--- title: "Preface – The Physician AI Handbook" source: "https://physicianaihandbook.com/preface.html" author: "Bryan Tegomoh, MD, MPH" last_updated: "2026-10-30" doi: "10.5281/zenodo.18251404" license: CC BY 4.0 generated-by: handbook-markdown-export --- # Preface ## AI as a Clinical Tool Artificial intelligence is entering clinical medicine as a new category of tool, and it deserves the scrutiny physicians apply to any clinical intervention: what was tested, in whom, against what comparator, and with what outcome. Algorithms interpret chest radiographs. Deep learning models analyze pathology slides. Natural language processing extracts information from electronic health records. But published performance does not by itself establish clinical utility in a local workflow. Promotional claims can exceed the independent evidence for the exact product, version, population, and intended use. Even authorized or well-validated systems require careful implementation, explicit monitoring, and honest acknowledgment of limitations. This handbook addresses the challenge physicians face: how to critically evaluate these tools, integrate them responsibly into clinical workflow, understand their limitations, and decide which applications genuinely improve patient care. ## Handbook Scope and Purpose This is a field guide for evidence-based AI evaluation, not a computer science textbook. It explains as much of the technology as a physician needs to judge a claim about it. This handbook prioritizes peer-reviewed evidence from major medical journals, exact FDA authorization records, and real-world implementations over press releases and vendor whitepapers. Where evidence clearly supports specific tools, I name them. Where products have documented limitations or failures, I describe the evidence and its boundaries. Physicians deserve honest assessments, not diplomatic neutrality between well-supported and unsupported claims. Citations are checked against Crossref, PubMed, publisher records, or official organizational sources where available, and FDA status against FDA’s own records. Performance figures that come only from a vendor are identified as vendor-reported. When a claim proves outdated, overstated, or unsupported, it is corrected in place or bounded to what the evidence shows. ## Reading Guide You do not need to read sequentially. Jump directly to your specialty chapter. Use the search function. Read the TL;DR summaries for quick orientation. Read the full chapters when evaluating tools for your practice. **Three approaches:** 1. **Quick Scan:** Read chapter TL;DRs only for rapid orientation 2. **Deep Dive:** Full chapters for implementation planning 3. **Specialty Focus:** Foundations, your specialty chapter, and Clinical Implementation and Evaluation Every chapter begins with an expandable **Chapter Summary (TL;DR)** containing clinical context, key evidence, what works, what does not, and the clinical bottom line. Use the summary for orientation, then read the underlying evidence before making an implementation decision. Stay skeptical. Match the strength of the claim to the study design, and do not treat retrospective validation as proof of clinical benefit. Professional duties remain, while legal responsibility for AI-assisted care depends on the jurisdiction, intended use, institutional controls, and facts of the case. See [Physician AI Liability and Regulatory Compliance](./implementation/liability.html). ## Choose Your Path Select the pathway that matches your specialty and immediate needs: ### Primary Care & Family Medicine **Primary Care, Family Medicine, Outpatient Practice** Start here: - [AI Fundamentals](./foundations/ai-basics.html): What AI actually is - [Primary Care Applications](./specialties/primary-care.html): AI in family medicine - [LLMs in Practice](./practical/llm-practice.html): ChatGPT and Claude for clinical tasks - [AI-Assisted Documentation](./practical/documentation.html): Ambient scribes - [AI Physician Toolkit](./practical/toolkit.html): Essential tools ### Diagnostic Specialties **Radiology, Pathology, Dermatology, Ophthalmology** Start here: - [Diagnostic Imaging & Radiology](./specialties/radiology.html): AI-assisted diagnostics - [Pathology & Laboratory](./specialties/pathology.html): Digital pathology AI - [Dermatology](./specialties/dermatology.html) & [Ophthalmology](./specialties/ophthalmology.html): Computer vision applications - [Evaluation Framework](./implementation/evaluation.html): Assessing AI diagnostic tools ### Surgical Specialties **General Surgery, Orthopedics, Neurosurgery, OBGYN** Start here: - [Surgery & Perioperative Care](./specialties/surgery.html): AI in the OR - [OBGYN Applications](./specialties/obgyn.html): Maternal-fetal medicine AI - [Clinical Workflow Integration](./implementation/workflow.html): Practical implementation - [Medical Liability](./implementation/liability.html): Legal considerations ### Medical Specialties **Internal Medicine, Cardiology, Oncology, Neurology** Start here: - [Internal Medicine & Hospital Medicine](./specialties/internal-medicine.html): AI for hospitalists - [Cardiology Applications](./specialties/cardiology.html): Cardiovascular AI - [Oncology & Precision Medicine](./specialties/oncology.html): AI in cancer care - [Neurology Applications](./specialties/neurology.html): Neurological AI tools ### Emergency & Critical Care **Emergency Medicine, Critical Care, Pulmonary Medicine** Start here: - [Emergency Medicine](./specialties/emergency.html): AI in the ED - [Critical Care & Pulmonary](./specialties/critical-care.html): ICU and pulmonary AI - [Clinical AI Safety](./implementation/safety.html): Risk management - [Case Studies](./appendices/case-studies.html): Real implementations ### Pediatrics & Neonatology **Pediatrics, Neonatology, Child Health** Start here: - [Pediatrics & Neonatology](./specialties/pediatrics.html): AI in child health - [Medical Ethics & Equity](./implementation/ethics.html): Special pediatric considerations - [Privacy & HIPAA](./implementation/privacy.html): Protecting pediatric data - [Physician Toolkit](./practical/toolkit.html): Practical tools ## Questions About the Handbook ### What is the purpose of the Physician AI Handbook? The handbook helps physicians critically evaluate AI tools, integrate them responsibly into clinical workflows, understand their limitations, and determine which applications have credible evidence of improving care or workflow. ### How should the handbook be read? Three approaches are available: use chapter TL;DRs for a quick scan, read full chapters for implementation planning, or combine the Foundations, relevant specialty, and Implementation chapters for a specialty-focused path. ### What sources does the handbook use? The handbook prioritizes peer-reviewed research, official regulatory records, professional-society guidance, and documented real-world implementations. Vendor materials and press releases are labeled as such and do not substitute for independent clinical evidence. ------------------------------------------------------------------------ **[Bryan Tegomoh, MD, MPH](https://bryantegomoh.com/)** Berkeley, California October 2025 ## About the Author Bryan Tegomoh, MD, MPH, is a physician and medical epidemiologist whose work spans pathogen surveillance, pandemic preparedness, and clinical AI evaluation. He helped establish Nebraska’s statewide pathogen genomic surveillance program through CDC and CSTE, served as a technical consultant to the World Health Organization on epidemic and pandemic preparedness from 2022 to 2024, and contributed to clinical evaluations of AI models at xAI. He is Deputy Editor of Rapid Reviews: Infectious Diseases, and his work has been published in Science, Nature Methods, Nature Microbiology, and MMWR.