepatitis from liver slides
A new deep-learning model diagnoses autoimmune hepatitis with expert-level accuracy in some scenarios, but its failure against hepatitis B reveals a critical diagnostic blind spot.
AI spots pancreatic cancer years before doctors
A new AI model can detect lethal pancreatic tumors up to three years before they show up on standard medical scans.
AI Survival Models Fail to Beat 1995 Formula
A new reanalysis reveals that highly praised machine learning survival models underperform both human doctors and a thirty-year-old statistical formula at predicting patient death at critical clinical milestones.