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

Samsung Smart Ring Tracks Hourly Sleep Disruption
Consumer wearables are shifting from passive wellness tracking toward quantified clinical screening.

Machine Learning Finds No Hypothermia Benefit After Cardiac Arrest
Machine learning models applied to landmark trial data show cooling cardiac arrest patients to 33 °C offers no hidden benefit to specific...

AI Cardiac MRI Beats Clinicians at Predicting Mortality
Algorithms trace heart contours better than human eyes, but the actual survival advantage in clinic remains modest.

MRUSuNet Model Improves Prostate Cancer Spatial Volume Detection on Ultrasound
Combining MRI and transrectal ultrasound in a single AI model improves 3D spatial volume detection of prostate cancer over standard radiologist MRI...

AI Cardiac Scans Outperform Clinicians in Predicting Survival
Automated heart MRI measurements predict long-term patient mortality better than human experts while cutting reading times from minutes to seconds.

AI model predicts wasting in dialysis patients
By combining basic blood markers with machine learning, clinicians can now spot metabolic wasting in kidney failure patients before severe physical decline...

Medicare Automated Denial Pilot Triggers High Rejections
A federal experiment using algorithms to audit Medicare prior authorizations created operational turmoil while driving initial denial rates above fifty percent.

AI Maps Normal Spine Aging Across 22,979 Adults
Automated MRI analysis of tens of thousands of asymptomatic spines challenges how radiographers distinguish normal structural aging from painful spinal pathology.

AI Predicts Diabetic Foot Ulcer Care Outcomes
A multi-outcome AI model improved doctor recommendation quality scores in a 200-patient prospective trial.

The Health AI Brief — Week of November 2, 2026
AI Medical Suggestions Cost Triple Human Doctors

Compact AI Predicts Hepatitis B Risk With Less Data
Trimming clinical data inputs by four-fifths barely degrades AI performance when assessing chronic hepatitis B severity during hospital admission.

AI Predicts Fever Persistence in Cancer Patients
Predictive algorithms could curb unnecessary CT scans and antibiotic changes in cancer patients by identifying who will stop running a fever.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.