The Physician AI Handbook
Peer-Reviewed Evidence for Every Specialty
Welcome to The Physician AI Handbook
AI performance in real-world clinical settings often falls short of published validation studies. Written by a physician for clinicians, health system leaders, and anyone building or deploying clinical AI.
Three questions drive this handbook: What does the peer-reviewed evidence actually show? How do you evaluate claims against that evidence? What are the medico-legal implications when AI is wrong?
This resource is continuously updated as new research emerges.
Important Disclaimers
This handbook is for educational and informational purposes only. It does not provide medical advice, diagnosis, or treatment. AI systems discussed here are decision-support tools, not substitutes for clinical judgment.
Clinical use remains context-specific. Physicians should validate AI outputs before clinical use, follow applicable FDA and HIPAA requirements, and meet the standard of care in their jurisdiction.
Information may become outdated as AI tools, evidence, and clinical guidelines change. Verify recommendations with current clinical guidance before application.
This handbook does not provide legal advice. Consult qualified legal counsel for questions about malpractice, liability, and regulatory compliance.
Recent highlights
- 20 Nov AI provisions of the CY 2027 Medicare Physician Fee Schedule final rule (opens the source in a new tab) Medicare payment rules shape which AI tools practices can afford to adopt and what evaluation and monitoring work earns credit. In Healthcare Policy and AI Governance
- 20 Nov Goldsmith et al.: LLM-drafted discharge summaries and the verification paradox (opens the source in a new tab) A draft reviewers prefer under protected study conditions is not yet evidence of safer transitions of care at the bedside. In AI-Assisted Clinical Documentation
- 14 Nov Schlicker et al.: clinicians rarely noticed a failing AI assistant (opens the source in a new tab) Human sign-off is a weak safeguard against a degrading model; monitoring across many patients may catch failures that individual clinicians miss. In Integration into Clinical Workflow
- 13 Nov Anthropic guidance on building safety evaluations: what to ask about a grader (opens the source in a new tab) Before accepting a vendor safety claim, physicians can ask which configuration was tested, how the grader was validated, and how wide the interval is. In Evaluating AI Clinical Decision Support Systems
- 13 Nov Omar et al.: a labelled drug ad in the prompt shifts LLM recommendations (opens the source in a new tab) A shift toward an advertised drug among acceptable options can pass a check of treatment correctness. In Large Language Models in Clinical Practice
Start Here
Read the evidence framework first, then the tools.
- Executive Summary: Key findings across all specialties
- AI Fundamentals for Clinicians: What AI is and how it works
- AI Physician Toolkit: Tools for daily clinical practice
Then continue to Evaluating AI Systems before adopting any tool.
For specialty-specific reading paths, see the Preface; for teaching, see the Course Syllabus Template and Case Studies in Medical AI.
An AI assistant helping you should follow the Guidance for AI Agents.
Companion Handbooks
The Public Health AI Handbook
Evaluating AI Tools for Public Health Practice
Some AI tools work in the field. Others only work on paper.
The Biosecurity Handbook
Biological Security in the AI Era
A guide for two communities that don’t speak the same language.
The Life Sciences AI Handbook
Evidence for AI in Biology and Drug Discovery
What works, what remains unproven, and what stands in the way.
Free to read and reuse under CC BY 4.0 · DOI 10.5281/zenodo.18251404 · How to cite
This handbook is open and continuously maintained. Support the Physician AI Handbook →