Non-invasive Continuous Blood Pressure Measurement Based On Mean Impact Value Method,BP Neural Network,and Genetic Algorithm

Blood pressure is one of the important physiological parameters of the human body,which can reflect the functional status of the human cardiovascular and cerebrovascular systems to a certain extent,and is an important basis in the diagnosis of disease,evaluation of treatment efficacy,and prognostication.Because human blood pressure is affected by a number of factors,such as mood,physiological cycle,physical condition,and the external environment,the results of single or discontinuous measurement fluctuate,while continuous measurement can monitor blood pressure throughout each cardiac cycle.Therefore,continuous blood pressure measurement is of great significance for clinical and medical researches.To address the shortcomings of existing blood pressure measurement models based on pulse wave transit time(PWTT)or pulse wave parameters(PWPs),and correction and detection accuracy problems caused by individual differences,a new method of non-invasive continuous blood pressure measurement—the GA-MIV-BP neural network model—is presented.Results revealed no marked differences between the blood pressure values calculated by the model and the actual measured blood pressure values.The two values were consistent and interchangeable.Therefore,this algorithm is of great significance to promote the clinical application of a non-invasive continuous blood pressure monitoring method.The main research work and achievements of this paper are as follows:1.This paper deeply analyzed research status of the methods of non-invasive continuous blood pressure measurement at home and abroad,and studied the physiological basis of pulse wave and blood pressure.Based on the exploration of the feasibility of PWPs and PWTT measurement of blood pressure,a method of blood pressure measurement based on PWPs and PWTT is proposed.2.A denoising algorithm of pulse wave signal based on DTCWT-Spline and feature points recognition algorithm of pulse wave based on DTCWT-SW-DM are proposed.Through in-depth analysis of various sources of interference,spectrum distribution characteristics,waveform characteristics and the shortcomings of existing pulse wave signal processing methods in pulse wave signals,effective algorithms are designed to purify and process pulse wave signals and identify feature points.3.A denoising algorithm of ECG signal based on DTCWT-MF and cardiac R-wave detection algorithm based on DTCWT-SW are proposed.Aiming at the shortcomings of existing ECG signal processing methods,an effective ECG signal purification method and R-wave extraction method are designed.4.A new method of non-invasive continuous blood pressure measurement—the GA-MIV-BP neural network model—is presented.By extracting the characteristic parameters of denoised ECG signals and pulse wave signals,PWPs and PWTT are obtained.The mean impact value(MIV)method is used to select the factors that greatly influence blood pressure from the extracted PWTT and PWPs.These factors are used as inputs,and the actual blood pressure values as outputs,to train the BP neural network model.The individual parameters are then optimized using a genetic algorithm(GA)to establish a continuous blood pressure monitoring model for a single individual.