A Novel BCG Heart Rate Detection System Using a Piezoelectric Sensor Embedded in a Shoe Insole

Smart insoles are a tool with great potential for monitoring physiological parameters, including heart rate (HR), whose measurement on the sole of the foot remains a challenge. In this work, a new system for beat-to-beat HR detection based on the measurement of the ballistocardiogram (BCG) with a piezoelectric sensor embedded in a commercial insole is presented. BCG is a noninvasive method for measuring whole-body recoil forces in reaction to cardiac ejection of blood through the vascular tree at each heartbeat, thus eliminating the need to detect any specific artery or to establish direct contact with the skin. The validation of the proposed system was done with 25 subjects: BCG and an electrocardiogram (ECG) lead I were acquired simultaneously for 2 min while standing or sitting with no instructions to maintain silence or refrain from moving. A signal segmentation process was performed to discard segments contaminated by motion artifacts, achieving a mean coverage factor (CF) above 95% in both positions. For beat-to-beat HR detection from the BCG, an algorithm based on the continuous wavelet transform (CWT) was used, which yielded a mean of true positives (TPs) detected of 82.7% in standing position and 91.8% in seated position. To assess the agreement between the HR values obtained from BCG and ECG, a Bland-Altman plot was used to compare them. The 95% confidence intervals (CIs) in beats per minute (bpm) were ±3.64 and ±3.21 bpm in the standing and seated positions, respectively, meeting the accuracy limits recommended by the AAMI standard for HR meters.