Key result
A machine learning-based 14-marker flow cytometry workflow identified stimulated platelet populations with >80% accuracy and differentiated young from old platelets with 76% accuracy.
Why the study?
Platelet function depends on surface markers and distinct circulating platelet subpopulations have emerged, but their exact nature remains debatable.
Population
Platelet-rich plasma and whole blood samples from healthy volunteers
Comparison
Vehicle- vs agonist-stimulated platelets, and young vs old platelets sorted by SYTO-13 staining intensity
Design
Laboratory phenotyping and machine learning validation study
Authors
Loading...
Spectral cytometry refines platelet subpopulation phenotyping; hypothesis-generating for clinical thrombosis relevance, prospective validation needed.
A novel 14-marker spectral flow cytometry panel coupled with machine learning accurately phenotypes platelet subpopulations by activation status and age, providing a robust tool for future disease characterization.
Vadgama et al. (2024) studied Healthy. Machine learning-based spectral flow cytometry phenotyping was evaluated on Accuracy of identifying stimulated platelets and differentiating young from old platelets. A machine learning-based 14-marker flow cytometry workflow identified stimulated platelet populations with >80% accuracy and differentiated young from old platelets with 76% accuracy.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: