Abstract Background Platelets are crucial for thrombosis and haemostasis, with their function driven by the expression of specialised surface markers. The concept of distinct circulating sub-populations of platelets has emerged in recent years, but their exact nature remains debatable. We reasoned that a more comprehensive characterisation of surface marker changes at rest and upon activation would be valuable in determining this. Objective To use a full spectrum flow cytometry-based panel, together with parameters of physical properties, to describe surface marker changes in healthy platelets at rest and on activation, and to observe how these responses differ according to platelet age. Methods A 14-marker flow cytometry panel was developed and applied to vehicle- or agonist-stimulated platelet-rich plasma samples obtained from healthy volunteers, or to platelets sorted according to SYTO-13 staining intensity as an indicator of platelet age. Data were analysed using both user-led and independent approaches incorporating novel machine learning-based algorithms. Results The assay detected changes in marker expression in healthy platelets, at rest and on agonist activation, that are consistent with the literature. Machine learning identified stimulated populations of platelets with high accuracy (>80%). Similarly, differentiation between young and old platelet populations achieved 76% accuracy, primarily weighted by FSC-A, CD41, SSC-A, GPVI, CD61, and CD42b expression patterns. Conclusions Our findings provide a novel assay to phenotype platelets coupled with a robust bioinformatics and machine learning workflow for deep analysis of the data. This could be valuable in characterising platelets in disease. (240 words) Essentials Platelet function is directed by the expression of specialised surface markers Circulating platelet sub-populations are incompletely characterised Multi-parameter spectral flow cytometry allows robust and comprehensive phenotyping of platelets Coupling multi-parameter spectral flow cytometry with machine learning offers a powerful method to determine platelet sub-populations