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

AI discharge summaries outperform doctors in London trial
Rushed physicians routinely write incomplete discharge summaries, but automated drafts generated from electronic health records cut downstream safety risks while winning clinical...

AI Chart Summaries Cut Radiologist Workloads
Automated clinical chart summaries are shaving crucial minutes off imaging prep without compromising diagnostic safety.

AI Models Flunk Complex Pharmacy Exam Questions
High scores on basic medical recall hide critical AI failures in complex clinical reasoning and visual data.

ER Doctors Would Act on Fake AI Abstracts
Polished writing from AI models tricks acute care physicians into trusting fabricated scientific claims.

DeepSeek Matches GPT Accuracy But Fails Safety Tests
Open-source AI models can match proprietary giants in diagnostic skill, but their safety guardrails collapse under deliberate pressure.

Fine-tuned LLM accelerates trial bias reviews
Pairing a fine-tuned language model with clinician reviewers cuts manual overhead in clinical trial appraisals without sacrificing judgment accuracy.

MDCalc CrossCover Verifies Clinical Generative AI
Clinicians using generative AI for quick answers risk acting on convincing fabrications.

Open AI Models Match Commercial LLMs on Notes
Open-weight AI models can extract clinical comorbidities from medical text just as accurately as proprietary systems like GPT-4 and Claude.

Splitting AI Knowledge and Experience Boosts TCM Prescribing
Training AI on general medical textbooks actually hurts its ability to mirror expert prescribing habits.

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

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.

Specialized Fine-Tuning Helps AI Match Counselor Responses
Structured counseling data and targeted prompting allow smaller open-source models to perform comparably to human therapists in single-turn dialogue benchmarks.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.