flowchart LR
A[Part I:<br/>Foundations] --> B[Part II:<br/>Applications]
B --> C[Part III:<br/>Implementation]
C --> D[Part IV:<br/>Resources]
D --> E[Part V:<br/>Future]
style A fill:#ffffff,stroke:#2563eb,stroke-width:2px,color:#334155
style B fill:#ffffff,stroke:#2563eb,stroke-width:2px,color:#334155
style C fill:#ffffff,stroke:#2563eb,stroke-width:2px,color:#334155
style D fill:#ffffff,stroke:#2563eb,stroke-width:2px,color:#334155
style E fill:#ffffff,stroke:#2563eb,stroke-width:2px,color:#334155
click A "/foundations/history.html"
click B "/applications/surveillance.html"
click C "/implementation/evaluation.html"
click D "/practical/toolkit.html"
click E "/future/emerging.html"
The Public Health AI Handbook
Evaluating AI Tools for Public Health Practice
Peer-reviewed evidence for the decisions public health leaders actually face.
Welcome to The Public Health AI Handbook
Most AI tools perform worse in the field than in the paper. Health departments, ministries of health, and public health agencies worldwide face the same challenge: separating tools that work from tools that were validated on clean data they will never have. This is a guide to that evaluation, grounded in peer-reviewed evidence, built for the people making those decisions.
Three questions drive every chapter: Which AI tools actually perform in real-world public health settings? How do you evaluate a model when your 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.
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Information may become outdated given the rapidly evolving nature of AI technology and public health practice.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
Epidemiologists / 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 / Public Health Leadership
“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 4–8) – Surveillance, forecasting, genomics, clinical AI, substance use
- Part III: Implementation (Chapters 9–13) – Evaluation, ethics, privacy, safety, deployment
- Part IV: Resources (Chapters 14–16) – Toolkit, project walkthroughs, AI-assisted coding
- Part V: Future (Chapters 17–22) – Emerging tech, global health, policy, misinformation, 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