In partnership with
AIHealthTech Insider: Issue # 102
May 25, 2026
This issue follows a clear pattern: a single MRI predicting Alzheimer’s, routine CT scans revealing pancreatic cancer years early, cardiac MRI being interpreted with near-specialist accuracy, and ECGs flagging hidden cardiac arrest risk. The big shift is not just better diagnosis, it is whether everyday scans and tests could become early-warning systems for millions of patients.
Summaries are for education, not medical advice. Always verify locally before clinical use.
🔬 The Big Story
An AI just predicted Alzheimer's years before symptoms using a scan you've probably already had.
UCSF published a study in Nature Aging that most people outside medicine haven't heard about yet.
Image: AI-generated, AIHealthTech Insider
One routine MRI scan. No specialist. No expensive tests. No years of follow-up data. The AI predicts Alzheimer's diagnosis and future cognitive decline and outperformed every existing method tested against it.
Here's why that matters: most people outside major cities can't access proper Alzheimer's testing. This works on the basic MRI machine already sitting in most hospitals.
The part nobody is saying out loud: the scan that could predict your future may already be in your medical file. Taken for a different reason. Read as normal. Filed away.
Who decides who gets screened next and who pays for what comes after?
That question hasn't been answered yet.
New here? This is AIHealthTech Insider — AI healthcare signals every week, plain English, no jargon. Subscribe free below.
Sponsored
ChatGPT gives you generic answers because you give it generic prompts.
You know the fix: longer prompts, more context, clearer constraints. But typing all that takes five minutes per prompt, so you shortcut it. Every time.
Wispr Flow lets you speak your prompts instead of typing them. Talk through your thinking naturally — include context, constraints, examples — and get clean text ready to paste. No filler words. No cleanup.
Works inside ChatGPT, Claude, Cursor, Windsurf, and every other AI tool. System-level, so there's nothing to install per app. Tap and talk.
Millions of users worldwide. Teams at OpenAI, Vercel, and Clay use Flow daily. Free on Mac, Windows, and iPhone.
⚡ Quick Hits
🔸AI spotted pancreatic cancer up to 3 years before doctors could.
Mayo Clinic's REDMOD AI analyzed routine CT scans, the kind already taken for other reasons and detected pancreatic cancer up to 3 years before clinical diagnosis.
Image: AI-generated, AIHealthTech Insider
The numbers are hard to ignore.
It identified 73% of pre-diagnostic cancers at a median of 16 months before diagnosis. In scans taken more than two years before diagnosis, it found nearly three times more early cancers than specialists reviewing the same scans without AI.
Here's why that matters: more than 85% of pancreatic cancer patients are diagnosed after the disease has already spread. Five-year survival is below 15%.
The cancer was there. The scan was there. Nobody could see it.
The AI could.
🔸AI just read a beating heart better than most cardiologists.
Carnegie Mellon and Cleveland Clinic built CMR-CLIP — an AI that interprets cardiac MRI, the most complex imaging in medicine, without any manually labeled training data.
Image: AI-generated, AIHealthTech Insider
It was trained on 13,000+ scans. More than most cardiologists see in an entire career.
The accuracy: 99% on certain heart conditions. 35% better than general-purpose AI models.
Translation: the AI has already seen patterns across more hearts than any human could hold in memory.
🔸The heart attack warning hiding in your routine ECG.
A study published in JACC: Advances followed 1.7 million patients. Researchers at the University of Washington built an AI that reads standard ECG and health record data and reduces cardiac arrest risk prediction from 1 in 1,000 down to 1 in 100.
Image: AI-generated, AIHealthTech Insider
Most cardiac arrests happen in people with no known heart disease.
A 12-lead ECG costs almost nothing. It exists in clinics worldwide.
Know someone in healthcare, medicine, or AI? Forward this to them. They can subscribe free here →
🌍 Beyond AI
Women and Alzheimer's: the risk gap is bigger than anyone thought.
A UC San Diego study published May 19 analyzed 17,000 adults. The finding: common risk factors — high blood pressure, depression, physical inactivity — damage women's brains harder than men's.
Image: AI-generated, AIHealthTech Insider
Nearly two-thirds of the 7 million Americans living with Alzheimer's are women.
Most prevention guidelines were built on research done mostly on men.
That's not a small detail. That's the whole problem.
And there's one risk factor on the list that's both the most damaging and the most fixable. Most women don't know it's there.
📊 Stat of the Week
$2.1 billion — what Isomorphic Labs raised in a single Series B round. One company. One round. AI drug discovery.
The detail that matters more: 54% of all digital health investment in 2025 went to AI-enabled companies — up from 37% the year before. Experts say 2026 will concentrate that money into even fewer hands.
🐰 Rabbit Hole
Two links worth falling into this week:
Cardiac arrest kills most people who had no prior warning. An AI just changed that using a test that costs almost nothing and exists in every clinic worldwide. → newsroom.uw.edu
AI is now the first thing millions of patients interact with before seeing a doctor. But HHS just flagged a problem nobody in Silicon Valley is talking about. → medcitynews
💡 The One Thing
One scan. One ECG. One AI finding a treatment a whole team of specialists couldn't.
This week's stories share a quiet pattern: AI is getting faster at catching what humans miss — especially for women, especially for rare diseases, especially in places that couldn't afford the old tools.
The harder question is still the same every week: who gets access first, and who finds out last?
That's what this newsletter exists to answer. Every Sunday. Plain English. No jargon.
If someone forwarded this to you — you can get it free every week below.
Image: AI-generated, AIHealthTech Insider
If a single MRI could tell you whether you're likely to develop Alzheimer's in the next 10 years, would you want to know?
Stay ahead: AI Healthcare News!
This is just a glimpse of the AI healthcare revolution. Subscribe for exclusive updates on medicine’s future!
