Clustering temporal step-counting patterns for 24 hours with machine learning revealed potential heterogeneity in the categorization by a traditional tertile procedure.
S. S. Nawrin, H. Inada, H. Momma, R. Nagatomi
The paper uses machine learning to cluster 24-hour step-counting patterns from accelerometer data, revealing heterogeneity not captured by traditional tertile categorization.
bioRxiv · Jun 4, 2023 · PreprintAnimal Behavior & Cognition