The Public Health AI Handbook

A Practical Guide for Epidemiologists and Public Health Practitioners

An open-source, practical guide for understanding and applying AI in public health
Author

Bryan Tegomoh, MD, MPH

Published

October 2025

Welcome to The Public Health AI Handbook

This handbook started as something deeply personal: a collection of notes from resources online, bookmarked research papers, saved blog posts, meeting summaries, open-source github projects, courses, and synthesized resources as I tried to make sense of artificial intelligence’s role in public health practice.

As an epidemiologist working in surveillance and outbreak response, I kept encountering AI applications (outbreak prediction models, genomic surveillance tools, automated case classification systems) but the knowledge was frustratingly fragmented. Research papers buried behind paywalls. Technical blog posts assuming computer science backgrounds. Marketing materials overpromising capabilities. Online courses that were either too theoretical or too tool-specific.

After months of reading, taking courses, testing tools, and synthesizing information, I realized: if I was struggling to piece this together, other public health practitioners probably were too.

This handbook is the result of that synthesis work. It’s not meant to be the definitive academic treatise on AI in public health. It’s a curated, organized, and tested resource designed to save you the searching I did. Think of it as the guidebook I wished existed when I started learning about AI in our field.

Every chapter represents my attempt to distill hours of reading, tool testing, and practical experimentation into what might be useful for public health practice. I’m still learning, and this handbook will evolve as I do.

Quick Start: Choose Your Path

Select the pathway that matches your role and immediate needs:

State/Local Health Departments

“I need to evaluate AI tools my agency is considering”

Start here (20 min): - AI Fundamentals - What AI actually is - Evaluation Framework - Audit vendor claims - Ethics & Privacy - Critical considerations

Epidemiologist/Public Health Workforce

“I want to use AI in my surveillance or research work”

Start here (30 min): - Disease Surveillance - AI for outbreak detection - Forecasting - Predictive models - Practical Tools - Hands-on code - Using LLMs: Theory & Practice - ChatGPT, Claude, Copilot for analysis

Jump to: Case Studies for real implementations

Policy Maker/Director

“I need to make informed decisions about AI adoption”

Start here (15 min): - Global Health Perspectives - Strategic overview - Policy & Governance - Frameworks and regulations - Ethics & Fairness - Responsible AI principles - AI Misinformation - Combat health misinfo

Health Communication/Behavioral Health

“I work in health communication, behavior change, or community outreach”

Start here (25 min): - AI Misinformation - Detect and counter health misinfo - Behavioral Interventions - AI chatbots, personalized messaging - Using LLMs: Theory & Practice - Communication assistance tools

Focus: Messaging, behavior change, combating misinformation, personalization

Frontline Healthcare Workers/Clinicians

“I’ll be using AI tools in direct patient care or community health”

Start here (25 min): - Clinical AI Applications - Real-world use cases - Deployment & Workflow - Integration strategies - Evaluation - Assessing tool reliability

Focus: Practical usability, workflow integration, patient-facing implications

Data Scientists/AI Developers

“I’m building or customizing AI systems for public health”

Start here (30 min): - Data Quality & Pipelines - Public health data requirements - Practical Toolkit - Code examples and tools - AI-Assisted Coding - GitHub Copilot, Cursor, development tools - Model Evaluation - Validation frameworks

Focus: Technical limitations, data requirements, model behavior

New to AI entirely? → Read Part I: Foundations sequentially (2-3 hours total)

Your Feedback Makes This Better

I wrote this from my perspective and experience, which means it has blind spots. Contributions are welcome:

  • Found something wrong? Please submit an issue on GitHub
  • Have a better approach? Share it
  • Implemented something different? Tell your story
  • Working in low-resource settings? LMIC contexts are especially vital. AI implementation looks different with infrastructure, data, and resource constraints
  • Frontline healthcare worker or community health perspective? Practical workflow realities
  • Want to contribute code examples? Pull requests welcome
  • Find this helpful? Star the repository and share with colleagues

Follow updates on Twitter/X

What is this handbook?

The Public Health AI Handbook is an open-source, practical guide for understanding and applying artificial intelligence in public health—written by a public health professional (MD, MPH, UC Berkeley) with real-world experience.

This is NOT another hype-filled “AI for X” book.

This is a field guide for:

  • Epidemiologists who want to use AI tools without becoming machine learning engineers
  • Public health practitioners seeking to understand AI capabilities and limitations
  • Students entering the intersection of public health and data science
  • Policymakers making informed decisions about AI adoption in health departments

What makes this different?

What you’ll get:

  • Practical tools and working code
  • Real case studies (successes and failures)
  • Honest assessments of what I’ve learnt AI can and cannot do
  • No prerequisites beyond basic public health knowledge
  • Open access forever

What you won’t get:

  • Math-heavy theory without application
  • Generic “AI is amazing” hype
  • Ignoring messy real-world data problems
  • All the answers (I don’t have them)
  • Overpromising future capabilities
  • Paywalled content

Book Structure: Your Roadmap

Part I: Foundations

Essential AI concepts, data principles, and historical context

Chapters 1-3 2-3 hours Start here if new to AI

Key topics: AI fundamentals, machine learning basics, data quality, public health history with technology

Part II: Current Applications

Disease surveillance, forecasting, genomics, clinical support

Chapters 4-6, 8 3-4 hours Jump here for specific use cases

Key topics: Outbreak detection, predictive modeling, genomic surveillance, clinical AI

Note: Comprehensive LLM coverage moved to Part V (Chapter 20)

Part III: Implementation

Evaluation, ethics, privacy, deployment

Chapters 9-12 3-4 hours Critical for real-world implementation

Key topics: Model evaluation, ethics & fairness, privacy protection, deployment strategies

Part IV: Practical Resources

Tools, code examples, step-by-step project guides, AI-assisted coding

Chapters 13-15 5-6 hours Hands-on learning

Includes: AI toolkit, first project walkthrough, AI-assisted coding and development tools (VS Code, Copilot, Cursor, Git/GitHub), Python/R code examples

Part V: The Future

Emerging technologies, global health, policy, misinformation, LLMs (theory & practice), behavioral AI

Chapters 16-21 7-8 hours Forward-looking perspectives

Topics: Emerging AI methods, global health applications, policy & governance, AI-generated misinformation and infodemics, comprehensive guide to Large Language Models in public health (theory, practice, privacy, validation), AI-driven behavioral interventions and personalized health coaching, research frontiers

How to use this handbook

Choose Your Path

For practitioners → Jump to relevant applications For students → Read sequentially Part I → V For researchers → Check case study library For policymakers → Start with Chapter 16

About the Author

Bryan Tegomoh, MD, MPH is a physician and epidemiologist with experience in disease surveillance, outbreak response, and health data science. He earned his MPH from the University of California, Berkeley School of Public Health and has worked on surveillance systems, outbreak investigations, and public health data analysis.

Recognizing the growing intersection between artificial intelligence and public health practice, Bryan invested significant time understanding how AI tools and methods apply to real-world epidemiological challenges, not as a computer scientist, but as a practicing public health professional working to separate hype from practical utility.

This handbook emerged from that learning process: a synthesis of academic research, technical documentation, online courses, and hands-on experimentation with tools and code, all organized specifically for public health practitioners who need to understand AI capabilities and limitations without becoming machine learning engineers.

Acknowledgements & Inspiration

This handbook draws inspiration from excellent open resources including: - The Epidemiologist R Handbook by Applied Epi - R for Data Science by Hadley Wickham & Garrett Grolemund - The open-source public health and data science communities

Nearly everything valuable here builds on others’ published research, open-source code, documented implementations, and teaching. My contribution is mainly synthesis and organization—gathering scattered resources and testing them in public health contexts. Credit for insights belongs to those whose work I learned from; responsibility for errors is mine.

Contributing

This is a living handbook. Your contributions make it better:

Report Issues Submit on GitHub

Suggest Edits Click “Edit” on any page

Share Case Studies Email your examples

Support the Project Star us on GitHub

Terms of Use

License

This work is licensed under the MIT License. Free to use, share, and adapt with attribution.

Citation

Tegomoh, Bryan. The Public Health AI Handbook. 2025. https://publichealthaihandbook.com

How to cite this handbook

Academic Use

Training programs and academic courses are welcome to use this material. Please cite appropriately and let us know how you’re using it!

TipReady to start?

New to AI? → Begin with the Preface then Chapter 1: AI in Context

Want hands-on practice? → Jump to Chapter 13: Your AI Toolkit

Looking for specific applications? → Browse Part II: Current Applications