The Public Health AI Handbook
Evaluating AI Tools for Public Health Practice
What works. What doesn’t. What to ask before adoption.
Welcome to The Public Health AI Handbook
AI performance in public health surveillance and outbreak settings often falls short of controlled trial results. This handbook provides evidence-based guidance for evaluating AI tools in real-world public health practice, covering surveillance, forecasting, and outbreak response across resource-constrained settings.
Three questions drive every chapter: Which AI tools actually perform in real surveillance and outbreak settings? How do I evaluate a model when my data is messy, delayed, and incomplete? What happens when the algorithm is wrong and public health action follows?
The handbook covers five areas: foundations of public health AI, applications in surveillance and forecasting, implementation and evaluation frameworks, practical tools and code, and future directions. You can read sequentially or jump to the section most relevant to your work.
This resource is continuously updated as new research emerges.
Important Disclaimers
This handbook is for educational and informational purposes only and does not constitute official public health guidance, operational protocols, or policy recommendations. It is not a substitute for guidance from public health authorities (CDC, WHO, state/local health departments).
Public health officials remain solely responsible for programmatic decisions, validating AI tool outputs before public health action, ensuring regulatory compliance (HIPAA, data protection laws), and meeting professional standards in their jurisdiction.
Information may become outdated given the rapidly evolving nature of AI technology and public health practice. Verify recommendations with current public health guidelines and protocols before implementation.
This handbook does not provide legal or regulatory advice. Consult qualified legal counsel for questions about data governance, procurement, liability, and regulatory compliance.
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: - 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 public health research work”
Start here: - 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
Policymakers/ Director
“I need to make informed decisions about AI adoption”
Start here: - 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: - 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: - Clinical AI Applications - Real-world use cases - Deployment & Workflow - Integration strategies - Evaluation - Assessing tool reliability
Focus: Practical usability, workflow integration, patient-facing implications
AI Developers/ Engineers/ Researchers (Technical)
“I’m building or customizing AI systems for public health”
Start here: - 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.
Book Structure
- Part I: Foundations (Chapters 1–3) – AI concepts, data quality, public health history with technology
- Part II: Applications (Chapters 4–7) – Surveillance, forecasting, genomics, clinical AI
- Part III: Implementation (Chapters 8–12) – Evaluation, ethics, privacy, safety, deployment
- Part IV: Resources (Chapters 13–15) – Toolkit, project walkthroughs, AI-assisted coding
- Part V: Future (Chapters 16–21) – Emerging tech, global health, policy, LLMs, behavioral AI
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
Tegomoh, B. (2025). The Public Health AI Handbook: Evaluating AI Tools for Public Health Practice. DOI: 10.5281/zenodo.18263442. URL: publichealthaihandbook.com