Yesil Science / Blog

LLM's

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

3,641articles so far

LLM's · 363 articles

LLM's

AI medical reports increase doctor editing workloads

Large language models can draft medical reports, but high error rates mean clinicians spend their saved time correcting the software's mistakes.

LLM's

AI agents fail at independent clinical data analysis

A new study reveals that while AI agents can draft brilliant research plans, they make silent, repetitive coding errors that require human...

AI Ethics

Doctors distrust tech companies to regulate clinical AI

Clinicians are quietly adopting generative AI for administrative tasks while deeply distrusting the tech companies building these tools to police themselves.

LLM's

Cheap AI models beat specialized clinical software

Hospitals trying to automate lung cancer screening eligibility no longer have to choose between speed, cost, and clinical accuracy.

Hospital Management

AI discharge summaries beat human drafts in trial

Automated discharge summaries for long hospital stays reduce dangerous information gaps without increasing patient risk, challenging the assumption that AI cannot handle...

Drug Discovery

AI Enzyme Discoveries Face Real World Disputes

An AI agent's first biological discovery has immediately collided with a human authorship dispute, signaling a messy future for automated science.

LLM's

AI Reads Autopsy Reports to Classify Brain Diseases

An AI trained on autopsy text can spot rare brain diseases with surprising accuracy, but it fails completely when pathologies mix.

LLM's

LLMs predict cancer outcomes from clinical notes

AI can now scan messy hospital notes to group cancer symptoms and predict which patients face the highest risk of death or...

LLM's

Perspective independence, more than personas, drives LLM teams – and where they reverse

Splitting medical AI into a team of specialized virtual doctors actually hurts diagnostic accuracy when facing real-world emergency room cases.

LLM's

AI-designed shoulder rehab matches human therapy plans

A triple-masked trial shows that AI-assisted exercise plans perform just as well as human-designed physical therapy for shoulder pain.

LLM's

When patients bypass doctors for AI lab readings

Desperate to skip long wait times, patients are pasting highly sensitive medical data into general-purpose chatbots.

LLM's

AI fails a simple medical test trick

A simple change to multiple-choice questions reveals that medical AI models may rely on pattern recognition rather than actual clinical reasoning.