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

AI Will Make Healthcare More Expensive First
The promise of artificial intelligence in medicine comes with a hidden tax: a short-term surge in healthcare spending driven by hyper-efficient billing.

AI identifies malaria species in blood smears
A new hierarchical deep learning framework separates malaria species from healthy cells with near-perfect accuracy, even when clinical data is highly imbalanced.

Radiology practices are building their own AI
Radiology groups are no longer waiting for software vendors to build clinical AI; they are becoming the software companies themselves.

AI predicts oral cancer risk using saliva
A new neural network detects oral cancer risk with near-perfect accuracy, but its real value lies in exposing how lifestyle habits and...

AI vessel segmentation made radiologist diagnoses worse
A highly accurate deep learning tool designed to help radiologists spot vertebral artery tears actually degraded their diagnostic performance.

Why Sending Health Data Is Not Enough
Connecting hospital databases was supposed to solve the digital health puzzle, but generative AI is proving that raw data pipelines are useless...

Uncoded Clinical Features from Multilingual Electronic Health Records in Catalonia: Development and Validation Study
A new hybrid pipeline proves that small, local AI models can extract hidden clinical data from health records without risking patient privacy...

Basecamp Research pivots from data to drugs
A massive genomic database is worthless if it cannot cure human disease.

AI predicts sleep apnea using body geometry
A new AI model analyzes complex bodily rhythms to spot severe sleep apnea without the need for expensive overnight lab tests.

Medicare Targets Remote Patient Monitoring Vendors
A battle over who actually delivers virtual care is forcing a reckoning for the entire digital health industry.

AI writes eye ultrasound reports with high accuracy
A new multimodal AI system automatically drafts ophthalmic ultrasound reports and outperforms leading commercial models in clinical question-answering.

The Edge Diagnostic Shift
Medical AI developers are increasingly deploying diagnostic algorithms onto low-cost, portable hardware like smartphones and standard microscopes to bypass centralized hospital facilities.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.