Combined Impact of Heart Rate Sensor Placements with Respiratory Rate and Minute Ventilation on Oxygen Uptake Prediction

Abstract

Oxygen uptake ( (Formula presented.) ) is an essential metric for evaluating cardiopulmonary health and athletic performance, which can barely be directly measured. Heart rate ( (Formula presented.) ) is a prominent physiological indicator correlated with (Formula presented.) and is often used for indirect (Formula presented.) prediction. This study investigates the impact of (Formula presented.) placement on (Formula presented.) prediction accuracy by analyzing (Formula presented.) data combined with the respiratory rate ( (Formula presented.) ) and minute ventilation ( (Formula presented.) ) from three anatomical locations: the chest; arm; and wrist. Twenty-eight healthy adults participated in incremental and constant workload cycling tests at various intensities. Data on (Formula presented.), (Formula presented.), (Formula presented.), and (Formula presented.) were collected and used to develop a neural network model for (Formula presented.) prediction. The influence of (Formula presented.) position on prediction accuracy was assessed via Bland–Altman plots, and model performance was evaluated by mean absolute error (MAE), coefficient of determination (R2), and mean absolute percentage error (MAPE). Our findings indicate that (Formula presented.) combined with (Formula presented.) and (Formula presented.) ( (Formula presented.) ) produces the most accurate (Formula presented.) predictions (MAE: 165 mL/min, R2: 0.87, MAPE: 15.91%). Notably, as exercise intensity increases, the accuracy of (Formula presented.) prediction decreases, particularly within high-intensity exercise. The substitution of (Formula presented.) with different anatomical sites significantly impacts (Formula presented.) prediction accuracy, with wrist placement showing a more profound effect compared to arm placement. In conclusion, this study underscores the importance of considering (Formula presented.) placement in (Formula presented.) prediction models, with (Formula presented.) and (Formula presented.) serving as effective compensatory factors. These findings contribute to refining indirect (Formula presented.) estimation methods, enhancing their predictive capabilities across different exercise intensities and anatomical placements.