medAI Times

medAI Times
  • 0.0 (0)
  • Medicine
  • Updated Daily

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.

  1. 8h ago

    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 approvedFDA clears Clarius bedside ejection-fraction AIGE HealthCare auto-contouring tool cleared for radiation planningPhilips and WellSpan sign seven-year AI imaging allianceJoint Commission launches first hospital AI certificationWHO weighs AI for health-policy decisionsAnthropic scales Mythos cyber program to fifteen countriesPerplexity lets its agent write its own search codeOpenAI says chat is dead, pivots to agentsTL;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 NexusDAICITNPhilipsJoint CommissionWHOTechCrunchThe Decoderthe AAPM TG-275/TG-132 segmentation guidance and reviews on auto-segmentation QASubscribe: 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.

    20 min

  2. 3d ago

    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 AIFDA clears Philips Elevate Plus AI ultrasoundAI reads cancer from ordinary tissue slidesPatients start using AI scribes in the exam roomAI arms race is inflating medical billingARPA-H funds first FDA-authorized clinical AI agentsEli Lilly fires up a thousand-GPU drug-discovery supercomputerAnthropic confidentially files to go publicGoogle ships Gemma 4, a laptop-class multimodal modelMicrosoft unveils MAI-Thinking-1 reasoning modelTL;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 / MayoPhilipsQIMR Berghofer / Nature CommunicationsSTATSTATARPA-HHealthcare context / NVIDIAAnthropicHipther AI DispatchNature 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.

    13 min

  3. Jun 1

    Taiwan Bets $1.5B on AI Robot Nurses and Scrub Bots — Jun 1, 2026

    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 pushCoalition for Health AI ships 8 governance playbooksBostonGene brings 9 AI biomarker abstracts to ASCORoswell Park flags limits of AI clinical decision supportLancet Digital Health audits fairness metrics in clinical AIDana-Farber lands two plenaries at ASCO 2026Anthropic splits programmatic Claude usage into creditsNVIDIA unveils RTX Spark personal AI superchipTL;DR: Embodied AI moves from concept to a sovereign-scale deployment: NVIDIA, Foxconn, and Taiwan's hospital network commit $1.5B to put agentic and physical AI into real ORs and wards.CHAI publishes the most comprehensive open governance playbooks yet — eight modules for 100+ US health systems, mapped to the Joint Commission's coming AI certification.ASCO 2026 day three turns into AI day: BostonGene, Roswell Park, Dana-Farber, and a dedicated 4:30 PM AI session put oncology AI into the plenary spotlight.Sources cited: sourcesourcesourcesourcesourcesourcesourcesourcesourcesourceSubscribe: 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.

    21 min

  4. May 29

    Tempus AI Lifts Lung Cancer Testing by 24% at ASCO — May 29, 2026

    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 percentMayo Clinic brings thirty oncology AI studies to ASCOSylvester AI reads bone marrow to personalize myeloma therapyPenn Medicine flags AI gaps in patient cancer infoNEJM AI publishes MEDS open data standard for health AIAnthropic ships Claude Opus four point eight with dynamic workflowsAnthropic in talks to raise sixty-five billion at nine-hundred-sixty-five billionMythos moves toward broader release after ten thousand bugs foundTL;DR: ASCO 2026 kicks off in Chicago today — Tempus Next's AI clinical decision support lifted real-world biomarker-testing rates by +24% ALK, +18% EGFR, +13% PD-L1 in early-stage NSCLC across six community health systems, a rare deployed-AI outcomes win.Anthropic released Claude Opus 4.8 yesterday — high-effort default, dynamic workflows spawning hundreds of parallel subagents, agentic coding jumps 64.3→69.2%, ~4× fewer flawed-code passes, fast mode 3× cheaper. Pricing held at $5/$25 per M tokens.NEJM AI published the MEDS (Medical Event Data Standard) review on May 28 — an open data framework now used at 21 institutions and 27 papers that aims to fix reproducibility/portability in EHR-based clinical AI.Sources cited: businesswireMayo News NetworkNewswisePenn MedicineNEJM AIHarvard Science ReviewAnthropicTechCrunchUS NewsMEDS overviewSubscribe: 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.

    19 min

  5. May 27

    FDA Clears First AI That Reads Burn Wounds — May 27, 2026

    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 AIEli Lilly puts five hundred million into Korean AI labQIAGEN and NVIDIA team up on AI drug discoveryBristol Myers Squibb rolls Claude to thirty thousand staffAbu Dhabi and J&J launch AI surgical networkArtera takes multimodal cancer AI to ASCOTwin Health launches AI for GLP-1 stewardshipLancet study: ChatGPT discharge summaries boost patientsClaude adds twenty-eight security and compliance toolsDeepMind hires twenty researchers from Contextual AITL;DR: The FDA granted De Novo clearance to Spectral AI's DeepView — the first AI burn-wound assessment system, opening a brand-new device category for multispectral imaging in trauma and burn care.The pharma-AI operating model deepened in one week: Eli Lilly committed $500M to a Korean AI drug-discovery hub, QIAGEN tied up with NVIDIA on BioNeMo-powered target ID, and Bristol Myers Squibb put Claude in front of ~30,000 employees.Anthropic launched the Claude Compliance API with 28 enterprise security integrations (CrowdStrike, Microsoft Purview, Wiz, Okta, Zscaler, Cloudflare and more) — the missing governance layer hospitals and pharma IT have been waiting on.Sources cited: GlobeNewswireDong-A ScienceDigital Health NewsDigital Health NewsGulf NewsBusinessWireHIT ConsultantThe Lancet Digital HealthHelp Net SecurityHeyGoTradeSubscribe: 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.

    21 min

  6. May 22

    FDA Cleared These AI Tools — But Are They Proven? — May 22, 2026

    FDA cleared does not mean it actually works. Today, the proof. Run time: 16:28 In today's episode: AZmed's X-ray AI clears fractures, effusions, dislocationsFDA clears first digital-pathology breast cancer risk toolRadiologist-plus-AI beats AI alone for clot detectionTop journal: FDA cleared isn't FDA provenUltromics raises 55 million for echo AIFDA now clears an AI device every 31 hoursKPMG puts Claude in front of 276,000 staffAnthropic eyes 900-billion valuation, may pass OpenAIMicrosoft's 100 agents find 16 Windows flawsxAI ships Grok Build, its first coding agentTL;DR: A fresh wave of FDA clearances (AZmed's AZtrauma for fractures/effusions/dislocations; ArteraAI Breast) lands the same week a top journal warns that "cleared" is not "clinically proven" — the procurement question from yesterday's lung-CXR head-to-head is now everyone's problem.KPMG is rolling Claude out to 276,000+ employees as Anthropic courts a $30B raise at a $900B+ valuation that could top OpenAI for the first time.New peer-reviewed data shows radiologists plus AI beat AI alone at finding pulmonary embolism — the week's quiet through-line is collaboration and evidence, not replacement.Sources cited: Diagnostic ImagingArteraAuntMinnieAnnals of Internal MedicineCrescendo AI Healthcare NewsInnolitics 510(k) Year-in-ReviewAnthropicBloombergMicrosoft Security BlogThe DecoderSubscribe: 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.

    16 min

  7. May 20

    AI Saliva Cancer Test Returns Results in 10 Minutes — May 20, 2026

    A saliva test just flagged cancer in under ten minutes. Run time: 20:23 In today's episode: Hong Kong saliva device flags cancer in minutesAI risk scores failed to change transplant talksARPA-H funds a behavioral-health foundation modelLawsuits hit AI scribes over recorded consentAI avatar calmed cancer patients before treatmentMETiS TechBio lists on AI nanomedicine betAI matches MS patients to a repurposed drugKarpathy leaves OpenAI orbit, joins AnthropicGoogle I/O ships Gemini 3.5, Omni, and SparkClaude agents get self-hosted sandboxes and MCP tunnelsCursor's Composer 2.5 matches Opus 4.7TL;DR: A portable HKU device reads DNA-damage signals in saliva and returns a cancer-risk result via phone app in under 10 minutes — a potential cheap, non-invasive triage layer.A German RCT (PRIMA-AI) found that giving physicians AI graft-loss risk scores did NOT increase the rare-but-critical conversations about options after transplant failure — a clean reminder that prediction ≠ behavior change.Two AI-lab blockbusters landed: Andrej Karpathy joined Anthropic's pre-training team (May 19), and Google I/O unveiled Gemini 3.5 Flash, Gemini Omni (video), and the Gemini Spark agent.Sources cited: HKULucidQuest digestPR NewswireFisher PhillipsTechCrunchCNBCthe-decoderEffective context engineering for AI agentsSubscribe: 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.

    20 min

  8. May 18

    60% of Nurses Don't Trust Their Hospital's AI — May 18, 2026

    Most hospitals running AI agents have no idea if they actually work. Run time: 20:30 In today's episode: Only 59 percent of health orgs track their AI agentsQure.ai Aira deployed across Mozambique's national health systemAnnalise.ai goes network-wide at Parkway SingaporeNature Medicine: clinical trials for self-updating AINature Medicine: the AI co-scientist arrives in the clinicGoogle Health Coach launches tomorrow on GeminiAnthropic Code with Claude London hits tomorrowAnthropic briefs finance regulators on Claude Mythos risksTL;DR: Healthcare IT Today's May 17 industry digest surfaced two governance numbers worth pinning above every CIO's desk: only 59% of healthcare orgs actively track the performance of their AI agents in production, and 60% of nurses say they lack confidence in their organization's AI oversight — a credibility gap that lands the same week as Aidoc's CARE foundation model and Bayesian Health's continuous-sepsis monitor scale clinically.Nature Medicine published "Clinical trials for continuously monitored and updated AI systems" by van Amsterdam, Oberst, Feng et al., proposing a conceptual framework that separates AI-intrinsic monitoring/updating from trial-oversight monitoring — the methodological companion to last week's Frontiers in Science manifesto on adaptive surgical robots and the FDA's real-time trials pilot.VillageReach and Qure.ai have deployed Aira — Qure.ai's LLM-powered co-pilot for community health workers — across Mozambique's national health system under a Gates Foundation pandemic-preparedness grant, embedding it in the AlôVida hotline and PHEOC for early signal detection across primary care; pairs with last week's Anthropic-Gates $200M deal on neglected diseases.Sources cited: Healthcare IT TodayVillageReach announcementIHH HealthcareNature MedicineNature MedicineTechCrunchClaude.comLet's Data ScienceSubscribe: 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.

    21 min
See All (13)

About

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.

Information

  • Creator
    medAI Times
  • Years Active
    2K
  • Episodes
    13
  • Rating
    Clean
  • Copyright
    © 2026 medAI Times
  • Show Website
    medAI Times