The Physician AI Handbook

Peer-Reviewed Evidence for Every Specialty

What works. What doesn’t. What happens when AI is wrong. Evidence-based guidance for physicians evaluating clinical AI tools across all specialties.
Author

Bryan Tegomoh, MD, MPH

Published

February 2026

Welcome to The Physician AI Handbook

Clinical AI performance in real-world settings often falls short of published validation studies. This handbook helps physicians evaluate AI tools based on peer-reviewed evidence, written from a clinician’s perspective for clinicians, health system leaders, and anyone building or deploying clinical AI.

Three questions drive every chapter: What does the peer-reviewed evidence actually show? How do I evaluate claims against that evidence? What are the medico-legal implications when AI is wrong?

The handbook covers five areas: foundations of clinical AI, specialty-specific applications across all ACGME disciplines, implementation and evaluation frameworks, practical tools for daily practice, and future directions.

Continuously updated as new research emerges.

Important Disclaimers

This handbook is for educational purposes only and does not constitute medical advice, diagnosis, or treatment. AI systems discussed herein are not substitutes for professional medical judgment.

Physicians remain solely responsible for clinical decisions, validating AI outputs before clinical use, ensuring regulatory compliance (FDA, HIPAA), and meeting the standard of care in their jurisdiction.

Information may become outdated given the rapidly evolving nature of AI technology. Verify recommendations with current clinical guidelines before application.

This handbook does not provide legal advice. Consult qualified legal counsel for malpractice and liability questions.

Quick Start: Choose Your Path

Select the pathway that matches your specialty and immediate needs:

Primary Care & Family Medicine

“I need practical AI tools for my daily practice”

Start here:

Diagnostic Specialties

“Radiology, Pathology, Dermatology, Ophthalmology”

Start here:

Surgical Specialties

“General Surgery, Orthopedics, Neurosurgery, OBGYN”

Start here:

Medical Specialties

“Internal Medicine, Cardiology, Oncology, Neurology”

Start here:

Emergency & Critical Care

“I work in fast-paced, high-stakes clinical environments”

Start here:

Pediatrics & Neonatology

“I care for pediatric and newborn patients”

Start here:

Scope and Methodology

  • Claims require peer-reviewed citations; vendor marketing labeled as such
  • Limitations and failures documented alongside successes
  • No vendor funding or commercial relationships
  • Updated continuously as evidence emerges

Book Structure

  • Part I: Foundations (Chapters 1–3) – AI history in medicine, fundamentals, clinical data challenges
  • Part II: Clinical Specialties (Chapters 4–22) – AI across all ACGME-recognized specialties
  • Part III: Implementation (6 chapters) – Evaluation, ethics, privacy, safety, workflow, liability
  • Part IV: Practical Tools (4 chapters) – Toolkit, LLMs in practice, documentation, clinical research
  • Part V: Future (5 chapters) – Emerging tech, global health, policy, misinformation, physician-AI partnership

License & Citation

This work is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).

You are free to: Share, copy, redistribute, adapt, remix, and build upon this material for any purpose, including commercially, with attribution.

Full license details | CC BY 4.0 Legal Code

How to Cite

Physician AI Handbook DOI: 10.5281/zenodo.18251405

Tegomoh, B. (2025). The Physician AI Handbook: Peer-Reviewed Evidence for Every Specialty. DOI: 10.5281/zenodo.18251405. URL: physicianaihandbook.com

Full citation formats