An Autopsy of Four Drugs: The Cause of Death for Four AstraZeneca and Novartis Oncology Programs
Four Cases, One Broken Chain
Beyond the Slide
Pathologist & PhD in oncology. Expert in digital pathology, AI and diagnostics. Writing to decode the present — and build what’s next.
Subscribe:.rss.atom.json.md.m3u.pls
Live Last read · last published · next check
Latest episodes
When Target Expression Isn't Enough
The blind spot antibody-drug conjugates share with pathology AI
We Didn't Get Foundation Models Wrong. We Got the Question Wrong.
Better perception alone won’t solve digital pathology’s standardization problem
The Relocation of Fragility : Innovation doesn't eliminate fragility. It redistributes it.
THE MONTHLY REVIEW
THE COLD WAR OF DRUG DEVELOPMENT
This isn't a war to be won. It's a race to not be the one left behind.
Healthcare Didn't Adapt to AI. AI Adapted to Healthcare.
Why disruptive technologies lose their transformative power when organizations force them into legacy frameworks.
The Sophistication Trap : Why More Technology Doesn’t Necessarily Create More Value
The hospital had done the transition right.
Hacking the Medical System: How Necessity Drove Change But Not Adoption
How the industry built smarter algorithms when hospitals needed simpler systems and what happened when clinicians started fixing it themselves
The Proximity Paradox of Digital Pathology
How a technology designed to connect experts may be quietly weakening the invisible networks that make diagnosis possible.
The Most Expensive Experiment in Modern Biology
How technology-first thinking destroys R&D programs before they begin
Is Pharma Ready for AI?, Or Has It Confused Investment with Capability?
THE PROMISE : The biggest technology boom in the history of the pharmaceutical industry
The Problem Is Not the Model. It’s the Meeting After the Model.
AI is already producing useful predictions, what organizations still don’t know how to produce are decisions
The Translation Gap
Why modern biomedical organizations generate biological intelligence faster than they can operationalize it
The Domestication of Medical AI: How Europe selects which forms of clinical intelligence get to survive
Earlier this year, physicians across the UK and EU opened their laptops to find that OpenEvidence, a clinical AI platform used by more than 40% of doctors across 10,000 US hospitals, had gone dark overnight.
From Photograph to Video, The New Science of Measuring Disease: Rethinking Endpoints in the Age of AI (Part 4)
In the first article of this series, we corrected a misunderstanding: the FDA did not approve an AI-based endpoint.
The Gold Standard Was Made of Clay. Why Histology Was Never Enough. Rethinking Endpoints in the Age of AI (Part 3b)
In the previous chapter of this series, we explored the gap between what evidence promises and what patients experience.
The Trial Says It Works. Your Patient Disagrees: Rethinking Endpoints in the Age of AI (Part 3)
In the previous chapter, we left a question unanswered.
Beyond the Loop: AI as an Extension of Clinical Reasoning
If the problem wasn’t a lack of supervision, the solution can’t be more supervision either.
The Illusion of Control: Why "Human in the Loop" Is Clinical AI's Biggest Regulatory Fiction
This is a detour from my series on endpoints and digital pathology but this topic keeps generating questions I can't ignore: where are we actually going, and how?
An Endpoint Is Not a Biomarker, and That Difference Can Kill a Drug : Rethinking Endpoints in the Age of AI (Part 2)
In the previous chapter, we looked at a case that generated considerable noise in the community: the supposed “approval of an AI-based endpoint.”