A Blood Pressure Monitoring Device with Tactile and Tension Sensors Assisted by a Machine Learning Technique

This work presents the development of a continuous blood pulse-wave monitoring system with a highly sensitive tactile sensing array and tension sensor. The key element of the sensing device is a conductive polymer film that is patterned with microdome structures to enhance pressure sensitivity. The proposed array-type configuration greatly facilitates the measurement of blood pulse waves. In addition, the tension sensor, which detects the strap tension during pulse wave measurement, is capable of estimating the optimal conditions for measuring high-quality blood pulse waves. Furthermore, a machine-learning algorithm, the support vector regression, is employed for estimating the systolic blood pressure (SBP) and diastolic blood pressure (DBP) from the measured pulse-wave signals. The R
²
between the estimated SBP and the reference SBP was 0.724, and the R
²
between the estimated DBP and the reference DBP was 0.769.