Predicting Human Metabolic Rate Based on Multiple Physiological Parameters: A Pilot Study

Accurate prediction of human metabolic rate is essential for thermal comfort evaluation. However, traditional static lookup table methods lack adaptability in dynamic scenarios. OBJECTIVE: As a preliminary study, this study aimed to reveal the correlation mechanism between four physiological parameters (heart rate, mean arterial pressure, skin conductance level, and ear temperature) and metabolic rate, comparatively analyze the performance of different input parameter combinations constructed by linear regression, support vector regression, and two-layer neural network, and ultimately evaluate the effectiveness of the pure physiological parameter-driven model. METHOD: We recruited 36 healthy young participants and obtained four physiological parameters under nine different levels of exercise through experiments. After that, we used the analytical method in ISO 8996:2021 to calculate metabolic rate as the predicted ground truth, then conducted correlation comparisons based on the training set and verified the effectiveness of multi-parameter combination pathways. The generalization performance of the full-parameter combination models of the three algorithms was evaluated based on the testing set. RESULT: Physiological parameters exhibit complementary sex-specific differences and interval-dependent characteristics in reflecting metabolic rate, with nonlinear relationships to the observed variable; full-parameter combinations effectively enhance model accuracy. The two-layer neural network model demonstrates superior predictive and generalization performance on the testing set; however, larger-sample studies are warranted to substantiate these findings. Current models, likely constrained by limited sample sizes, yield disproportionately large relative absolute errors under low metabolic rate conditions, indicating substantial room for improvement before practical deployment. SIGNIFICANCE: This study preliminarily confirmed the effectiveness of a combination of multiple physiological parameters in predicting metabolic rate.