Yesil Science / Blog

Blog

Every article we have published: research summaries, product thinking and developments in health AI.

3,626articles so far

Latest articles

Blockchain

Instant Records Access Feeds Payer AI Agents

Patient-permissioned data sharing bypasses months of legacy payer exchanges to feed clinical AI on day one of coverage.

General Practice

Open AI Models Match Commercial LLMs on Notes

Open-weight AI models can extract clinical comorbidities from medical text just as accurately as proprietary systems like GPT-4 and Claude.

Digital Therapeutics

Digital CBT Cuts Insomnia in Cancer Survivors

A tailored sleep app doubled insomnia remission rates for cancer survivors compared to basic sleep education.

Machine Learning

AI CTA Analysis Predicts Mortality Post-TAVR

Automated tissue analysis on CTA scans predicts post-procedure mortality in minutes, addressing a major bottleneck in cardiac risk assessment.

Critical Care

Colorectal Cancer ICU Risk Model Fails External Validation

A machine learning model built to predict 28-day ICU mortality for severe colorectal cancer patients saw its predictive power plummet when tested...

Machine Learning

Abu Dhabi Deploys AI Assistant Across National Records

Abu Dhabi has embedded a generative AI physician assistant directly into its centralized health information exchange.

Machine Learning

High AUC hides calibration flaws in sleep AI

A machine learning tool accurately spots cognitive risk in sleep apnea patients, but faulty probability scoring proves why strong discrimination alone cannot...

AI in Genomics

Machine Learning Platform Optimizes Artificial MicroRNA Targeted Gene Silencing

Machine learning-guided design addresses complex sequence-structure relationships to optimize artificial microRNA efficacy and specificity for targeted gene silencing.

Wearables

AI Predicts Hypertensive Crises Three Days Early

Continuous biometric tracking can alert clinicians to dangerous blood pressure spikes long before patients land in the emergency room.

Infectious Diseases

AI Stratifies Tuberculosis Risk Without Costly Biomarkers

Clinicians can screen latent tuberculosis using epidemiological data instead of expensive blood work, but algorithmic risk scores cannot yet replace definitive diagnostic...

Wearables

FDA Clears AI to Fix Wearable ECG Flaws

Consumer smartwatches generate millions of heart readings every day, but clinicians waste valuable hours sorting through uninterpretable noise.

Machine Learning

CT Radiomics Classifies Vertebral Compression Fractures Accurately

A new CT-based machine learning model accurately differentiates fresh from old vertebral compression fractures, boosting junior radiologist performance without requiring MRI scans.