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

UK to accept US medical device approvals
The UK is abandoning regulatory isolationism to keep its healthcare system from falling behind.

Gut bacteria predict hospital stays for cirrhosis patients
Analyzing the gut microbiome could prevent costly hospitalizations for patients with advanced liver disease.

Nvidia-Backed Iambic Therapeutics Files For IPO
An AI-native biotech is testing public market appetite, signaling a shift from tech hype to clinical execution.

Top Performing AI Fails Clinical Reality Check
A new study reveals that training AI to ace medical benchmarks actually makes its clinical reasoning worse, exposing a dangerous gap in...

Why Chatbot Diagnosis Is Still Highly Risky
Patients who swap doctors for chatbots are playing a dangerous game of probability with their health.

Fully Automated Abstraction of Longitudinal Breast Oncology Records with Off-The-Shelf Large Language Models
Off-the-shelf artificial intelligence can now parse thousands of pages of messy medical records to build research-grade cancer datasets, matching the accuracy of...

The Pulmonology AI Report — September 2026
Imaging-based development and validation of artificial intelligence models for lung adenocarcinoma precursor lesions and early lung adenocarcinoma presenting as pulmonary nodules

How AI Solves the EHR Documentation Bottleneck
Doctors spend hours typing notes after their shifts end, but automating real-time chart completion could finally end the pajama-time documentation crisis.

AI finds which kidney patients need SGLT2 inhibitors
A new causal machine learning analysis reveals that standard population-level prescribing guidelines for diabetic kidney disease are masking critical, individual-level treatment failures.

AbbVie Bets on Iambic’s New AI Model
Big Pharma is no longer just experimenting with AI; it is embedding massive neural networks directly into the core of drug discovery.

AI ECG predicts genetic heart disease risk
A new study shows artificial intelligence can read standard electrocardiograms to spot a deadly genetic heart condition before traditional symptoms appear.

AI Solves the Clinical Trial Data Bottleneck
Clinical trials are stalling under the weight of unstructured data, but AI is shifting from an experimental tool to an operational necessity.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.