One retinal photo for risk stratification appeals to checkups and primary care — but patents and clinical limits must be clear so it isn't sold as fortune-telling.
AI NEWS
Health AI News
Chinese and English are the same day. This page lists every item, each with the original link, the author, and the engagement.
Latest day
November 3, 2026
5 items for 2026-11-03, ranked by combined engagement.
Top 3
Top journals airing AI-guided unproven treatment cases means hospital ethics and consent workflows must keep pace.
Pharma and device bosses should split budgets between discovery/design and clinical/compliance so slogans don’t set the pace.
All
Eric Topol: Nature BME publishes RetiME — retinal photos plus foundation models to estimate individual mortality risk and rebuild lifespan trajectories
One retinal photo for risk stratification appeals to checkups and primary care — but patents and clinical limits must be clear so it isn't sold as fortune-telling.
CollapseEric Topol: Nature BME publishes RetiME — retinal photos plus foundation models to estimate individual mortality risk and rebuild lifespan trajectories
Eric Topol highlights a Nov 2 Nature Biomedical Engineering paper introducing RetiME (Retinal Mortality Equivalent): low-cost, non-invasive retinal photos plus large foundation models map retinal features to individual mortality risk and reconstruct personalized lifespan trajectories tied to observed age at death. Trained on a European cohort and externally validated in three independent cohorts across Southeast Asia, Eurasia and North America, RetiME associated with all-cause and cause-specific mortality and predicted incidence of many systemic and ocular diseases. Trajectory clusters span cancer-predominant, cardiometabolic and neurodegenerative patterns. Authors note a provisional NUS patent; the paper says findings support further evaluation, not a replacement for comprehensive clinical assessment.
NEJM AI: multimodal molecular data plus an AI synthesis workflow guided therapy in an ambiguous adult medulloblastoma case
Top journals airing AI-guided unproven treatment cases means hospital ethics and consent workflows must keep pace.
CollapseNEJM AI: multimodal molecular data plus an AI synthesis workflow guided therapy in an ambiguous adult medulloblastoma case
NEJM AI describes a case where an AI-assisted molecular synthesis workflow integrating multimodal molecular data guided an as-yet unproven treatment decision in a diagnostically ambiguous adult sonic hedgehog–activated medulloblastoma. The post links out for detail and does not state efficacy endpoints in-tweet. It is a single-case report — extrapolation is risky, and “unproven treatment” itself signals limited evidence grade.
Bloomberg: Isomorphic Labs president says AI will be used to develop all medicines — only the speed is in question
Pharma and device bosses should split budgets between discovery/design and clinical/compliance so slogans don’t set the pace.
CollapseBloomberg: Isomorphic Labs president says AI will be used to develop all medicines — only the speed is in question
Bloomberg reports Isomorphic Labs president Max Jaderberg saying AI will be used to develop all medicines in the future — the only question is how quickly that arrives. The post is a headline blurb without pipeline or trial detail. Isomorphic is DeepMind’s drug-discovery arm; the remark reflects a top team’s view that AI pharma is shifting from assistive to default, while remaining a forward-looking claim rather than completed displacement.
U.S. rural study: 14 staff with no echo experience used real-time AI guidance for ~4,600 heart scans; 98% got all six views (preliminary conference findings)
Staff-short primary sites need human+AI guidance most — but acceptance still needs sonographer comparison, not view-completeness alone.
CollapseU.S. rural study: 14 staff with no echo experience used real-time AI guidance for ~4,600 heart scans; 98% got all six views (preliminary conference findings)
HealthAINav covers a U.S. rural health study: 14 nurses, nursing assistants and CT technologists with no prior echocardiography experience scanned 4,597 volunteers under real-time AI guidance, with remote specialists reviewing images. More than 99% of scans were adequate for core-lab measurements, median scan time was 9.5 minutes, 133 critical findings were flagged, and 98% captured all six required views. The author notes these were research scans without a direct comparison to qualified sonographers and without patient-outcome evaluation — preliminary conference findings. Engagement on the post is low; details follow the write-up.
HealthAINav on JAMA: Medicare’s AI-assisted prior-auth pilot saw ~15–19.5% drops in targeted services over six months (observational)
Utilization drops under AI prior auth ≠ quality gains; clinics should track delays and appeals, not only approval rates.
CollapseHealthAINav on JAMA: Medicare’s AI-assisted prior-auth pilot saw ~15–19.5% drops in targeted services over six months (observational)
HealthAINav summarizes a JAMA research letter on Medicare’s WISeR pilot in six states: prior auth was added for selected services and contractors may use AI to support reviews, while CMS says non-payment recommendations must come from licensed clinicians. Epidural steroid injections fell 15% and other targeted services 19.5% in the first six months. The author stresses this is observational utilization analysis — it may cut low-value care or reflect paperwork, delay or undertreatment — and does not prove better patient outcomes.