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

AI predicts dirty margins before breast cancer surgery
A new ensemble AI model predicts positive surgical margins before breast-conserving surgery, but its performance drop in external testing highlights the ongoing...

IVF Clinics Turn to AI for Embryo Selection
A new clinical deployment in California is putting AI-driven embryo selection to its first real-world test.

Circulating protein profiling identifies prognostic biomarkers in amyotrophic lateral Sclerosis
Measuring a single protein has been the gold standard for tracking ALS, but a new multi-protein signature suggests we have been missing...

The Vulnerable Back Door of Medical Supply Chains
When a major medical supplier loses control of its patient databases, the failure rarely starts in its own server room.

AI predicts breast cancer spread to the brain
A new multi-center model uses basic clinical data to flag brain metastasis before symptoms appear, challenging the need for expensive, complex biomarkers.

Big Pharma Pools Data for Antibody AI
AI drug discovery models are starving for physical data, forcing fierce competitors to pool their proprietary secrets.

AI predicts lung inflammation before immunotherapy starts
A new foundation model uses baseline CT scans to flag which lung cancer patients are likely to develop life-threatening lung inflammation from...

Paying for Clinical AI Without Bloating Budgets
Healthcare is funding clinical artificial intelligence through a broken payment system that rewards volume over value, threatening to spark an administrative arms...

AI translates ECG waves into clinical text
A new model bypasses rigid labels to turn raw cardiac waveforms directly into human-readable clinical narratives.

Why Radiologists Are Rejecting Standalone AI
The flood of FDA-approved radiology AI is hitting a wall of clinical rejection because developers forgot a basic rule of medicine: do...

AI spots hidden heart fat on standard ultrasounds
A new AI model extracts metabolic risk data directly from routine heart ultrasounds, bypassing the need for expensive CT scans.

Regulating the Billion-Record Health Data Boom
As national health data exchange scales at a dizzying pace, the federal government is shifting its focus from building connections to policing...
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.