System and method for automatically identifying physiological sound

Abstract

The invention provides a system for automatically identifying physiological sound, which comprises a collection module, a feature extraction module and an identification and classification module, wherein the collection module is used for collecting the physiological sound and converting the collected physiological sound into an electronic signal representing acoustic vibration; the feature extraction module is used for extracting a time domain feature value and a frequency domain feature value from the physiological sound; and the identification and classification module is used for classifying the time domain feature value and the frequency domain feature value and identifying at least one category to which the time domain feature value and the frequency domain feature value belong. According to the system for automatically identifying the physiological sound, identification and classification parameters of a pre-component in an identification and classification module are used for identifying features of potential abnormal physiological sound; the physiological sound category is identified according to the number of abnormal physiological sounds contained in one second, the whole process is based on an algorithm and is a quantifiable and standardized system, and the identification accuracy is high.

Description

technical field [0001] The invention relates to the technical field of medical identification, in particular to a system and method for automatically identifying physiological sounds. Background technique [0002] Physiological sounds include sounds from various organs such as heart sounds, lung sounds, bowel sounds, vascular echoes, tracheal breath sounds, bronchial breath sounds, and hand and foot breath sounds. Among them, breath sounds are commonly known as lung sounds, which can reflect the acoustic characteristics of the lung tissue, trachea and chest wall and other transmission media. Heart murmur is a kind of heart sound, which specifically refers to the abnormal sound produced by the vibration of the wall, valve or blood vessel caused by the turbulent flow of blood in the heart or blood vessel during systole or diastole, in addition to heart sound and extra heart sound. Noises with different frequencies, different intensities, and longer durations. Accurate analys...

AI Technical Summary

Problems solved by technology

[0005] The problem to be solved by the present invention is that existing stethoscopes often have different judgment results for the same patient's physiological sound auscultation due to differences in clinical experience and disease diagnosis level of different doctors, resulting in non-uniform auscultation standards

Images