Yesil Science / Blog
Blog
Every article we have published: research summaries, product thinking and developments in health AI.
Latest articles

AI maps damaged muscles using physics rules
A new deep learning model uses the laws of physics to map deformed muscles from scarce MRI data, proving that AI does...

The Health AI Brief — Week of September 21, 2026
Simple AI beats complex models in lung cancer

AI adoption rises but clinicians fear brain drain
As healthcare systems rush to integrate artificial intelligence, the hands-on expertise of doctors and nurses is facing an unexpected threat.

Brain Drift Crushes Standard Seizure AI Models
A major gap exists between how seizure-predicting algorithms perform in lab simulations and how they handle the chaotic reality of the human...

Patients Are Recording Their Doctors With AI
As clinicians adopt artificial intelligence to draft medical notes, patients are quietly deploying their own AI scribes to police the conversation.

Gene programs predict lupus nephritis drug response
A new machine learning analysis shows that a patient's response to lupus nephritis drugs can be predicted by tracking as few as...

A Dissolvable Implant to Fix Glaucoma Surgery
Glaucoma surgery fails up to forty percent of the time because patients cannot manage their own recovery.

AI predicts brain bleeding after stroke using MRI
A new machine learning model shows that combining high-resolution MRI with clinical data can spot patients at risk of dangerous brain bleeding...

Why Patient Portals Are Failing Security
When patient portals become the perfect disguise for cybercriminals, health systems must realize that warning users to "be careful" is no longer...

AI predicts breast cancer survival without mimicking pathologists
New clinical data shows that AI models do not need to mimic human pathologists to accurately predict breast cancer outcomes.

AI predicts which cancer patients face severe toxicity
A new AI-driven analysis of 50,000 patients reveals that severe cancer treatment side effects are not random mishaps but predictable genetic events.

A Leaked Poster Shakes AI Drug Valuation
A premature data leak reveals that in AI drug development, information control is just as volatile as clinical efficacy.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.