Revealing Key Factors of Heat-related Illnesses using Geospatial Explainable AI Model: A Case Study in Texas, USA

Sustainable Cities and Society, Год журнала: 2025, Номер unknown, С. 106243 - 106243

Опубликована: Фев. 1, 2025

Язык: Английский

---

An explainable AI framework for spatiotemporal risk factor analysis in public health: a case study of cardiovascular mortality in South Korea

GIScience & Remote Sensing, Год журнала: 2024, Номер 61(1)

Опубликована: Дек. 5, 2024

Understanding environmental disease risk factor analysis at the district level is essential for gaining valuable insights into regional variations, offering a broader perspective compared to individual-level studies. Recently, explainable artificial intelligence (XAI) has received increasing attention in of factors affecting public health. However, previous purely data-driven XAI-based analyses faced challenges capturing effect variables, leading confusion regarding key spatiotemporal factors. Therefore, this study proposes framework that includes two complementary following assumptions. Regionally rescaled variables must account unequal effects on factors, which are likely influenced by variations adaptation capacity weather conditions and differences exposure-response relationships air pollutants. District-level distribution highlights geographic disparity sociodemographic vulnerability, whereas temporal variation diseases underscores impacts. Based these hypotheses, we using schemes: one employs district-level as target variable, another utilizes residual within each district. We evaluated analyzing association between cardiovascular age-standardized mortality rate (CVD-ASMR) various South Korea from 2010 2019, high-performing random forest light gradient boosting models with additive Shapley explanation. Compared analyses, proposed schemes achieved significantly better results relationships. In schemes, most districts high CVD-ASMR was low education related patterns were greenness pollution levels. addition, enabled us reasonably analyze interaction i.e. temperature Furthermore, its observed situations vulnerability poor quality. These findings provide insightful health planning sustainable cities society pinpointing high-risk areas tailoring strategies address challenges.

Язык: Английский

---

Projected risk and vulnerability to heat waves for Montreal, Quebec, using Gaussian processes

Sustainable Cities and Society, Год журнала: 2024, Номер unknown, С. 105907 - 105907

Опубликована: Окт. 1, 2024

Язык: Английский

---

Projecting the overall heat-related health burden and associated economic costs in a climate change context in Quebec, Canada

The Science of The Total Environment, Год журнала: 2024, Номер 958, С. 178022 - 178022

Опубликована: Дек. 13, 2024

Язык: Английский

---