Appendix L — Course Syllabus Template
This syllabus template is designed for MPH programs, epidemiology training, health department professional development, and related programs. Faculty may adapt the structure, readings, and assignments to their specific context and audience.
- 12-week format: Standard graduate semester structure
- 6-week intensive format: Combine weeks as indicated for accelerated programs
- Modular use: Individual weeks can be extracted for focused workshops
- Health department adaptation: See notes for practice-focused versions
Course Overview
Course Title: AI for Public Health Practice: From Surveillance to Implementation
Level: Graduate seminar (MPH, DrPH, PhD) or professional development for health departments
Prerequisites: Basic epidemiology and biostatistics recommended. No prior AI knowledge required.
Primary Text: Tegomoh, B. (2025). The Public Health AI Handbook: Evaluating AI Tools for Public Health Practice. DOI: 10.5281/zenodo.18263442
Learning Objectives:
By the end of this course, students will be able to:
- Explain core AI/ML concepts in public health terminology
- Evaluate AI tools for disease surveillance and outbreak detection
- Assess epidemic forecasting models and their limitations
- Apply genomic surveillance AI to pathogen tracking
- Identify deployment challenges specific to public health infrastructure
- Analyze ethical and equity implications of population-level AI
- Design implementation strategies appropriate for health department contexts
12-Week Syllabus
Week 1: Why Most AI Projects Fail in Public Health
Theme: Historical context and failure patterns
Required Reading:
- AI in Healthcare: A Brief History (Chapter 1)
- Preface
Learning Objectives:
- Trace AI development in public health from early expert systems to modern ML
- Explain why Google Flu Trends worked, then failed
- Identify recurring patterns in public health AI failures
Discussion Questions:
- Google Flu Trends initially outperformed CDC. What went wrong?
- What’s different about public health AI vs. clinical AI?
- Why are public health practitioners often skeptical of AI hype?
Week 2: Machine Learning Fundamentals for Epidemiologists
Theme: AI concepts translated for public health audiences
Required Reading:
- Machine Learning Fundamentals (Chapter 2)
Learning Objectives:
- Distinguish supervised learning, unsupervised learning, and reinforcement learning
- Explain overfitting in epidemiological terms
- Connect ML concepts to familiar statistical methods
Discussion Questions:
- How is an ML classification model similar to and different from logistic regression?
- When would you use supervised vs. unsupervised learning in surveillance?
- What’s the epidemiological equivalent of overfitting?
Week 3: The Data Problem in Public Health AI
Theme: Why public health data makes AI hard
Required Reading:
- The Data Problem in Public Health AI (Chapter 3)
Learning Objectives:
- Identify data quality issues specific to public health (reporting lags, inconsistent standards)
- Analyze how data limitations constrain AI applications
- Assess generalizability concerns for population-level AI
Discussion Questions:
- A vendor trained their model on hospital data. What problems arise for health department use?
- How do reporting delays affect real-time surveillance AI?
- What data infrastructure investments would most improve AI readiness?
Assignment: Data audit (1,500 words): Assess the AI readiness of a public health dataset you have access to
Week 4: AI for Disease Surveillance and Outbreak Detection
Theme: Current applications and evidence
Required Reading:
Learning Objectives:
- Evaluate syndromic surveillance AI systems
- Analyze wastewater surveillance AI applications
- Assess early warning systems and their performance
Discussion Questions:
- How should AI outbreak detection integrate with traditional surveillance?
- What’s the cost of false positives in automated outbreak detection?
- How did COVID-19 change surveillance AI applications?
Week 5: Epidemic Forecasting with AI
Theme: Promises and limitations of predictive models
Required Reading:
- Epidemic Forecasting with AI
- The AI Morgue: Failure Post-Mortems: COVID-19 forecasting failures
Learning Objectives:
- Evaluate epidemic forecasting model types (mechanistic, statistical, ML, ensemble)
- Analyze why COVID-19 forecasting performed poorly in 2020
- Apply appropriate skepticism to forecasting claims
Discussion Questions:
- Why is epidemic forecasting fundamentally harder than weather forecasting?
- What did the COVID-19 Forecast Hub teach us about ensemble models?
- How should decision-makers use uncertain forecasts?
Week 6: Genomic Surveillance and Pathogen Analysis
Theme: AI for sequencing data and variant tracking
Required Reading:
Learning Objectives:
- Explain how AI assists variant classification and lineage assignment
- Evaluate phylogenetic inference AI tools
- Assess antimicrobial resistance prediction applications
Discussion Questions:
- How did AI support SARS-CoV-2 variant tracking?
- What are the limitations of AI for predicting variant characteristics?
- How should health departments integrate genomic AI into routine surveillance?
Midterm: Take-home exam covering Weeks 1-6
Week 7: Clinical Decision Support and Diagnostic AI
Theme: Population health implications of clinical AI
Required Reading:
Learning Objectives:
- Analyze population-level impacts of clinical AI deployment
- Evaluate screening AI (diabetic retinopathy, cancer) from a public health perspective
- Assess implications for health equity at population scale
Discussion Questions:
- How does clinical AI deployment affect population health metrics?
- What’s the public health role in clinical AI oversight?
- Should health departments influence clinical AI adoption? How?
Week 9: Evaluating AI Systems for Public Health
Theme: Practical evaluation frameworks
Required Reading:
Learning Objectives:
- Apply evaluation frameworks specific to public health contexts
- Identify red flags in vendor marketing and validation claims
- Design validation studies appropriate for health department resources
Discussion Questions:
- How should health departments evaluate AI they can’t replicate internally?
- What validation should vendors provide before public health deployment?
- How do you evaluate AI when you don’t have data science staff?
Assignment: Vendor evaluation (2,000 words): Critically evaluate an AI product marketed to health departments
Week 10: Ethics, Equity, and Privacy
Theme: Values and risks in population-level AI
Required Reading:
Learning Objectives:
- Analyze algorithmic bias in population health AI
- Apply ethical frameworks to surveillance AI decisions
- Navigate privacy considerations in public health AI
Discussion Questions:
- How does algorithmic bias manifest differently in public health vs. clinical AI?
- When is surveillance AI an appropriate public health intervention?
- How should public health balance AI capability with privacy protection?
Week 11: Why Most Prototypes Fail in Health Departments
Theme: Implementation challenges specific to public health
Required Reading:
- AI Deployment in Healthcare: Why Most Prototypes Fail
- AI Safety in Healthcare: Protecting Patients and Populations
Learning Objectives:
- Identify infrastructure barriers in health departments
- Analyze why academic pilots often fail to scale
- Design implementation strategies for resource-constrained settings
Discussion Questions:
- Why do AI tools that work in research settings fail in health departments?
- What infrastructure investments enable AI adoption?
- How should health departments approach AI when they lack technical staff?
Week 12: Future Directions and Career Pathways
Theme: Emerging technologies and professional development
Required Reading:
- Emerging AI Technologies for Public Health
- Large Language Models in Public Health: Theory and Practice
- Career Guide: Pathways in Public Health AI
Learning Objectives:
- Evaluate emerging AI technologies (LLMs, multimodal AI)
- Analyze how AI might transform public health practice
- Identify career pathways in public health AI
Discussion Questions:
- How should public health practitioners prepare for AI-augmented practice?
- What LLM applications are appropriate for public health? What aren’t?
- What skills will public health professionals need in 5-10 years?
Final Assignment: Implementation proposal or policy brief (3,000 words)
Assessment Structure
| Component | Weight | Due |
|---|---|---|
| Class participation | 15% | Ongoing |
| Data audit (Week 3) | 15% | Week 3 |
| Midterm exam | 20% | Week 6 |
| Vendor evaluation (Week 9) | 20% | Week 9 |
| Final proposal/brief | 30% | Week 12 |
6-Week Intensive Format
For professional development programs, combine weeks as follows:
| Intensive Week | Standard Weeks | Focus |
|---|---|---|
| 1 | 1-2 | History, failures, ML fundamentals |
| 2 | 3-4 | Data challenges, surveillance AI |
| 3 | 5-6 | Forecasting, genomic surveillance |
| 4 | 7-8 | Clinical AI, substance use, social determinants |
| 5 | 9-10 | Evaluation, ethics, privacy |
| 6 | 11-12 | Implementation, futures, careers |
Supplementary Reading Lists
Public Health AI Foundations
- Rajkomar, A., Dean, J., & Kohane, I. (2019). Machine Learning in Medicine. NEJM, 380(14), 1347-1358.
- Wiens, J. et al. (2019). Do no harm: A roadmap for responsible machine learning for health care. Nature Medicine, 25(9), 1337-1340.
Surveillance and Forecasting
- Mooney, S.J. & Pejaver, V. (2018). Big Data in Public Health: Terminology, Machine Learning, and Privacy. Annual Review of Public Health, 39, 95-112.
- Reich, N.G. et al. (2019). Accuracy of real-time multi-model ensemble forecasts for seasonal influenza in the U.S.. PLOS Computational Biology, 15(11), e1007486.
Implementation and Policy
- Shaw, J. et al. (2019). Artificial Intelligence and the Implementation Challenge. Journal of Medical Internet Research, 21(7), e13659.
- World Health Organization (2021). Ethics and governance of artificial intelligence for health. WHO Guidance.
Adaptation Notes for Instructors
For MPH programs: This syllabus aligns with CEPH competencies for data analysis and evidence-based practice. Emphasize Weeks 3-6 (surveillance applications) for students focusing on epidemiology.
For DrPH/PhD programs: Expand technical content in Weeks 2, 5-6. Add methods-focused assignments requiring students to implement simple surveillance AI.
For health department training: Compress to 6-week format. Emphasize practical evaluation (Week 9) and implementation (Week 11). Add hands-on workshops with tools actually used in your jurisdiction.
For informatics programs: Expand technical content throughout. Add coding exercises and model development assignments.
License
This syllabus template is released under the same CC BY 4.0 license as The Public Health AI Handbook. Faculty may adapt freely with attribution.