Yesil Science / Blog

LLM's

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

3,642articles so far

LLM's · 363 articles

AI Ethics

AI misses suicide risk in long conversations

New research reveals that as digital therapy sessions drag on, artificial intelligence loses its ability to detect suicidal ideation, even as human...

Cardiology

Artificial intelligence-based ECG reconstruction error as a continuous predictor of all-cause mortality: a multi-cohort retrospective validation study

By measuring what an artificial intelligence model fails to reconstruct in an electrocardiogram, researchers have found a highly generalizable way to predict...

Critical Care

AI agents draft safe ICU handoff summaries

A new multi-agent AI pipeline proves that the safest way to use language models in hospitals is to stop treating them as...

Infectious Diseases

AI still lags behind doctors on antibiotic choices

A new double-blind trial reveals that specialized medical AI still cannot match human doctors when prescribing antibiotics for complex hospital infections.

LLM's

Chatbots fail to ease patient decisional conflict

A new clinical trial reveals that giving patients ChatGPT before or after their specialist visits does not reduce their anxiety or help...

LLM's

AI reconstructs baby heart signals without skin damage

A new AI model reconstructs missing neonatal heart signals using light-based sensors, bypassing the need for irritating skin adhesives in intensive care.

LLM's

Automated Disease Activity Assessment in Systemic Lupus Erythematosus Using Privacy-Preserving Large Language Models

Automating lupus tracking with open-source language models could finally bring standardized disease monitoring to busy clinics.

Digital Health Education

LLMs Fail Local Speech in Nigerian Clinical Test

A new clinical benchmark reveals that large language models fail frontline health workers unless their queries are translated into English first.

Hospital Management

AI discharge summaries target doctor burnout

A new pilot shows that automating clinical notes saves little time but dramatically lowers cognitive fatigue.

Drug Discovery

AI agent runs biomedical research tasks autonomously

A new AI agent named Biomni can design and run its own lab experiments, shifting the bottleneck of medical discovery from human...

LLM's

AI matches radiologists in emergency head CT triage

A new AI model drafts emergency head CT reports that radiologists cannot tell apart from human work.

Hospital Management

AI Scribes Move to the Nursing Ward

Hospitals are finally realizing that relieving doctor burnout is only half the battle if nurses are still drowning in digital paperwork.