Central arterial pressure waveform reconstruction system and method

Abstract

The invention discloses a central arterial pressure waveform reconstruction system and method, a peripheral artery pulse wave measurement module of the reconstruction system sends measured peripheral artery pulse waves to a pulse wave correction module for correction, and outputs corrected pulse wave data to a central arterial pressure reconstruction calculation module; and the central arterial pressure reconstruction calculation module is composed of an input layer, a calculation layer and an output layer. The input layer receives the corrected peripheral artery pulse waves and inputs the corrected peripheral artery pulse waves to the calculation layer, the calculation layer is composed of a plurality of long-short-term memory units, and each long-short-term memory unit receives signals of the input layer at the current moment and output of the long-short-term memory unit at the previous moment; each long-short-term memory unit outputs to the output layer and simultaneously serves as the input of the long-short-term memory unit at the next moment; and the output layer outputs the finally reconstructed central arterial pressure pulse wave to a data display module. According to the method, end-to-end central arterial pressure waveform reconstruction can be automatically realized, and the reconstruction accuracy is obviously superior to that of a traditional method.

Description

technical field [0001] The invention relates to a central arterial pressure waveform reconstruction system and method, in particular to a system and method for realizing non-invasive reconstruction of peripheral arterial to central aortic blood pressure waveform by using a bilateral long-short-term memory artificial neural network, belonging to artificial intelligence and medical device technology the cross field. Background technique [0002] Central arterial pressure waveform refers to the curve of ascending aortic root blood pressure over time, which contains rich physiological and pathological information of the human body. By extracting the parameters of the central arterial pressure waveform, such as systolic pressure, diastolic pressure, average pressure, pulse pressure, reflex intensity, augmentation index, ejection time, cardiac output, etc., the physiological and pathological conditions of the tester can be evaluated and predicted. Moreover, some clinical studies ...

AI Technical Summary

Problems solved by technology

[0009] Aiming at the problems faced by existing non-invasive central arterial pressure waveform reconstruction methods and devices, such as difficulties in establishing simulation models, inaccurate parameter estimation, and relatively large reconstruction errors, the present invention proposes a system and method for central arterial pressure waveform reconstruction. It adopts a new central arterial pressure waveform reconstruction method based on bilateral long-short-term memory neural network. This method does not need to establish an intermediate simulation model and its parameter estimation link, and directly realizes end-to-end central arterial pressure reconstruction. To drive, establish a sequence-to-sequence waveform prediction model to realize reconstruction and detection from peripheral arterial pressure waveform to central arterial pressure waveform

Images