Functional Data Methods for Understanding Human Physiological System Responses to Exercise

Physiological response to physical exercise through analysis of cardiopulmonary measurements has been shown to be predictive of a variety of diseases. Nonetheless, the clinical use of exercise testing remains limited because interpretation of test results requires experience and specialized training. Additionally, the type and duration of the exercise testing most effective for prediction of fitness and disease remains controversial. This research examines the use of advanced machine learning methods to understand physiological mechanisms and to predict exercise test completion in a protocol consisting of multiple exercise bouts. Cardiopulmonary signals of 81 healthy children were captured breath-by-breath during these exercise bouts. We explored machine learning strategies to model the relationship between the physiological time series, the participant's demographic variables, and the binary outcome variable indicating whether the participant completed the test. The best performing model, a generalized spectral additive model with functional and scalar covariates, achieved 93.6% classification accuracy and an F1 score of 93.5%. Additionally, functional analysis of variance testing showed that participants in the `quit' and `not-quit' groups have significantly different functional means in three signals: heart rate, oxygen uptake rate, and carbon dioxide uptake rate. Overall, these results show the capability of functional data analysis to identify key differences in the exercise-induced responses of participants in multiple bout exercise testing.