An NIH-funded study used deep learning to analyze thrice-daily smartphone surveys from 62 patients in opioid addiction treatment, accurately forecasting relapse risk hours to days in advance, though researchers caution the small, non-diverse sample needs broader validation.
An AI tool embedded in Epic at NewYork-Presbyterian and Weill Cornell Medicine flags pregnant patients at risk for postpartum depression during routine prenatal visits, part of a wider 2026 research push toward predicting the condition before it starts.
A new Harvard-developed AI model called popEVE has flagged 123 previously unknown disease genes in a cohort of 30,000 undiagnosed patients, with 25 already confirmed by independent labs, offering a new path through the years-long diagnostic odyssey many rare disease families face.
Whoop is adding on-demand video visits with licensed clinicians alongside new AI coaching features that let its algorithm remember a user's real-life context, a move that pits it directly against rival Oura's new AI health assistant.
University of Houston researchers had older adults sculpt their ideal AI companion robot out of clay, surfacing a finding that could reshape the industry: seniors want practical help, not surveillance dressed up as companionship.
Slingshot AI pulled its heavily funded therapy chatbot Ash out of the United Kingdom over unresolved medical device regulations, a retreat that exposes how unsettled the rules remain for AI mental health tools worldwide.
Aidoc's First Read, an AI tool that drafts full chest X-ray radiology reports rather than just flagging abnormalities, received FDA Breakthrough Device Designation, signaling a new regulatory path for generative AI in imaging.
Roche agreed to acquire digital pathology firm PathAI for up to $1.05 billion, aiming to fuse AI-based tissue slide analysis with its oncology companion diagnostics to speed and sharpen cancer treatment matching.
Atlanta startup CheckWellCall has soft-launched an AI-powered daily wellness check-in call for seniors, automating structured voice conversations that flag deviations from a resident's baseline for family caregivers or senior living staff to follow up on.
A Nature Communications study published August 12, 2026 by Dana-Farber and Mass General Brigham researchers found that genomic screening of newborn blood spots could flag childhood cancer risk years before diagnosis, with AI-driven variant analysis making population-scale screening feasible.