Sitemap
Every public page, in one place.
The community pages and the full reading library. The machine-readable version lives at /sitemap.xml.
The community
Reading & reference
Policies
The library
Every published article — each carries a byline, a named reviewer, an updated date, and numbered primary sources.
Briefing3
Evaluation13
- HealthBench Professional, explained: how OpenAI now measures clinician-facing AI
- LLM evals vs clinical evaluation: two different instruments
- AUROC explained for clinicians
- Calibration curves for clinicians
- Dataset shift and model decay
- How to read an AI validation study
- How to read an FDA clearance summary
- Internal vs external validation
- Prospective vs retrospective evaluation
- Sample size and confidence intervals in AI studies
- Subgroup performance and bias audits
- Ten red flags of an overfit model claim
- What benchmark scores don't tell you
Ambient AI11
- Ambient AI reaches nursing documentation: what the inpatient turn means
- AI scribe vendor landscape 2026
- AI scribes: what the evidence actually shows
- Ambient AI ROI calculator: a transparent model
- Documentation time and burnout: what the evidence shows
- Hallucination and omission rates in AI scribe notes: what the studies measured
- The Kaiser Permanente 2.5-million-encounter ambient scribe deployment, analyzed
- Coding, billing, and upcoding risks of ambient AI notes
- Do ambient AI scribes need FDA regulation?
- An implementation checklist for medical groups deploying ambient AI scribes
- Patient consent for ambient recording, by jurisdiction
Agentic AI10
- Agent safety frameworks for clinical settings
- Agents in nursing workflows: documentation, handover, and the virtual-nursing evidence
- Designing human oversight for clinical agents
- Documented agentic deployments in healthcare: a tracker
- EHR-integrated agents: what it takes, and what the evidence shows
- How to evaluate an agent before deployment
- MCP and interoperability for hospital agents
- Prior-authorization agents: what the CMS rule and the evidence actually say
- Revenue-cycle and coding agents: accuracy, denials, and the compliance stakes
- What is agentic AI in healthcare
Regulation16
- The CMS WISeR Model, explained: AI prior authorization reaches traditional Medicare
- EU AI Act on 2 August 2026: what now applies to healthcare
- The first FDA-cleared patient-facing LLM: what UpDoc's 510(k) actually says
- US state laws on AI mental-health chatbots: a tracker
- Building an algorithmovigilance program
- EU AI Act for healthcare: a living timeline
- The FDA AI-enabled device list: a statistics tracker
- The FDA's total-product-lifecycle draft guidance for AI devices, explained
- HIPAA and LLMs: what is permitted
- The hospital AI governance committee playbook
- Liability when clinical AI errs
- Predetermined Change Control Plans in practice
- Transparency and labeling requirements for clinical AI
- The UK MHRA AI Airlock, explained
- US state laws on AI scribes: a tracker
- WHO guidance on large language models in health
Specialties12
- AI in cardiology: what is cleared and evidenced in 2026
- AI in Emergency Care
- AI in hospital operations: a 2026 evidence guide
- AI in nursing: a 2026 evidence guide
- AI in oncology: what the evidence actually shows
- AI in pathology: what is cleared and evidenced in 2026
- AI in pediatrics: a 2026 guide
- AI in pharmacy: a 2026 evidence guide
- AI in primary care: exam scores versus patient outcomes
- AI in psychiatry and mental-health chatbots: a 2026 guide
- AI in radiology: what is cleared and evidenced in 2026
- AI in surgery: a 2026 guide
Comparisons9
- The best AI in healthcare courses in 2026, compared
- AI scribe head-to-head comparison
- AI tools for medical education compared
- Clinical reference AI compared
- Imaging AI marketplaces compared
- Medical coding AI compared
- Open vs closed models for hospital deployment
- Patient communication drafting tools compared
- Patient triage chatbots compared
Glossary20
- Agentic AI
- AI hallucination in clinical contexts
- Algorithmovigilance
- Ambient AI scribe
- Clinical decision support system
- Clinical LLM
- De-identification vs anonymization
- External Validation
- Software as a Medical Device (SaMD)
- Federated learning in healthcare
- Foundation model
- Human-in-the-loop
- Model calibration
- Model Context Protocol in health IT
- Model drift
- Predetermined Change Control Plan (PCCP)
- Prompt injection in clinical systems
- Retrieval-augmented generation (RAG)
- Sensitivity, specificity, and AUROC
- Synthetic patient data
Statistics8