Unit 6
Session duration: 6 academic hours, including:
- Lecture: 2 h,
- Data lab workshop: 3 h,
- Reflection / Q&A: 1h.
Learning objectives:
By the end of this unit, students will be able to:
- Understand basic concepts of AI, machine learning (ML), and big data as applied to public and environmental health.
- Explore the use of AI-driven models for predicting disease outbreaks related to environmental changes.
- Use open big data platforms (e.g., Google Earth Engine, GBD, Copernicus) to identify health trends.
- Evaluate the risks and ethical challenges of AI use in climate-health surveillance.
- Collaborate on designing a concept model of an AI-based surveillance solution for environmental health issues.
Session format: Data lab format with exploration of real datasets, group AI model ideation, and ethical reflection.
Inclusivity & sustainability focus:
- Emphasizes responsible and ethical AI use
- Addresses global inequality in data access and infrastructure
- Promotes student collaboration in digital innovation for health equity
Discussion questions:
- What types of data are most valuable for predicting health risks related to climate?
- How can machine learning enhance early warning systems for vector-borne or air pollution–related illnesses?
- What are the risks of bias or misinformation in AI-based health prediction models?
- How accessible are AI and big data tools for low-resource settings?
- Can AI-based systems replace traditional public health surveillance?
The instructor:
- Explains how big data sources (satellite, weather, health records) are integrated for modeling.
- Presents case examples: BlueDot (pandemic prediction), Google Flu Trends (lessons learned), IBM AI for air quality.
- Demonstrates use of simple dashboards (e.g., Kaggle datasets + notebooks, Earth Engine visualizations).
Students:
- Participate in guided exploration of real-time data dashboards.
- Form teams to develop a concept for an AI-based tool for tracking a climate-sensitive disease.
- Present prototype (paper-based or digital mock-up) and explain logic/inputs/outputs.
- Reflect on trade-offs between innovation, equity, and reliability.
Assignments:
Before the session: 1) Read: “Ethics and governance of artificial intelligence for health” (WHO, 2021); 2) Watch: Short demo on Google Earth Engine for environmental health.
During the session: 1) Explore and evaluate one AI-powered public health tool or dataset; 2) Create an AI concept solution in groups.
After the session: 1) Submit Diary #6: “AI in public health: empowering or replacing the human role?”; 2) Optional: Share group mock-up model (presentation or PDF)
Recommended reading & resources:
- WHO. (2021). Ethics and Governance of Artificial Intelligence for Health: https://www.who.int/publications/i/item/9789240029200, https://www.who.int/publications/i/item/9789240084759
- WHO (2024). Action framework advances multi-source surveillance. https://www.who.int/westernpacific/newsroom/feature-stories/item/world-health-organization-and-partners-across-asia-and-the-pacific-explore-new-frontiers-for-public-health-surveillance.
- Enoch, Olanite. (2024). AI for Public Health Surveillance. https://www.researchgate.net/publication/384732109_AI_for_Public_Health_Surveillance
- Jane M. Kunberger, Melanie R. Colón, Ashley M. Long. Using Google Earth Engine to develop interactive mapping tools for conservation planning. Journal for Nature Conservation, Volume 87, 2025, 126997, https://doi.org/10.1016/j.jnc.2025.126997.
- Google Earth Engine Tutorials; https://earthengine.google.com/, https://www.numberanalytics.com/blog/google-earth-engine-environmental-monitoring;
- Short demo on Google Earth Engine for environmental health: https://www.youtube.com/watch?v=2i6cw7nTbhI
- IHME: Global Burden of Disease: https://vizhub.healthdata.org/gbd-foresight/
- Copernicus Open Access Hub: https://www.copernicus.eu/en/access-data/conventional-data-access-hubs
- UNEP AI for Good: https://aiforgood.itu.int/about-us/un-ai-actions/unep/