Blood pressure monitoring method and device based on electrocardio-piezoelectric pulse wave coupling

Abstract

The invention discloses a blood pressure monitoring method and device based on electrocardio-piezoelectric pulse wave coupling. The blood pressure monitoring method comprises the following steps: obtaining piezoelectric pulse wave signals and electrocardiosignals; preprocessing the piezoelectric pulse wave signals and the electrocardiosignals to obtain a signal sequence and extracting features; according to the features, calculating pulse transmission time (PTT) and heart rate (HR) and segmenting the signal sequence; and and establishing a convolutional neural network-long and short term memory neural network (CNN-LSTM) model based on the mixed features, training the model by using the segmented signal sequence, and measuring a blood pressure by using the trained model.

Description

technical field [0001] The present application belongs to a blood pressure measurement method and equipment in the field of human health detection, and specifically relates to a machine learning blood pressure measurement method and equipment based on the mixed characteristics of piezoelectric pulse wave signals and electrocardiographic signals. Background technique [0002] Blood pressure refers to the pressure that blood exerts on the arterial wall when the heart contracts and relaxes to push the blood to flow around the body in the blood vessels. Blood pressure is usually represented by systolic blood pressure (SBP) and diastolic blood pressure (DBP). Systolic blood pressure refers to the blood pressure at which the blood pressure reaches its maximum value in the mid-systolic period of the ventricle, and diastolic blood pressure refers to the blood pressure at which the blood pressure gradually decreases when the ventricle relaxes and reaches the minimum value when the ven...

AI Technical Summary

Problems solved by technology

[0005] However, there are still some problems in the current research on blood pressure monitoring technology, mainly as follows: first, the accuracy of the single PTT method is low and does not meet the medical standards; second, the pulse wave signal used by researchers to study blood pressure measurement technology is basically It comes from the photoelectric pulse wave signal, and the photoelectric pulse wave signal mostly collects the change of capillary volume at the end of the human limbs, the signal is weak, the characteristics of double wave are not obvious, and it is easily affected by environmental noise

Third, at present, when analyzing the characteristics of pulse waves, the method of manually extracting features is mostly used, and its effectiveness is confirmed after limited sample experiments. Different researchers have different extraction of features, and there is no uniform standard.

Images