TOPIC
AI
3 entries across the knowledge base
Model governanceWho is accountable when the model is wrong, how you'd know, and what makes it stop. Governance is not paperwork around AI — it is the part that makes AI usable in a hospital at all.article · 8 min · practitionerLLM fundamentalsWhat a large language model actually does, in the only terms that matter clinically: it predicts plausible text. Everything useful and everything dangerous about it follows from that one fact.article · 7 min · foundationClinical decision support AIRule-based CDS fires when a condition is met and can always explain itself. AI-based CDS predicts — and the shift from 'because rule 14' to 'because the model said 0.83' changes what safety even means.article · 8 min · practitioner