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

AI predicts future lab results from patient records
A new transformer model can simulate how a patient's lab values will react to specific drugs before they are even prescribed.

Oracle Puts OpenAI in Patient Portals
Giving patients direct access to AI-translated medical records is a bold play to win the EHR wars, but it shifts a massive...

AI predicts patient paths after emergency room discharge
A new generative model beats traditional machine learning at predicting which discharged emergency patients will return to the hospital.

AI Triages Rheumatology Referrals as Well as Doctors
A new study shows that smart prompting makes cheap, small AI models triage patients just as safely as expensive ones.

How FHIR data format changes AI clinical quality
Feeding raw medical data directly into clinical AI models might be degrading their performance without anyone noticing.

AI learns genetic disease boundaries from health records
An attention-based AI model has mapped the genetic boundaries between neurological and psychiatric diseases using nothing but raw electronic health records.

A Multimodal large language model-based triage tool for osteoporotic vertebral compression fractures using posture and movement videos
A new AI model screens for painful spinal fractures using simple home videos instead of immediate, expensive hospital scans.

AI finds clinical trial results better than humans
A new AI tool proves that human error, not machine limitation, is the biggest obstacle to tracking missing clinical trial data.

AI turns patient texts into clinical data
A new startup is betting that conversational AI can bridge the dangerous information gap between doctor visits for chronic disease patients.

AI summaries fail to improve patient scan comprehension
Patients who read AI-generated summaries of their brain scans feel significantly more confident, but they do not actually understand their medical results...

AI reads triage notes to spot strokes
A local language model can flag stroke patients directly from emergency room triage notes, bypassing the need for cloud-based data sharing.

Towards Accessible Radiological Image Analysis via Local Agentic Framework: Validation in Mammography
A new study shows that a consumer-grade computer running an LLM agent can build world-class medical AI without elite engineering teams.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.