Key points are not available for this paper at this time.
This study maps the evolving intersection of urban health and artificial intelligence (AI) through a bibliometric analysis, with the aim of advancing a more conceptually grounded and urban-oriented understanding of this emerging field. Using a dataset of 125 publications indexed in Scopus and Web of Science (WoS), and analyzed through VOSviewer, the study identifies dominant research trajectories, thematic clusters, and temporal shifts in scholarly attention between 2014 and 2025. Publication trends reveal a rapid expansion following the COVID-19 pandemic, reflecting the growing integration of AI into urban health governance and crisis management. The analysis identifies four interconnected thematic clusters: (1) urban health monitoring, (2) predictive analytics for urban health, (3) AI-based public health surveillance, and (4) environmental health and GIS-based analysis. A temporal overlay analysis further demonstrates a conceptual shift from early technology- and monitoring-focused research toward more recent concerns with risk, exposure, spatial inequality, and long-term urban health impacts. Beyond mapping the literature, the study offers a critical urban interpretation of these patterns, arguing that AI in urban health is increasingly embedded within data-driven modes of urban governance rather than operating as a purely technical tool. At the same time, the findings reveal significant and persistent research gaps, including the limited engagement with social equity, algorithmic bias, and the uneven representation of cities in the Global South. Many AI models are implicitly trained on data from well-resourced “smart” cities, raising concerns about their applicability to informal settlements, low-income neighborhoods, and institutionally constrained urban contexts. By highlighting these conceptual, spatial, and justice-related gaps, this study reframes the future of AI-driven urban health research as a fundamentally place-based and governance-oriented challenge. It calls for future work that integrates AI with theories of spatial justice, urban inequality, and context-sensitive planning to ensure that data-driven health innovations contribute to more inclusive and equitable urban futures.
Dehrashid et al. (Wed,) studied this question.