A Systems-Based Foundation for Equitable AI in Hyperlocal Climate-Health Adaptation
1
School of Public Health Sciences, University of Waterloo, Waterloo, Canada
2
Systems Design Engineering, University of Waterloo, Waterloo, Canada
3
Digital Technologies Research Centre, National Research Council Canada, Waterloo, Canada
Popul. Med. 2026;8(Supplement Supplement 1):A952
ABSTRACT
BACKGROUND:
Artificial intelligence (AI) interventions can shift public health strategies from reactive management to proactive prevention of climate-related health risks at the hyperlocal level1–3. However, without accounting for local social, organizational, and governance contexts, AI interventions may reinforce existing inequities and unintentionally harm vulnerable populations4,5. Therefore, this study serves as a foundational step toward designing effective and equitable climate-health AI interventions by generating a systems map that captures how hyperlocal public health and urban systems (PHU) are structured, function, and how they are experienced by communities in the context of climate change adaptation.
METHODS:
This qualitative, single-case study utilizes a multi-method approach to model the PHU system in the Region of Waterloo, Canada. The study has two phases designed to understand the system’s objective structure and subjective experience. Phase 1 (P1) established formal and informal system relationships through a thematic analysis of key documents and social network analysis based on a whole-network, roster-based survey administered to regional and municipal government managers, hospital and paramedic service administrators, and community-based organizations’ leaders6,7. Semi-structured interviews with key informants provided additional context on informal dynamics and decision-making processes. Findings from P1-informed preliminary system diagrams guide Phase 2 (P2), which documents local residents’ lived experience through focus groups. The findings will be synthesized and validated with stakeholders to identify priorities and opportunities for future AI interventions.
RESULTS:
P1 successfully produced a preliminary map of the PHU system and identified initial areas where AI could have the greatest potential impact. P2 is ongoing and enhancing this model by integrating community perspectives and contextual knowledge.
CONCLUSIONS:
This study demonstrates a practical, systems-based approach for informing equitable AI interventions in hyperlocal climate-health adaptation. By integrating system structure, function, and lived experiences, this study establishes a critical, foundational step for designing AI interventions that are context-aware and locally grounded.
Artificial intelligence (AI) interventions can shift public health strategies from reactive management to proactive prevention of climate-related health risks at the hyperlocal level1–3. However, without accounting for local social, organizational, and governance contexts, AI interventions may reinforce existing inequities and unintentionally harm vulnerable populations4,5. Therefore, this study serves as a foundational step toward designing effective and equitable climate-health AI interventions by generating a systems map that captures how hyperlocal public health and urban systems (PHU) are structured, function, and how they are experienced by communities in the context of climate change adaptation.
METHODS:
This qualitative, single-case study utilizes a multi-method approach to model the PHU system in the Region of Waterloo, Canada. The study has two phases designed to understand the system’s objective structure and subjective experience. Phase 1 (P1) established formal and informal system relationships through a thematic analysis of key documents and social network analysis based on a whole-network, roster-based survey administered to regional and municipal government managers, hospital and paramedic service administrators, and community-based organizations’ leaders6,7. Semi-structured interviews with key informants provided additional context on informal dynamics and decision-making processes. Findings from P1-informed preliminary system diagrams guide Phase 2 (P2), which documents local residents’ lived experience through focus groups. The findings will be synthesized and validated with stakeholders to identify priorities and opportunities for future AI interventions.
RESULTS:
P1 successfully produced a preliminary map of the PHU system and identified initial areas where AI could have the greatest potential impact. P2 is ongoing and enhancing this model by integrating community perspectives and contextual knowledge.
CONCLUSIONS:
This study demonstrates a practical, systems-based approach for informing equitable AI interventions in hyperlocal climate-health adaptation. By integrating system structure, function, and lived experiences, this study establishes a critical, foundational step for designing AI interventions that are context-aware and locally grounded.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
