Clustering temporal step-counting patterns for 24 hours with machine learning revealed potential heterogeneity in the categorization by a traditional tertile procedure

ObjectivesPhysical activity is a crucial aspect of health benefits in the public society. Although studies on the temporal physical activity patterns might lead to the protocol for efficient intervention/program, a standardized procedure to determine and analyze the temporal physical activity patterns remains to be developed. Here, we attempted to develop a procedure to cluster 24-hour patterns of physical activity as step counts measured with an accelerometer-based wearable sensor. MethodsData was collected from 42 healthy participants, comprising 35 males and 7 females, at the Sendai Oroshisho center in 2008. Using unsupervised machine learning, specifically the kernel k-means algorithm with the global alignment kernel was applied on a total of 815 days from 42 participants, and 6 activity patterns were identified. Further, the probability of each 24-hour step-counting pattern was calculated for every participant., and was used in MATLAB to apply spectral clustering, and 5 activity behaviors were identified. ResultsWe could identify six 24-hour step-counting patterns and five daily step-behavioral clusters. When the amount of physical activity was categorized into tertile groups reflecting highly active, moderately active, and low active, each tertile group consisted of different proportions of six 24-hour step-counting patterns. ConclusionsOur study introduces a novel approach using an unsupervised machine learning method to categorize daily hourly activity, revealing six distinct step counting patterns and five clusters representing daily step behaviors. Our procedure would be reliable for finding and clustering physical activity patterns/behaviors and reveal heterogeneity in the categorization by a traditional tertile procedure using total step amount.