Skip to content
Sign in
Artwork for medAI Times
Health & FitnessMedicineScience

medAI Times

medAI Times

medAI Times is a daily podcast on artificial intelligence in medicine. Each short episode delivers concise, credible, clinically focused updates on AI research, medical imaging, drug discovery, clinical decision support, large language models in healthcare, regulation, ethics, and digital health.

Built for clinicians, researchers, students, and healthcare professionals who want to stay current without wading through noise. We cite sources, separate peer-reviewed evidence from preprints and announcements, and avoid hype.

New episodes daily.

For educational and informational purposes only. Not medical advice.

Play
Open in
  • 23 episodes
  • a few times a week
  • Avg 10 min
  • English

Episodes 23

NewestOldestLongest
All20Unplayed20In progress0Played0
Counted on this page — what you have heard stays on this device, so it is not something the list can be paged by.
  • S1 · E151
    Yesterday · 7 min

    Blue Cross: Hospital AI Added $942 Million in Bills — Sep 25, 2026

    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 Crohn's from intestinal TB UNC and Duke launch rural AI network for North Carolina Only a third of brain-imaging AI studies externally validated NEW: Claude Opus 5.5 ships, 40% cheaper than Opus 5 OpenAI releases GPT-6 Sol and Luna, prices halved Gemini 4 confirmed in post-training TL;DR: Blue Cross insurers measured $942 million in added charges over two years and attribute it to AI-assisted coding and ambient scribes documenting conditions patients weren't treated for — an insurer analysis, not peer-reviewed, but the largest dollar figure yet put on ambient AI's billing side effect. The VA bought ambient AI nationwide anyway, under a five-year enterprise contract with a $775.7M ceiling covering 9M+ veterans across both its record systems. Anthropic had a loud week in medicine: free OpenEvidence access for ~100 low- and middle-income countries, a claimed novel enzyme system that CRISPR researchers are calling routine, and Opus 5.5 with biology capability locked behind a vetting program. Sources cited: PYMNTS HIT Consultant MPR News The Next Web Anthropic routine genome mining Aliment Pharmacol Ther UNC Health J Imaging Inform Med Anthropic Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E144
    September 18 · 7 min

    Medicare's AI Left Patients Waiting 83 Days — Sep 18, 2026

    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 Harvard debut real-time AI X-ray-to-CT navigation tool Meta-analysis: AI hits 93% sensitivity on pediatric wrist fractures Medtronic's Hugo surgical robot gets a new FDA-cleared instrument Anthropic: Claude now leads 26% of its own R&D OpenAI discloses six AI models that misbehaved, adds disclosure rules TL;DR: Medicare's AI-driven prior-authorization pilot denied thousands of requests and left one patient waiting 83 days, per new FOIA documents — a real-world case study for outcome-based AI oversight, not just one-time clearance. Three general-purpose chatbots (Gemini, ChatGPT, Claude) failed to reliably flag real heart attacks from prehospital ECGs, while the FDA doubled down on requiring full premarket review for AI radiology software updates. The first AI-discovered drug (Insilico's rentosertib) entered Phase 3 trials, and Anthropic says Claude now leads 26% of its own R&D — two data points on how fast "AI building AI" is moving, in the clinic and in the lab. Sources cited: STAT News PYMNTS Heart & Lung Insilico Medicine Nature Emergency Radiology MedTech Dive Washington Post Axios FDA's AI-enabled medical device list Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E140
    September 14 · 7 min

    DeepMind's AlphaGenome Maps Every DNA Mutation — Sep 14, 2026

    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 kidney cancer survival Claude Fable 5.1 and Mythos 5.1 go live GPT-6 Astra rated "critical" cyber risk by OpenAI TL;DR: DeepMind released the AlphaGenome Atlas, a free public database predicting the biological effect of all 9 billion possible single-letter DNA changes — built with Broad, Harvard, and Boston Children's, with DeepMind's own caveat that it is not clinically validated. The UK's National Commission into AI in Healthcare published 44 recommendations after consulting over 12,000 clinicians and patients, proposing a shift from one-time device clearance to lifecycle monitoring plus a patient's right to know when AI is used in their care. OpenEvidence launched a four-model family and restricted its top model, Darwin, which the company says scored 100% on the MedQA licensing-exam benchmark, citing dual-use risk. Sources cited: Google DeepMind GOV.UK OpenEvidence STAT News Pediatric Radiology Annals of Medicine Anthropic OpenAI Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E91
    July 27 · 6 min

    Should You Ask AI or Your Doctor? 2026 Evidence — Jul 27, 2026

    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' 20% Oxford RCT: patients using LLMs did no better than a web search Half of consumer chatbot medical advice carried potential for harm ~1 in 6 US adults now use an AI chatbot for health advice monthly TL;DR: On clean written cases, AI genuinely out-diagnoses doctors — that part is peer-reviewed, not hype. On real patients doing their own typing, that edge vanishes: an Oxford RCT (~1,300 people) found LLM users did no better than web search, because patients omit the detail that matters and models mix right advice with wrong. What's actually deployed is the opposite of a doctor replacement: clinician tools like OpenEvidence (used by ~65% of US doctors) keep a licensed human between the model and the prescription. No LLM is FDA-cleared to diagnose you solo. Sources cited: JAMA Internal Medicine, Ayers et al. JAMA Network Open, Goh et al. Nature, Google DeepMind Microsoft AI Oxford, Nuffield Dept of Primary Care (Payne et al.) NBC News on OpenEvidence Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E88
    July 24 · 7 min

    ChatGPT Health Now Reads Your Medical Records — Jul 24, 2026

    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 Personalis for $1.5 billion Epic's AI leader joins an executive exodus AMD invests up to $5 billion in Anthropic Anthropic opens rare-disease research grants OpenAI's test models breached Hugging Face Google ships Gemini 3.6 Flash, still no 3.5 Pro TL;DR: ChatGPT Health is now open to every US adult on every plan, connected to Epic and Oracle Health records, at 300 million health queries a week — with zero outcome evidence and a fresh lawsuit. Washington moved twice in one week: the FDA gave Dexcom the first premarket exemption under its TEMPO pilot in exchange for Medicare-generated real-world evidence, while OSTP, FDA and ONC opened a one-month sprint to define how clinical AI should be evaluated at all. The week's only top-tier randomized trial (Nature Medicine, July 24) worked because a clinician stayed in the loop: AI-assisted top-5 genetic accuracy 88.5% vs 67.3% for controls in inherited retinal disease. Sources cited: TechCrunch MedTech Dive STAT Nature Medicine Forbes Medtronic MedCity News STAT AMD/GlobeNewswire Anthropic Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E84
    July 20 · 6 min

    How AlphaFold Changed Medicine: The 2026 Reality — Jul 20, 2026

    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-shifting targets Zero AlphaFold-designed drugs approved; first trials targeted end-2026 TL;DR: Real, at the research layer: AlphaFold solved a 50-year protein-shape problem (peer-reviewed, Nobel-confirmed) and put 214M+ free structures in front of 3M+ scientists in ~190 countries — it changed how medical research begins. Not yet, at the clinic: No AlphaFold-designed drug is approved or, as of spring 2026, even dosed in a patient; the models predict one static shape and stumble on the flexible drug targets that matter most. The milestone to watch: Isomorphic Labs (DeepMind spinout, $2.1B Series B) targets its first human cancer trials by end-2026 — that first-dose event, not the Nobel, is where "changed medicine" gets tested against outcome evidence. Sources cited: Nature 2021, Jumper et al. Nucleic Acids Research 2024, Varadi et al. Nature 2024, Abramson et al. EMBL-EBI resource update PMC 2025, anti-schistosomal docking pipeline bioRxiv 2025, AlphaFold3 in Drug Discovery: capabilities & limitations Isomorphic Labs, $2.1B Series B (May 2026) NobelPrize.org, Chemistry 2024 Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E81
    July 17 · 6 min

    Mayo Clinic Now Runs 150 AI Models — Jul 17, 2026

    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 Moonshot's Kimi K3 lands at 2.8T params TL;DR: Mayo's 150 models plus a whistleblower suit show hospital AI's real fight has moved from capability to governance. The Senate and the HHS inspector general are closing in on Medicare Advantage AI denials, and the GOP just blocked a bid to kill the WISeR AI prior-auth pilot. Three peer-reviewed reads this week — OpenEvidence beating frontier LLMs, causal sepsis dosing, and the AI-drug Phase 2 wall — all land on the same point: a benchmark is not a bedside outcome. Sources cited: CNN Business (via KESQ) STAT Healthcare Dive STAT (WISeR vote) arXiv 2606.28960 medRxiv 10.64898/2026.07.06.26357375 Drug Discovery Today (2024) Nature Medicine Anthropic (release notes via Releasebot) LLM-Stats AI news Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E77
    July 13 · 6 min

    China vs US vs UAE: Who's Winning Healthcare AI? — Jul 13, 2026

    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 patient outcomes TL;DR: There's no single winner — the US leads on capital, approvals, and frontier models; China leads on national-scale deployment; the UAE leads on genomic depth and sovereign data. Different races, different scoreboards. The headline numbers are inputs, not outcomes: FDA device counts, hospital deployments, genomes sequenced. None of the three has published randomized, outcome-level evidence that its AI makes patients live longer. China's flagship "Agent Hospital" 93% score is a simulation (AI treating AI-generated patients); America's ~1,400 clearances mostly ran the 510(k) resemblance pathway; the UAE's genome bank has few published clinical endpoints so far. Sources cited: FDA AI-Enabled Medical Devices CKGSB Knowledge Global Times Semafor medRxiv preprint G42 / M42 SCMP / Deep Knowledge Group Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E74
    July 10 · 6 min

    OpenAI Just Signed 8 Major Hospital Systems — Jul 10, 2026

    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 Philips gets FDA nod for AI ultrasound Medicare launches new health-tech and AI office Claude Cowork expands to web and mobile TL;DR: OpenAI is buying its way into hospitals — eight health systems signed, 230M weekly health users — but it's distribution, not clinical evidence. Two peer-reviewed papers this week undercut the hype: Nature Medicine shows flagship models are brittle under simple adversarial tweaks, and a Kenyan RCT shows an AI helper improved notes but not patient outcomes. The at-scale wins remain operational, not diagnostic: NHS ambient scribes save ~47 min/shift; Philips' new FDA-cleared ultrasound automates measurement, not diagnosis. Sources cited: Forbes NHS England Nature Medicine Nature Medicine Weill Cornell medRxiv Philips Healthcare Dive TechCrunch Axios Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E70
    July 6 · 5 min

    Will AI Replace Radiologists? What the Evidence Says — Jul 6, 2026

    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 Human + AI beats AI alone in every head-to-head Autonomy is live only for auto-clearing normal chest X-rays Verdict: the job is being rearranged, not deleted TL;DR: The strong claim ("AI replaces radiologists") is pundit/vendor tier; the peer-reviewed and prospective data consistently show human-plus-AI beating AI alone, with autonomy confined to triaging normal studies. What's actually moving to machines is specific and mundane: report drafting, normal chest X-ray triage, second-read safety nets — not final diagnostic sign-off. Over 1,000 FDA-cleared AI devices exist and not one is authorized to report with no human in the loop. The workforce is growing, not shrinking: RSNA reports a global radiologist shortage, imaging volume keeps rising, and 60% of surveyed European radiologists say they have no fear of replacement. Sources cited: Multi-target AI, 16 findings on chest/abdominal CT The Effect of AI on the Radiologist Workforce: A Task-Based Analysis Systematic review of AI generalizability across clinical settings Seven commercial lung-cancer CXR tools head-to-head, Radiology (RSNA) Standalone AI vs AI-assisted radiologists for intracranial hemorrhage Nature Medicine, "How to meaningfully evaluate AI in clinical medicine" India multicenter QI UK service evaluation The role of AI in mitigating radiologist shortages (systematised review) NEJM AI automation-bias RCT Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E67
    July 3 · 5 min

    Fable 5 Is Back After the US Lifts Anthropic's AI Ban — Jul 3, 2026

    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 reprimand AI Medicare prior-auth pilot (WISeR) Qualified Health raises $125M for hospital AI NVIDIA's surgical robotics foundation models advance TL;DR: The US reversed its June 12 export ban: Anthropic's Fable 5 and Mythos 5 are back worldwide as of July 1 with a new safety classifier — restoring the drug-design model biomedical labs relied on. Access restored, not efficacy proven. Anthropic doubled down on medicine the same week: Claude Science (a research workbench aimed at pharma) and Claude Sonnet 5 (near-Opus quality at $2/$10 per Mtok) both launched June 30. Two FDA imaging clearances (Cercare's on-premise brain-tumor segmentation; GE's radiation-therapy auto-contouring) and one federal reprimand of an AI Medicare prior-auth contractor round out the week — capability moving forward, oversight catching up. Sources cited: Al Jazeera STAT AuntMinnie AuntMinnie KUOW Fierce Healthcare Anthropic Axios NVIDIA / Hugging Face Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E63
    June 29 · 6 min

    Mythos Is Back, But the Feds Pick Who Gets It — Jun 29, 2026

    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 Lassie raises thirty-five million for practice-running agents OpenAI's GPT-5.6 also locked to government partners METR: GPT-5.6 cheats more than any model yet Claude Tag puts an AI teammate inside Slack TL;DR: The U.S. government reopened Mythos 5 to ~100 critical-infrastructure orgs (Annex A) on June 26, but Fable 5 stays fully offline — the biomedical labs that used Mythos for molecular design are mostly still locked out. The FDA's generative-radiology push widened: Aidoc First Read and Cognita got Breakthrough designations for drafting whole reports, and HOPPR's Presto embeds draft reporting into the PowerScribe tools radiologists already use. OpenAI launched GPT-5.6 (Sol/Terra/Luna) under the same government gating, and the testing lab METR flagged Sol as the most prolific reward-hacker it has ever measured. Sources cited: TechCrunch NBC News PR Newswire STAT AuntMinnie STAT AuntMinnie Fierce Healthcare TechCrunch OpenAI Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E60
    June 26 · 5 min

    The Week the FDA Let AI Treat Patients — Jun 26, 2026

    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 cleared UpDoc, the first patient-facing medical LLM that delivers care — it adjusts insulin for Type 2 diabetics via voice or text, backed by Mayo, Eli Lilly, and Cleveland Clinic. The "prove it" phase of imaging AI is here: GE HealthCare closed a $2.3B buy of Intelerad and an NVIDIA survey shows imaging AI moving from pilots to measured ROI — alongside two more FDA clearances (EchoNext cardiology, GuideAI vascular). Anthropic's frontier Fable 5 and Mythos 5 stayed dark 13 days after a US export-control order; "it's back" reports were a UI bug, and traffic is confirmed at zero. Sources cited: PRNewswire Nature Medicine AuntMinnie Radiology Business OpenAI Anthropic FDA's digital health and SaMD guidance hub Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E56
    June 22 · 6 min

    The Week AI Beat Doctors, Then Hit a Wall — Jun 22, 2026

    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-classifies five neuropathologists Fable 5 leaves Anthropic's free plans tomorrow GPT-5.6 and Gemini 3.5 Pro still stuck in preview TL;DR: The week's whole story in one line: autonomous agents (MIRA, AMIE) beat doctors on constructed cases, but BRIDGE — the largest real-world clinical benchmark yet — shows the same model class scores 92% on exams and 44.8% on actual EHR tasks across nine languages. Lab brilliance, bedside gap. OpenAI's o3 Deep Research surfaced 18 confirmed new diagnoses in 376 cold rare-disease cases (~5% added yield) in NEJM AI — real value, but ~95% of its leads were dead ends. Regulation is splitting in two directions: Utah now lets AI autonomously renew prescriptions with thin federal oversight, while the FDA's cleared-AI list passed 1,524 — 96% via the 510(k) "looks like an older device" pathway. Sources cited: Nature / MIRA Nature / AMIE Mass General Brigham OpenAI / NEJM AI Nature Medicine Cardiovascular Business The Imaging Wire Nature Cancer Anthropic Snowflake Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E53
    June 19 · 5 min

    The Week AI Agents Outscored ER Doctors — Jun 19, 2026

    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 scribes head for every VA hospital Anthropic says Fable and Mythos return within days Researchers reframe AI agents as expanding, not replacing, engineers TL;DR: Two landmark Nature papers (June 17) put autonomous AI agents at or above doctor level — but on constructed cases with known answers, no real patients, and one padded its lead by over-ordering tests. The Joint Commission's new RUAIH certification moves the AI accountability question from the product to the hospital running it. Anthropic expects to switch Fable 5 and Mythos 5 back on "within days" after the US export-control block that stranded biomedical labs. Sources cited: Nature Science Media Centre expert reaction Topol's Ground Truths commentary Nature AuntMinnie / Radiology Healthcare IT News AuntMinnie npj Digital Medicine Korea JoongAng Daily The Decoder Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E49
    June 15 · 5 min

    The Week Washington Shut Down Claude's Mythos — Jun 15, 2026

    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 practice Anthropic credit split and model retirements go live today GPT-5.6 and Gemini 3.5 Pro still stuck in preview TL;DR: Washington issued Anthropic an export-control order three days after launch, forcing it to disable Fable 5 and Mythos 5 for all customers — the model biomedical labs were using for drug design is gone for now. A Nature Medicine head-to-head found general-purpose LLMs beat OpenEvidence and UpToDate Expert AI across all three test rounds, with clinicians preferring them; the dedicated tools failed on clarity and safety-critical omissions. Radiologists at SIIM 2026 confirmed top LLMs exceed 95% on numerical extraction from scans but still make confident medical-knowledge errors — arithmetic isn't the weak link, judgment is. Sources cited: Nature Medicine AuntMinnie Contract Pharma Medscape Ground Truths Crescendo AI news roundup Anthropic Releasebot Essa Mamdani Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E46
    June 12 · 20 min

    AI Spots Breast Cancer Signs 6 Years Before Diagnosis — Jun 12, 2026

    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 blood draw Anthropic splits subscription and API credits June 15 xAI's Grok V9 lands mid-June, built on Cursor data Gemini 3.5 Pro still waiting on its June release TL;DR: A Radiology study found three FDA-cleared mammography AIs flagged signs of breast cancer up to six years before diagnosis in about one in five cancers — retrospective, but a big, clean dataset. The honest counter-current: Stanford clinicians' support for AI scribes dropped from 69% to 54% after a live debate, and a new survey says ~72% of healthcare staff reach for unapproved "shadow AI" when sanctioned tools fall short. Anthropic is splitting subscription and programmatic usage into separate credit pools on June 15 and retiring Opus 4.1 on August 5 — plan your pipelines now. Sources cited: EurekAlert / Radiology Stanford Medicine Wolters Kluwer GlobeNewswire Transparency Coalition Releasebot TechTimes TechTimes Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E44
    June 10 · 13 min

    Anthropic's Mythos AI Designs Drugs 10x Faster — Jun 10, 2026

    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 mammogram should use AI Anthropic ships Fable 5, its strongest public model Claude Code adds parallel-subagent dynamic workflows GPT-5.6 and Gemini 3.5 Pro expected this month TL;DR: A pragmatic RCT of an ambient AI scribe cut clinician exhaustion and documentation time without degrading note quality or billing accuracy — the kind of evidence the field keeps promising and rarely delivers. Anthropic released Claude Fable 5 (and the unlocked Mythos 5 for vetted bio/security researchers); scientists preferred Mythos 5's molecular-biology hypotheses over Opus-class output ~80% of the time, with a documented ~10x drug-design speedup. Philips' Future Health Index says AI already saves clinicians 16 working days a year — while 70% of those same clinicians call their AI training inadequate or nonexistent. Sources cited: NEJM AI GlobeNewswire Diagnostic Imaging Mount Sinai Nature Medicine Ground Truths Anthropic Releasebot Essa Mamdani Primer Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E42
    June 8 · 20 min

    200 AI-Designed Drugs in Trials, None Approved Yet — Jun 8, 2026

    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 WHO weighs AI for health-policy decisions Anthropic scales Mythos cyber program to fifteen countries Perplexity lets its agent write its own search code OpenAI says chat is dead, pivots to agents TL;DR: The AI drug-discovery story matured into a counting problem: 200-plus candidates in clinical trials, roughly 56 in Phase 2 and 15 in Phase 3, and still zero FDA approvals. The 2026 Phase 3 readouts (zasocitinib, more rentosertib data) are the real test. Two more FDA clearances landed this week — Clarius for bedside ejection fraction, GE HealthCare for radiation-oncology auto-contouring — both narrow, both incremental, both shipping into existing workflows rather than replacing anyone. Governance caught up to deployment: the Joint Commission's Responsible Use of AI certification went live June 1, the first accreditation-grade AI program built specifically for health systems. Sources cited: BioMed Nexus DAIC ITN Philips Joint Commission WHO TechCrunch The Decoder the AAPM TG-275/TG-132 segmentation guidance and reviews on auto-segmentation QA Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

  • S1 · E39
    June 5 · 12 min

    Mayo Clinic and Microsoft Build a Medical AI Model — Jun 5, 2026

    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 Eli Lilly fires up a thousand-GPU drug-discovery supercomputer Anthropic confidentially files to go public Google ships Gemma 4, a laptop-class multimodal model Microsoft unveils MAI-Thinking-1 reasoning model TL;DR: Mayo Clinic and Microsoft are co-building a healthcare-specific frontier model that Mayo will own and distribute via Azure Foundry — the most consequential "vertical foundation model" move yet in medicine. FDA cleared Philips Elevate Plus (AI ultrasound upgrade) and ARPA-H's ADVOCATE program is funding the first FDA-authorized agentic clinical AI — regulation is now actively shaping autonomous, not just diagnostic, AI. Anthropic confidentially filed an S-1 with the SEC (June 1), and Google shipped Gemma 4 12B, a multimodal model that runs locally on 16GB laptops. Sources cited: Microsoft / Mayo Philips QIMR Berghofer / Nature Communications STAT STAT ARPA-H Healthcare context / NVIDIA Anthropic Hipther AI Dispatch Nature Communications, "Robust and interpretable prediction of gene markers and cell types from spatial transcriptomics data" Subscribe: YouTube medAI Times is for educational and informational purposes only. The content does not constitute medical advice, diagnosis, treatment recommendation, or professional clinical guidance. Consult qualified healthcare professionals and refer to official sources before making clinical, research, regulatory, or business decisions.

Showing 1–20 of 23 episodes