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

Mayo Clinic Embeds AI Decision Support in EHR
Point-of-care medical reference is shifting directly into physician workflows to reduce cognitive burnout.

PCOS Miscarriage Risk AI Fails Real World Test
A machine learning model accurately ranked miscarriage risk for pregnant patients with PCOS, but sharp performance drops mean it cannot guide treatment...

AMA AI Liability Shift Exposes EHR Logging Deficits
Hospitals face unprecedented legal exposure when clinical AI causes harm if data logs cannot prove human oversight.

AI Predicts Postoperative Mortality in 11 Milliseconds
A dynamic deep learning architecture accurately flags surgical mortality risk before an operation ends, but site-specific calibration issues prevent immediate clinical deployment.

Predicting Surgical Kidney Injury With Federated AI
Preventing surgical complications requires accurate risk prediction before a patient ever reaches the operating room.

AI Delirium Model Survives External Hospital Testing
A multimodal machine learning model for delirium risk maintained strong accuracy when deployed live at a separate hospital without retraining, though high...

AI Chatbots Fail to Lower Maternal Mental Distress
Giving new and expectant mothers access to a generative AI chatbot does not reduce anxiety or depression symptoms over a full year.

AI Stroke Tools Miss Half of Distal Occlusions
Relying on artificial intelligence to clear stroke patients can leave deadly arterial blockages completely undetected.

AlphaFold3 Predicts T Cell Targets From Sequence
A new computational pipeline models T cell receptors to predict target antigens before lab validation begins.

Lab-Based AI Fails to Beat Biomarker in COPD
A machine learning model triages heart failure in COPD patients using basic blood tests, but it misses too many cases to replace...

HHS AI Rule Shifts Evaluation Risk to Hospitals
Deregulation reduces developer compliance costs but forces health systems to build their own clinical AI vetting mechanisms.

Four Proteins Improve AI Prediction of Kidney Disease
Adding four blood proteins to standard demographic data improves long-term chronic kidney disease prediction models.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.