iScience Article Machine learning of COVID-19 clinical data iden- tifies population structures with therapeutic po- tential David Greenwood, Thomas Taverner, Nicola J. Adderley, ..., Krishnarajah Nirantharakumar, Wayne Croft, Paul Moss p.moss@bham.ac.uk Highlights UMAP-assisted clustering can define subgroups of acute COVID-19 patients These clusters could be validated in independent patient cohorts Cluster assignation on the day of admission was predictive of 28-day mortality Clusters uncover clinical interactions that may to guide treatment approaches Greenwood et al., iScience 25, 104480 July 15, 2022 ª 2022 The Author(s). https://doi.org/10.1016/ j.isci.2022.104480 ll OPEN ACCESS