A doctor comments on Microsoft's new medical diagnosis AI

What did they create? Two key innovations:
1. SDBench: A testing environment using 304 real medical mysteries from NEJM where AI starts with just "29yo woman with sore throat" and must decide what to ask/test next

2. MAI-DxO: An AI system that simulates 5 doctors working… pic.twitter.com/G8orzGAuOk

— Dr. Dominic Ng (@DrDominicNg) June 30, 2025

MAI-DxO isn't a new model but instead a framework built on top of existing LLM's (ChatGPT, Claude, Gemini).

How does this framework work?
It asks the LLM to simulate a virtual panel of 5 specialised AI doctors:
Dr. Hypothesis (tracks diagnoses)
Dr. Test-Chooser (selects optimal… pic.twitter.com/sYCV6zKmuU

— Dr. Dominic Ng (@DrDominicNg) June 30, 2025

But there's five issues I see:
1. They used ZERO healthy patients
95% of sore throats are viral and this AI was only tested on incredibly rare diagnostic cases.

We don't know if it will order biopsies on every patient with a sore throat "just to rule out rhabdomyosarcoma."

— Dr. Dominic Ng (@DrDominicNg) June 30, 2025

3. The physician comparison was rigged
Docs were banned from:
❌ Googling symptoms
❌ Consulting colleagues
❌ Using UpToDate/medical databases
❌ Calling specialists

That's not how we practice!!
It's like testing a chef who can't use recipes or taste their food.

— Dr. Dominic Ng (@DrDominicNg) June 30, 2025

5. No "When to Stop" Testing
Great doctors know when NOT to test. This AI was never evaluated on:

"This headache is just stress"
"Let's wait and see"
"More tests will cause more harm than good"

The benchmark rewards finding zebras, not recognising horses.

— Dr. Dominic Ng (@DrDominicNg) June 30, 2025

Final thought: We don't need AI that can diagnose every rare disease. We need AI that knows when to diagnose and when to reassure. That's the real art of medicine.

But what do you think?

— Dr. Dominic Ng (@DrDominicNg) June 30, 2025

If you liked this post please follow me @DrDominicNg and retweet.

It takes me some time to read and write these posts so I'd love to get more people's thoughts on it!

I've also just started a new newsletter on neuroscience:https://t.co/l0Ii2PPLCg

— Dr. Dominic Ng (@DrDominicNg) June 30, 2025