The Clinical AI Field Guide

Author

Rafe McBeth

Published

January 8, 2026

Welcome

The Clinical AI Field Guide

This book provides a practical introduction to artificial intelligence and machine learning for medical applications. Think of it as a field guide—enough to identify what you’re looking at and ask the right questions, not an encyclopedia of everything.

The goal: give clinicians, researchers, and students just enough foundation to engage meaningfully with AI—to ask the right questions, spot the pitfalls, and understand what’s actually happening when someone says “the model predicted…”

It accompanies the MPHY 6120 course at the University of Pennsylvania, but stands alone for anyone seeking to understand how AI is transforming healthcare.

Who This Book Is For

Medical professionals wanting to understand AI tools
Data scientists entering the healthcare domain
Students in biomedical informatics, medical physics, or health data science
Researchers applying ML to clinical problems

Reader Tracks

Not everyone needs every chapter. Choose your path:

Clinical Track — Understanding AI, not building it:

Start with Ch 1-2 (History, Framing), Ch 5 (EDA—understand data quality!), Ch 6 (Classical ML concepts)
Focus on Ch 11 (LLMs), Ch 13-17 (Applications), Ch 18-22 (Responsible AI)
Skip or skim: Ch 3-4 (Programming/Stats—reference as needed), Ch 7-10, 12 (implementation details)

Technical Track — Building clinical AI systems:

Read all chapters sequentially
Ch 2-5 are prerequisites; don’t skip them (especially Ch 2 on problem framing and Ch 5 on data quality)
Code examples are designed to be copied and adapted

Quick Reference — Evaluating an AI tool today:

Ch 18 (Interpretability): What questions to ask
Ch 20 (Fairness): Bias red flags
Ch 21 (Regulation): Compliance requirements
Ch 22 (Writing the Field Guide): Documentation standards

How to Use This Book

Each chapter includes:

Clinical Context: Real-world motivation for why this topic matters
Core Concepts: Theory explained accessibly with medical examples
Code Examples: Executable Python/PyTorch snippets you can adapt
Key Terms: Indexed terminology for quick reference

The code examples use standard libraries (PyTorch, scikit-learn, MONAI, scispaCy) and are designed to run on modest hardware.

Acknowledgments

This book draws on materials developed for the Penn AI for Medicine course. Thanks to the students and teaching assistants who provided feedback on early drafts.

License

This work is licensed under CC BY-NC-SA 4.0. You are free to share and adapt the material for non-commercial purposes with attribution.

# Welcome {.unnumbered} This book provides a practical introduction to artificial intelligence and machine learning for medical applications. Think of it as a field guide—enough to identify what you're looking at and ask the right questions, not an encyclopedia of everything. The goal: give clinicians, researchers, and students just enough foundation to engage meaningfully with AI—to ask the right questions, spot the pitfalls, and understand what's actually happening when someone says "the model predicted..." It accompanies the MPHY 6120 course at the University of Pennsylvania, but stands alone for anyone seeking to understand how AI is transforming healthcare. ## Who This Book Is For - Medical professionals wanting to understand AI tools - Data scientists entering the healthcare domain - Students in biomedical informatics, medical physics, or health data science - Researchers applying ML to clinical problems ## Reader Tracks Not everyone needs every chapter. Choose your path: **Clinical Track** — Understanding AI, not building it: - Start with Ch 1-2 (History, Framing), Ch 5 (EDA—understand data quality!), Ch 6 (Classical ML concepts) - Focus on Ch 11 (LLMs), Ch 13-17 (Applications), Ch 18-22 (Responsible AI) - Skip or skim: Ch 3-4 (Programming/Stats—reference as needed), Ch 7-10, 12 (implementation details) **Technical Track** — Building clinical AI systems: - Read all chapters sequentially - Ch 2-5 are prerequisites; don't skip them (especially Ch 2 on problem framing and Ch 5 on data quality) - Code examples are designed to be copied and adapted **Quick Reference** — Evaluating an AI tool today: - Ch 18 (Interpretability): What questions to ask - Ch 20 (Fairness): Bias red flags - Ch 21 (Regulation): Compliance requirements - Ch 22 (Writing the Field Guide): Documentation standards ## How to Use This Book Each chapter includes: - **Clinical Context**: Real-world motivation for why this topic matters - **Core Concepts**: Theory explained accessibly with medical examples - **Code Examples**: Executable Python/PyTorch snippets you can adapt - **Key Terms**: Indexed terminology for quick reference The code examples use standard libraries (PyTorch, scikit-learn, MONAI, scispaCy) and are designed to run on modest hardware. ::: {.content-visible when-format="pdf"} ## A Note on This Edition This print edition focuses on concepts and clinical context—readable, portable, light on code. Full executable code examples with syntax highlighting are available in the online version at [clinicalai.guide](https://clinicalai.guide). ::: ## Acknowledgments This book draws on materials developed for the Penn AI for Medicine course. Thanks to the students and teaching assistants who provided feedback on early drafts. ## License This work is licensed under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/). You are free to share and adapt the material for non-commercial purposes with attribution.