Natural patterns of physical activity in youth are characterized by brief periods of exercise of varying intensity interspersed with rest. To better understand systemic physiologic response mechanisms in children and adolescents, we examined five responses [heart rate (HR), respiratory rate (RR), oxygen uptake (V̇O2), carbon dioxide production (V̇CO2), and minute ventilation (V̇E), measured breath‐by‐breath] to multiple brief exercise bouts (MBEB). Two groups of healthy participants (early pubertal: 17 female, 20 male; late‐pubertal: 23 female, 21 male) performed five consecutive 2‐min bouts of constant work rate cycle‐ergometer exercise interspersed with 1‐min of rest during separate sessions of low‐ or high‐intensity (~40% or 80% peak work, respectively). For each 2‐min on‐transient and 1‐min off‐transient we calculated the average value of each cardiopulmonary exercise testing (CPET) variable (Y̅). There were significant MBEB changes in 67 of 80 on‐ and off‐transients. Y̅ increased bout‐to‐bout for all CPET variables, and the magnitude of increase was greater in the high‐intensity exercise. We measured the metabolic cost of MBEB, scaled to work performed, for the entire 15 min and found significantly higher V̇O2, V̇CO2, and V̇E costs in the early‐pubertal participants for both low‐ and high‐intensity MBEB. To reduce breath‐by‐breath variability in estimation of CPET variable kinetics, we time‐interpolated (second‐by‐second), superimposed, and averaged responses. Reasonable estimates of τ (<20% coefficient of variation) were found only for on‐transients of HR and V̇O2. There was a remarkable reduction in τHR following the first exercise bout in all groups. Natural patterns of physical activity shape cardiorespiratory responses in healthy children and adolescents. Protocols that measure the effect of a previous bout on the kinetics of subsequent bouts may aid in the clinical utility of CPET.

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, until this work no methods have identified which dynamic gas exchange or heart rate responses influence an individual's decision to start or stop physical activity. This research examines the use of advanced machine learning methods to predict completion of a test consisting of multiple exercise bouts by a group of healthy children and adolescents . All participants could complete the ten bouts at low or moderate-intensity work rates, however, when the bout work rates were highintensity, 50% refused to begin the subsequent exercise bout before all ten bouts had been completed (task failure). We explored machine learning strategies to model the relationship between the physiological time series, the participant's anthropometric 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 'failed' and 'success' 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 with generalized spectral additive models to identify key differences in the exercise-induced responses of participants in multiple bout exercise testing.

<p> 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, until this work no methods have identified which dynamic gas exchange or heart rate responses influence an individual’s decision to start or stop physical activity. This research examines the use of advanced machine learning methods to predict completion of a test consisting of multiple exercise bouts by a group of healthy children and adolescents. All participants could complete the ten bouts at low or moderate-intensity work rates, however, when the bout work rates were high-intensity, 50% refused to begin the subsequent exercise bout before all ten bouts had been completed (task failure). 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 ’failed’ and ’success’ 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 with generalized spectral additive models to identify key differences in the exercise-induced responses of participants in multiple bout exercise testing.</p>