LLM's
Every article we have published: research summaries, product thinking and developments in health AI.
LLM's · 363 articles

AI Spotters Catch Radiology Text Errors in Seconds
A general-purpose AI model caught internal text errors in radiology reports almost ten times faster than human radiologists while outperforming them on...

Doctors Miss AI Errors in Emergency Discharge Summaries
Human oversight fails to catch specific AI errors before emergency discharge papers reach patients.

Clinicians Created a Tool to Grade Medical AI
A new 10-point evaluation tool reveals that even expert clinicians struggle to agree on whether AI-generated health advice is acceptable.

AI Medical Suggestions Cost Triple Human Doctors
Large language models recommend clinical plans that cost more than triple what human physicians order, driven by defensive over-testing.

Synthetic Data Trains Open AI for Spanish EHRs
Off-the-shelf artificial intelligence tools fail to extract complex psychiatric symptoms from Spanish clinical notes without extensive retraining.

AI Models Recommend Triple the Medical Costs
Large language models default to expensive defensive medicine, threatening to balloon healthcare spending without improving patient outcomes.

AI Personas Fail to Predict Real Patient Confusion
Using AI models to simulate patient feedback on discharge notes risks masking genuine patient confusion, particularly for lower-literacy groups.

AI Pipeline Resolves Conflicting Penile Cancer Guidelines
A new software workflow combines three AI models with human experts to automatically spot conflicting medical guidelines and missing research.

Google releases open medical vision model MedGemma
Open-weight medical AI models are proving that domain-specific fine-tuning can outperform massive general systems while requiring significantly less training data.

Atomic Fact Checking Cuts Medical AI Errors
Breaking AI responses into single statements catches critical medical errors that standard retrieval systems miss.

LLMs Can Build Medical Exam Cases Automatically
Generative AI can draft full clinical examination stations in a single prompt, but clinical accuracy gaps require strict expert oversight.

AI Models Curb Low-Value Care Lapses
Large language models usually resist ordering low-value medical tests, but occasional lapses still risk driving unnecessary diagnostic cascades.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.