Category
Health AI
Machine learning and language models in clinical settings, with a focus on evidence, bias and oversight.
4 articles
Newest
Ambient Documentation Tools in the Exam Room: Promise, Limits and Consent
Ambient tools that draft clinical notes from a recorded conversation can reduce typing, but they add questions about accuracy, consent and review.
Hospital Risk Scores and the Alert Problem: Why Good Predictions Still Get Ignored
Early-warning models for hospital patients only help if the alerts they raise fit into how nurses and physicians actually work.
Bias Audits for Clinical Algorithms: What a Useful Review Includes
A useful bias audit compares model performance across patient groups and checks what the model was trained to predict.
Clinical AI Assistants: What Evidence to Ask For Before Deployment
Hospitals evaluating AI assistants for clinicians should ask for validation on their own patients, not only a vendor demo.