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

Eli Lilly Expands TuneLab to Biologics
Big Pharma is learning that keeping proprietary data locked in a vault is no longer the fastest way to win the drug...

Google AI BAAs Do Not Guarantee Data Safety
A signed business associate agreement with a tech giant does not mean your patient data is safe from AI training models.

New Skin Cancer AI Beats Nineteen Dermatologists
A new clinical model outperforms specialists in diagnosing skin cancer, but its hidden failure modes reveal why deploying diagnostic AI remains a...

Machine Learning Fixes Liquid Biopsy False Alarms
A new machine learning model tackles the biological noise threatening to derail non-invasive cancer testing.

Large language models enable consensus-level interpretation in metagenomic diagnostics
A new study shows that local language models can analyze complex genomic data just as accurately as panels of medical experts.

The $450 Million Bet on Consumer Diagnostics
A massive new capital injection proves that venture capital is bypassing traditional doctors to sell health tracking directly to anxious consumers.

Algorithm predicts brain bleed recovery using brainstem line
A simple anatomical marker combined with machine learning could change how clinicians predict long-term recovery after a severe brain bleed.

AI turns surgical video into hospital revenue
Hospitals are losing millions because surgeons are terrible at paperwork, but the solution is not another dictation tool—it is the video feed...

Doctors adopted a specialized AI for bowel disease
A new clinical trial shows that doctors will actually use generative AI in daily practice, provided it is chained to strict medical...

Who Pays When Medical AI Fails?
Clinicians are being forced into a dangerous double-bind as health systems deploy artificial intelligence faster than courts can assign blame.

GSK Bets Big on Cellular Foundation Models
Big Pharma is shifting its AI strategy from targeting specific diseases to funding the underlying operating system of human biology.

AI cuts unnecessary tests for rare skin cancer
A new deep learning tool could stop pathologists from ordering endless, defensive tests to rule out a mimic of common skin rashes.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.