Spatial and spatiotemporal machine learning models for COVID-19 dynamics: a review of methodology and reporting practices.

Abstract

COVID-19 has transitioned from a pandemic to an endemic state, but the emergence of novel variants continues to pose significant public health challenges. In this study, the application of spatial and spatiotemporal machine learning (ML) models in understanding the dynamics of COVID-19 was systematically reviewed, as were contextual local-level comprehensive socio-environmental drivers. A systematic search was conducted across the Scopus, Web of Science, PubMed, Emcare (via Ovid), and the World Health Organization COVID-19 databases, and gray literature, adhering to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Data extraction was conducted according to the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies checklist, and study quality was assessed using a validated scoring system. A total of 42 studies met the inclusion criteria. The review Findings indicate that global-scale spatial and spatiotemporal ML models dominate the field. Long-standing standalone factors in the demographic, environmental, and socioeconomic domains are frequently used as local-level drivers. However, the integration of composite indicators, aggregating multiple standalone factors into a single score, is notably lacking. Such composite indicators have the potential to reduce model complexity, improve interpretability, and enhance performance by capturing multidimensional aspects of vulnerability or risk in a more simplified form. This review highlights critical gaps in the current use of spatial and spatiotemporal ML models to understand the spatial epidemiology of COVID-19. Addressing these gaps could significantly enhance the understanding of COVID-19 dynamics and inform the development of effective public health strategies to mitigate future threats.