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

Whistleblower Lawsuit Exposes Healthcare AI Safety Gaps
A federal whistleblower lawsuit alleging a massive cover-up of AI error rates challenges the narrative of seamless clinical automation.

AI Detects Blood Cancers From Routine Blood Tests
A new AI model turns the standard complete blood count into an instant classifier for leukemia and severe infections, bypassing the slow...

Penn Medicine Puts AI in Virtual Triage
Health systems are outsourcing the clinical interview to algorithms, but the real test is whether doctors actually regain their time.

Chatbots fail to ease patient decisional conflict
A new clinical trial reveals that giving patients ChatGPT before or after their specialist visits does not reduce their anxiety or help...

Evernorth Bets $100 Million on AI Pharmacy
Specialty drug costs are eating health insurance budgets alive, forcing payers to automate the back office just to survive the margin squeeze.

AI Predicts Veteran Mortality Using Outpatient Billing Codes
A new model bypasses complex clinical charts to predict long-term death risk using nothing but raw billing codes.

Turning Failed Clinical Trials Into AI Models
Biotech companies are finding a second life for failed drug data, but recycling bad trials into predictive algorithms carries hidden risks.

AI reconstructs baby heart signals without skin damage
A new AI model reconstructs missing neonatal heart signals using light-based sensors, bypassing the need for irritating skin adhesives in intensive care.

Federal Health Agencies Are Rushing Into AI
Federal health agencies are rapidly adopting artificial intelligence, but their rush to deploy these tools is outpacing their willingness to govern them.

AI tackles the prostate MRI bottleneck
Doubling scanning capacity is useless if there are no radiologists left to read the scans.

Automated Disease Activity Assessment in Systemic Lupus Erythematosus Using Privacy-Preserving Large Language Models
Automating lupus tracking with open-source language models could finally bring standardized disease monitoring to busy clinics.

AI Exposes Hidden Veteran Self-Harm Data
Electronic health records are failing vulnerable patients because standard billing codes ignore the messy reality of clinical notes.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.