Continuous Blood Pressure Measurement Method Based on the Pulse Image Sensor and BP Neural Network

A continuous pressure measurement method is proposed based the pulse image sensor and BP neural network for continuous measurement of arterial blood pressure. The multi-information synchronous acquisition system is built to collect pulse image sequences, sphygmopalpation pressure, probe internal pressure, and blood pressure of subjects. The feature vector is formed from pulse image sequences, sphygmopalpation pressure, and probe internal pressure to predict continuous blood pressure by BP neural network. The results show that the mean difference (MD) and standard deviation (SD) of systolic blood pressure (SBP) and diastolic blood pressure (DBP) meet the standard of Association for the Advancement of Medical Instrumentation (AAMI). The method could be used to predict continuous blood pressure and provides a new method for arterial continuous blood pressure measurement.