The hidden ingredients in medical artificial intelligence
Healthcare providers are deploying algorithms without knowing what data trained them, creating a massive regulatory and clinical liability.
AI predicts future lab results from patient records
A new transformer model can simulate how a patient's lab values will react to specific drugs before they are even prescribed.
Medicare AI Payments Risk Driving Costly Overuse
Medicare's plan to pay hospitals for using AI tools risks creating a financial incentive to overdiagnose patients.
AI insulin resistance index predicts heart disease risk
A new deep learning index predicts cardiovascular death by tracking insulin resistance in the general public, moving metabolic screening beyond diabetic patients.
Turning Bedside Chats Into Patient Task Lists
Ambient AI is moving past physician burnout to tackle the chaotic reality of patient discharge.
AI Outperforms Pathologists in Ordering Lymphoma Tests
A new AI system can predict lymphoma subtypes and order diagnostic tests directly from initial biopsy scans, cutting down the days patients spend waiting for a diagnosis.
Oracle Puts OpenAI in Patient Portals
Giving patients direct access to AI-translated medical records is a bold play to win the EHR wars, but it shifts a massive cognitive burden from doctors to software.
Skin lesion AI misses its uncertainty targets
A new benchmark reveals that even calibrated image-recognition models struggle to safely hand off difficult skin cancer cases to human specialists.
Selling Autopilot to a Broken Healthcare System
Silicon Valley is betting billions that AI agents can run clinical workflows without human intervention, but the messy reality of hospital operations is pushing back.
Wearables and AI predict knee osteoarthritis pain
A new machine learning model proves that how we walk, rather than how much we walk, reveals the true severity of arthritic joint pain.