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

LUMANA: A Scenario-Based Field Validation of a Culturally Adapted AI System for Mental Health Screening in Sokoto State, Nigeria
An AI screening tool tested in Nigeria shows that local language translation and human oversight can bridge massive gaps in mental health...

Your medical records are leaving the clinic
Consumer health apps are racing to sync with your electronic health records, but they are stepping into a massive regulatory blind spot.

AI raises junior dentist accuracy to senior levels
A new clinical validation study shows that AI software bridges the diagnostic gap between novice and expert dentists, but struggles to catch...

AI radiology reporting bypasses hospital sales cycles
A major radiology practice is deploying its own AI reporting software to thousands of clinicians, bypassing the slow enterprise sales cycles that...

Hospital AI Tool Hallucinates Twelve Percent of Time
A new study reveals that while doctors find EHR-integrated generative AI easy to use, the software regularly invents clinical details and ignores...

The Gastroenterology AI Report — September 2026
EndoVLM: A Vision-Language Assistant for Gastrointestinal Endoscopy

Designing Drugs for Moving Targets
Traditional computer-aided drug design treats proteins like frozen statues, but human biology moves, making most early-stage drug candidates useless in the real...

AI turns ICU medical records into simple images
A new model bypasses complex data integration by flattening medical notes, scans, and heart rhythms into a single visual map.

AI Solves the Cancer Data Bottleneck
General AI models fail in oncology, but highly specialized software is quietly capturing the market by doing the tedious work doctors hate.

Eye scans help predict pregnancy diabetes risk
Adding retinal imaging to standard blood tests improves early gestational diabetes screening, but the incremental gain is smaller than AI optimists might...

Microsoft and Cortechs.ai Tackle Radiology Bottlenecks
Radiologists do not need more AI models; they need the models they already have to stop wasting their time.

A next-generation electronic frailty index leveraging deep learning on unstructured health records extends risk prediction across the full frailty spectrum
By analyzing the hidden text in medical records, a new AI tool spots life-threatening frailty decades before patients reach old age.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.