The Health AI Brief — Week of July 27, 2026
Tempus AI Buys Personalis for $1.5 Billion
AI Exposes Hidden Self-Harm in Medical Records
Standard medical billing codes are failing to track patient crises, leaving healthcare systems blind to critical mental health risks.
Enhancing the golden hour: classification of traumatic brain injury, severity, and concomitant clinical phenotypes using prehospital continuous physiological data during air transport
By analyzing continuous vital signs in the air, machine learning can identify traumatic brain injuries before the helicopter even lands.
Candid Health Raises $120M for AI Billing
A massive funding round in healthcare administration reveals that investors are betting on automated billing engines to solve the industry's most expensive back-office headache.
AI predicts dirty margins before breast cancer surgery
A new ensemble AI model predicts positive surgical margins before breast-conserving surgery, but its performance drop in external testing highlights the ongoing struggle with clinical generalization.
IVF Clinics Turn to AI for Embryo Selection
A new clinical deployment in California is putting AI-driven embryo selection to its first real-world test.
Circulating protein profiling identifies prognostic biomarkers in amyotrophic lateral Sclerosis
Measuring a single protein has been the gold standard for tracking ALS, but a new multi-protein signature suggests we have been missing the bigger biological picture.
The Vulnerable Back Door of Medical Supply Chains
When a major medical supplier loses control of its patient databases, the failure rarely starts in its own server room.
AI predicts breast cancer spread to the brain
A new multi-center model uses basic clinical data to flag brain metastasis before symptoms appear, challenging the need for expensive, complex biomarkers.
Big Pharma Pools Data for Antibody AI
AI drug discovery models are starving for physical data, forcing fierce competitors to pool their proprietary secrets.