A new Chalmers University AI model dramatically speeds up molecular dynamics simulations central to drug discovery, part of a broader 2026 push by pharma companies to pool structural data and train shared AI models like OpenFold3.
A device-agnostic AI platform unveiled at THT 2026 in Boston converts data from ordinary consumer wearables into early warnings for heart failure patients, reportedly cutting hospitalizations through earlier intervention.
Texas A&M and USC researchers are separately developing AI models that map Alzheimer's disease progression with far more precision than current diagnostics, potentially widening the window for early treatment.
Full results from the Swedish MASAI trial, involving over 105,000 women, show AI-supported mammography screening cut interval breast cancers by 12% and invasive interval cancers by 16% compared with standard double reading.
Apple has scaled back its planned standalone AI health coaching service, opting to roll out features gradually within its free Health app instead, even as rival Google launches a paid AI Health Coach.
A new AI foundation model trained on 1.6 million continuous glucose monitor readings cut one-hour glucose forecasting error nearly in half, promising more reliable diabetes management tools.
The FDA cleared Alife Health's Embryo Predict, the first AI embryo assessment tool for IVF backed by a 440-patient randomized clinical trial across seven U.S. fertility clinics.
A new AI algorithm called EvORanker compares genetic evolutionary patterns across 1,000 species to identify hidden gene-disease links, helping crack a previously unsolved rare disease case.
A Boston Children's Hospital and OpenAI study used an AI reasoning model to re-analyze 376 unsolved pediatric rare disease cases, helping physicians confirm 18 new diagnoses.
Kaiser Permanente's ambient AI scribes handled 2.5 million patient visits and saved doctors nearly 15,800 hours of documentation time, with 84% of clinicians reporting improved patient communication.