medAI Times

Can a chatbot safely interview real patients before the doctor does? Google just tested it. Run time: 7:28 In today's episode: Google's AMIE chatbot interviews 100 real patients, Lancet reports KFF: Medicare-run Slack gave health-AI industry inside access FDA's 2027 agenda: finish AI lifecycle guidance, draft chatbot rules FOLLOW-UP: Utah's AI prescribing pilots may collide with FDA...

California just made it law: AI can advise your nurse, not replace them. Run time: 6:35 In today's episode: California law limits hospital AI to advice, not decisions RFK Jr. says AI beats any doctor as second opinion Synthetic Hospital fools physicians, stumps ten AI models Harrison.ai head CT tool tested on 3,424 ED scans Heidi II moves scribe AI into referrals and follow-ups Ultrasound-video AI...

Hospital A I added nearly a billion dollars in charges. Nobody got sicker. Run time: 7:28 In today's episode: Blue Cross: hospital AI added $942 million in charges VA picks Abridge for ambient AI, $775.7M ceiling Allina doctors win first contract after AI-fueled strike Anthropic, OpenEvidence give clinical AI to 100 countries Claude flags a new CRISPR-adjacent enzyme system Phone app separates Cro...

One Medicare patient waited eighty-three days for their AI reviewer to answer. Run time: 7:10 In today's episode: Medicare's AI prior-auth pilot denied care, delayed one case 83 days FDA final order: AI radiology software still needs premarket clearance Gemini, ChatGPT, and Claude all fail a heart-attack screening test First AI-discovered drug doses first patient in a Phase 3 trial MIT and Ha...

Google just mapped every possible way a single DNA letter can go wrong. Run time: 7:23 In today's episode: DeepMind maps all 9 billion possible DNA mutations UK proposes 44 new rules for medical AI Rural AI push meets skepticism from actual providers OpenEvidence restricts its best model over dual-use risk AI spots collapsed lungs in newborns, 87.6% sensitivity AI-measured organ volume linked to k...

Chatbots beat doctors on paper. Then real patients used them and it fell apart. Run time: 6:50 In today's episode: Chatbot answers rated more empathetic than doctors, preferred 79% of the time GPT-4 alone beat physicians by ~15 points on diagnostic vignettes Google's AMIE matched or beat primary care docs in text consultations Microsoft's system solved 85% of hard NEJM cases vs doctors&#...

Three hundred million health questions a week. Chat G P T just opened the doors. Run time: 7:11 In today's episode: ChatGPT Health opens to every US adult FDA lets Dexcom skip part of premarket review White House starts clinical AI benchmarking sprint Nature Medicine RCT: eye AI lifts diagnosis Utah publishes AI prescription renewal data Medtronic clears real-time AI for surgery Tempus buys Person...

Two hundred million protein shapes, one Nobel Prize, and still zero A I drugs approved. Run time: 6:32 In today's episode: AlphaFold two hit ~90/100 accuracy at CASP14 (2020) Database now covers 214M+ protein sequences, 3M+ users 2024 Nobel Prize: Hassabis, Jumper (AlphaFold) + Baker (design) AlphaFold3 predicts drug-protein binding, 58% vs 24% docking Static shapes only — fails on flexible, shape...

Mayo Clinic is now running a hundred and fifty AI models at once. Run time: 6:48 In today's episode: Mayo Clinic now runs 150 AI models Senate probes Medicare Advantage AI care denials Specialized tool beats GPT, Gemini, Claude Causal AI: the vasopressor call decides survival AI drugs pass safety, stall on efficacy NeuroVFM reads a hospital's own scans Claude adds self-serve HIPAA setup Moons...

Three countries claim they're winning healthcare AI. None can prove it helps patients yet. Run time: 6:44 In today's episode: US leads on approvals: 1,400-plus FDA-cleared AI devices China leads on scale: DeepSeek live in 260-plus hospitals UAE leads on data: ~1M genomes sequenced, open clinical LLM Deep Knowledge index (May 2026): US 1, UK 2, China 3 The catch: almost none of it tied to pati...

OpenAI just signed eight hospital systems the same week two studies said not so fast. Run time: 6:29 In today's episode: OpenAI signs eight major hospital systems NHS deploys AI scribes to every A&E Nature Medicine finds top medical models brittle Kenya trial: AI helped notes, not patients Weill Cornell agents design clinical trials Cardiac digital twin flags non-responders before implant Phil...

Ten years ago an AI pioneer said stop training radiologists. The field grew instead. Run time: 5:40 In today's episode: Hinton's 2016 "stop training radiologists" call has now expired On narrow tasks, AI beats radiologists on average (AUC 0.88) A workforce model projects a ~33% cut in radiologist hours over 5 years But models crater on external data and disagree with each other Huma...

The most powerful AI the US banned last month is back — and biomedical labs want it. Run time: 5:33 In today's episode: US lifts export ban; Fable 5, Mythos 5 back worldwide Anthropic launches Claude Science for pharma research Claude Sonnet 5 ships: near-Opus quality, cheaper FDA clears on-premise brain-tumor MRI AI (Cercare) GE HealthCare clears auto-contouring for radiation therapy Feds reprima...

The most powerful medical AI model came back this week, but not for you. Run time: 6:39 In today's episode: Mythos returns for a hundred federal-list orgs only Fable 5 still dark, seventeen days on FDA fast-tracks AI that writes the radiology report HOPPR drops generative drafting into PowerScribe AI drug discovery declared clinical fact at BIO Canada issues governance rules for radiotherapy AI La...

The F D A just cleared an A I that tells patients how much insulin to take. Run time: 5:57 In today's episode: FDA clears first AI that treats patients ECG AI credited with world's first transplant FDA clears AI for clogged leg arteries GE HealthCare buys Intelerad for 2.3 billion GPT-5 Pro cracks a 3-year immunology puzzle Anthropic's Fable 5 still offline, 2 weeks on TL;DR: The FDA cle...

AI agents beat real doctors on diagnosis this week, then flunked the actual ward. Run time: 6:12 In today's episode: AI agents MIRA and AMIE out-diagnose doctors on test cases Biggest real-world benchmark: top model flunks half of clinical tasks o3 cracks 18 unsolved rare-disease cases Utah lets AI renew prescriptions; oversight thin FDA's cleared-AI list passes 1,500 Hetairos AI out-classifi...

Two AI agents outscored emergency doctors on real cases, then ordered twice the bloodwork. Run time: 5:31 In today's episode: Two AI agents match or beat doctors in Nature Google's AMIE outscores physicians on disease management AI flags small pancreatic tumors on routine CT Joint Commission rolls out first hospital AI governance cert Doctors split on patients reading scans with AI Ambient AI...

Three days after launch, Washington pulled the plug on Claude's two most powerful models. Run time: 5:38 In today's episode: U.S. government forces Anthropic to disable Fable 5, Mythos 5 General chatbots beat dedicated medical AI tools in Nature Medicine SIIM: AI nails the numbers, fumbles the judgment First AI-formulated drug enters a Phase 1 trial Topol: 44 trials, still not standard practi...

An AI just spotted breast cancer in scans taken six years before diagnosis. Run time: 20:02 In today's episode: AI sees breast cancer six years before diagnosis Stanford crowd cooled on AI scribes after debate Most clinicians admit using unapproved AI tools Saudi hospital shows off practical AI at HLTH Europe States move to regulate AI in insurance approvals Stanford and Mayo read tumors from a bl...

Anthropic just handed drug labs a model that designs molecules ten times faster. Run time: 13:30 In today's episode: Ambient AI scribe cuts clinician burnout in randomized trial Philips survey: AI saves sixteen workdays, training lags AIRS SwiftMR wins wider FDA MRI clearance Mount Sinai launches AI cancer trial-matching tool Nature Medicine: AI diagnosis accuracy swings fourfold Topol says every...

Two hundred AI-designed drugs are now in human trials. Not one is approved. Run time: 20:11 In today's episode: Two hundred AI-discovered drugs in trials, zero approved FDA clears Clarius bedside ejection-fraction AI GE HealthCare auto-contouring tool cleared for radiation planning Philips and WellSpan sign seven-year AI imaging alliance Joint Commission launches first hospital AI certification WH...

Mayo Clinic just decided to build its own medical A.I. and own it outright. Run time: 12:40 In today's episode: Mayo Clinic and Microsoft build a frontier medical AI FDA clears Philips Elevate Plus AI ultrasound AI reads cancer from ordinary tissue slides Patients start using AI scribes in the exam room AI arms race is inflating medical billing ARPA-H funds first FDA-authorized clinical AI agents...

Taiwan just put one and a half billion dollars behind robot nurses in real operating rooms. Run time: 20:53 In today's episode: Taiwan and Foxconn launch 1.5 billion dollar clinical AI push Coalition for Health AI ships 8 governance playbooks BostonGene brings 9 AI biomarker abstracts to ASCO Roswell Park flags limits of AI clinical decision support Lancet Digital Health audits fairness metrics in...

ASCO twenty twenty-six opens today, and AI just lifted lung-cancer biomarker testing by twenty-four percent. Run time: 19:27 In today's episode: Tempus Next lifts lung-cancer biomarker testing by twenty-four percent Mayo Clinic brings thirty oncology AI studies to ASCO Sylvester AI reads bone marrow to personalize myeloma therapy Penn Medicine flags AI gaps in patient cancer info NEJM AI publishes...

The FDA just cleared the first AI that reads burn wounds. Run time: 20:51 In today's episode: FDA grants De Novo clearance to burn-reading AI Eli Lilly puts five hundred million into Korean AI lab QIAGEN and NVIDIA team up on AI drug discovery Bristol Myers Squibb rolls Claude to thirty thousand staff Abu Dhabi and J&J launch AI surgical network Artera takes multimodal cancer AI to ASCO Twin H...