medical-ai
25 posts tagged medical-ai.
- Dense rewards made clinical agents ask better questions
- Radiology agents are only as good as their tool catalog
- MedGraph treats medical memory as patient state, not chat history
- MedPhysBench Tests Whether Medical AI Can Catch the Mistakes It Can Solve
- DiabAgent tests medical agents where mistakes compound
- LLM clients look useful for counselling practice, with limits
- Clinical notes as an early warning layer for hospital mental health risk
- Medical exam scores are not enough for clinical LLMs
- RAG Scores Move When Ground Truth Gets Better
- BatchBench puts biomedical vision models through the real failure mode
- An AI Agent That Reproduces Cancer Studies and Checks Where They Wobble
- AI Cancer Claims Need Milestones, Not Cigarette Theater
- Food Processing Is a Health Signal, Not Just a Nutrition Label Detail
- Prompt optimization should chase ranking, not accuracy, in imbalanced clinical AI
- When Rewording the Answer Key Reshuffles the Leaderboard
- CareMirror puts caregiver consent at the center of dementia AI
- K-Bench tests mental health chatbots where generic safety evals do not
- The Hallucination Detector That Doesn't Transfer to Your Domain
- NOAH models patient records as timelines, not snapshots
- Bare assertions are a weak spot for medical reasoning models
- Anatomy-informed networks put clinical constraints before more data
- Splitting the reward: how G-CARL grades medical explanations for facts and for tone
- Alzheimer’s surgery claims need evidence before amplification
- AMIE’s video consult result is about perception, not replacement
- What Actually Makes Medical Image Encoders Interoperable