Three days after launch, Washington pulled the plug on Claude's two most powerful models.

Run time: 5:38

In today's episode:

1. U.S. government forces Anthropic to disable Fable 5, Mythos 5
2. General chatbots beat dedicated medical AI tools in Nature Medicine
3. SIIM: AI nails the numbers, fumbles the judgment
4. First AI-formulated drug enters a Phase 1 trial
5. Topol: 44 trials, still not standard practice
6. Anthropic credit split and model retirements go live today
7. 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.

An AI just spotted breast cancer in scans taken six years before diagnosis.

Run time: 20:02

In today's episode:

1. AI sees breast cancer six years before diagnosis
2. Stanford crowd cooled on AI scribes after debate
3. Most clinicians admit using unapproved AI tools
4. Saudi hospital shows off practical AI at HLTH Europe
5. States move to regulate AI in insurance approvals
6. Stanford and Mayo read tumors from a blood draw
7. Anthropic splits subscription and API credits June 15
8. xAI's Grok V9 lands mid-June, built on Cursor data
9. 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.

Anthropic just handed drug labs a model that designs molecules ten times faster.

Run time: 13:30

In today's episode:

1. Ambient AI scribe cuts clinician burnout in randomized trial
2. Philips survey: AI saves sixteen workdays, training lags
3. AIRS SwiftMR wins wider FDA MRI clearance
4. Mount Sinai launches AI cancer trial-matching tool
5. Nature Medicine: AI diagnosis accuracy swings fourfold
6. Topol says every mammogram should use AI
7. Anthropic ships Fable 5, its strongest public model
8. Claude Code adds parallel-subagent dynamic workflows
9. 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.

Two hundred AI-designed drugs are now in human trials. Not one is approved.

Run time: 20:11

In today's episode:

1. Two hundred AI-discovered drugs in trials, zero approved
2. FDA clears Clarius bedside ejection-fraction AI
3. GE HealthCare auto-contouring tool cleared for radiation planning
4. Philips and WellSpan sign seven-year AI imaging alliance
5. Joint Commission launches first hospital AI certification
6. WHO weighs AI for health-policy decisions
7. Anthropic scales Mythos cyber program to fifteen countries
8. Perplexity lets its agent write its own search code
9. 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.

Mayo Clinic just decided to build its own medical A.I. and own it outright.

Run time: 12:40

In today's episode:

1. Mayo Clinic and Microsoft build a frontier medical AI
2. FDA clears Philips Elevate Plus AI ultrasound
3. AI reads cancer from ordinary tissue slides
4. Patients start using AI scribes in the exam room
5. AI arms race is inflating medical billing
6. ARPA-H funds first FDA-authorized clinical AI agents
7. Eli Lilly fires up a thousand-GPU drug-discovery supercomputer
8. Anthropic confidentially files to go public
9. Google ships Gemma 4, a laptop-class multimodal model
10. 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.

Taiwan just put one and a half billion dollars behind robot nurses in real operating rooms.

Run time: 20:53

In today's episode:

1. Taiwan and Foxconn launch 1.5 billion dollar clinical AI push
2. Coalition for Health AI ships 8 governance playbooks
3. BostonGene brings 9 AI biomarker abstracts to ASCO
4. Roswell Park flags limits of AI clinical decision support
5. Lancet Digital Health audits fairness metrics in clinical AI
6. Dana-Farber lands two plenaries at ASCO 2026
7. Anthropic splits programmatic Claude usage into credits
8. NVIDIA unveils RTX Spark personal AI superchip

TL;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:

• source
• source
• source
• source
• source
• source
• source
• source
• source
• source

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.

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:

1. Tempus Next lifts lung-cancer biomarker testing by twenty-four percent
2. Mayo Clinic brings thirty oncology AI studies to ASCO
3. Sylvester AI reads bone marrow to personalize myeloma therapy
4. Penn Medicine flags AI gaps in patient cancer info
5. NEJM AI publishes MEDS open data standard for health AI
6. Anthropic ships Claude Opus four point eight with dynamic workflows
7. Anthropic in talks to raise sixty-five billion at nine-hundred-sixty-five billion
8. Mythos moves toward broader release after ten thousand bugs found

TL;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:

• businesswire
• Mayo News Network
• Newswise
• Penn Medicine
• NEJM AI
• Harvard Science Review
• Anthropic
• TechCrunch
• US News
• MEDS overview

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.

The FDA just cleared the first AI that reads burn wounds.

Run time: 20:51

In today's episode:

1. FDA grants De Novo clearance to burn-reading AI
2. Eli Lilly puts five hundred million into Korean AI lab
3. QIAGEN and NVIDIA team up on AI drug discovery
4. Bristol Myers Squibb rolls Claude to thirty thousand staff
5. Abu Dhabi and J&J launch AI surgical network
6. Artera takes multimodal cancer AI to ASCO
7. Twin Health launches AI for GLP-1 stewardship
8. Lancet study: ChatGPT discharge summaries boost patients
9. Claude adds twenty-eight security and compliance tools
10. DeepMind hires twenty researchers from Contextual AI

TL;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:

• GlobeNewswire
• Dong-A Science
• Digital Health News
• Digital Health News
• Gulf News
• BusinessWire
• HIT Consultant
• The Lancet Digital Health
• Help Net Security
• HeyGoTrade

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.