A Heart Sound Diagnosis System Using Deep Learning and Low Difference Forest

Abstract

The present invention provides a heart sound diagnosis system combining deep learning and low difference forest, including a preprocessing module, which is configured to preprocess the acquired heart sound signal, and perform normalization, filtering and downsampling processing on the heart sound signal in sequence. ; The data conversion module is configured to extract audio features from the down-sampled data to generate second-order spectral data; the deep learning module is configured to use the trained deep learning model to perform feature extraction on the second-order spectral data; Feature classification module , which is configured to classify the extracted features using the trained low-discrepancy forest classifier to obtain a classified diagnosis result. The invention has lower requirements on professional equipment and personnel, and has portability and universality.

Description

technical field [0001] The invention belongs to the technical field of intelligent diagnosis, and in particular relates to a heart sound diagnosis system combining deep learning and low-difference forest. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Heart disease is one of the important diseases that affect human health. For patients with coronary heart disease and other heart diseases, early diagnosis and treatment can effectively prevent the deterioration of the condition and reduce the mortality rate. [0004] At present, the mainstream diagnosis method in the hospital is to conduct a preliminary diagnosis of the patient's heart through the electrocardiogram or heart sounds. However, both diagnostic methods have some problems. Although the former is accurate and easy to judge, it requires relevant professional equipment; although t...

AI Technical Summary

Problems solved by technology

Although the former is accurate and easy to judge, it requires relevant professional equipment; although the latter is low in cost, it requires a higher level of experience for doctors, and many areas cannot be equipped with professional equipment or experienced doctors in time. The correct diagnosis has a greater impact on

[0005] Some R&D personnel have begun to use deep learning models for auxiliary diagnosis, but some of the existing models have complex algorithms and huge network structures, making it difficult to deploy on mobile terminals. question of making judgments

Images