Mwase, Nandi SisasenkosiKebalepile, MosesJunger, WashingtonWichmann, Janine2026-02-052026-01Mwase, N.S., Kebalepile, M., Junger, W. & Wichmann, J. 2026, 'Unsupervised machine learning to investigate the joint effects of SO2, NO2, O3, PM2.5 and PM10 on respiratory and cardiovascular hospital admissions in the Vaal Triangle Airshed Priority Area, South Africa', Atmospheric Environment, vol. 366, art. 121660, pp. 1-10, doi : 10.1016/j.atmosenv.2025.121660.1352-2310 (print)1873-2844 (online)10.1016/j.atmosenv.2025.121660http://hdl.handle.net/2263/107848DATA AVAILABILITY : Data will be made available on request.Please read abstract in the article. HIGHLIGHTS • Unsupervised machine learning can be used as a dimension-reduction tool in air epidemiology. • Clustering methods allow to investigate multiple air pollutants (5≤) effects on hospital admissions. • There are noticeable limitations in using unsupervised machine learning in air pollution epidemiology studies.en© 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies. Notice : this is the author’s version of a work that was accepted for publication in Atmospheric Environment. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. A definitive version was subsequently published in Atmospheric Environment, vol. 366, art. 121660, pp. 1-10, 2026, doi : 10.1016/j.atmosenv.2025.121660.Air pollutionRespiratory diseaseCardiovascular disease (CVD)Machine learningClusteringAir pollution epidemiologyAdverse health effectsSouth Africa (SA)Postprint Article