The Cuffless Blood Pressure Measurement with Multi-dimension Regression Model based on Characteristics of Pulse Waveform

According to the advancement of wearable technology, many physiological monitoring instruments are gradually converted into wearable devices. But, the blood pressure monitor still is a cuff-type device in the consumer market, which also does not do the beat-by-beat continuous blood pressure measurement. Now, the cuffless blood pressure measurement has been developed based on the pulse transit time (PTT) but its accuracy is not better. According to the cardiac hemodynamic theorem, the blood pressure relates with the arterial characteristics. Therefore, the purpose of this study was to use the characteristics of the pulse wave measured by photoplethysmography (PPG) to estimate the blood pressure with a multi-dimension regression model. The contour of pulse wave includes some characteristics of the artery. There were 10 subjects participating the experiment, and the blood pressure of the subject was changed by the exercise. The results showed that the cumulate root mean square error of the estimated systolic and diastolic pressures with the multi-parameters were 69.3 mmHg and 39.8 mmHg were better than only using one parameter, PTT, 82.1 mmHg and 45.2 mmHg, respectively.