Classified detection system for various apnea syndromes

Abstract

The invention discloses a classification detection system for various apnea syndromes based on an Efficient NeT neural network, and belongs to the field of snore detection and disease discrimination.The system comprises an audio collection module, a snore extraction module, a feature extraction module, a snore recognition module and a statistical judgment module, and the audio collection module is used for collecting audios of a detected patient in the whole night sleep state; the snore extraction module is used for extracting all snore segment audios in the complete audio; the feature extraction module is used for carrying out feature extraction on the collected snore sections; the snore recognition module is used for automatically recognizing and detecting various snores of all snore sections by using a model based on the Efficient NeT neural network; and the statistical judgment module is used for carrying out statistics on various snore conditions and completing classified detection on various apnea syndromes according to the AHI indexes.

Description

technical field [0001] The invention relates to the fields of snoring sound detection and disease discrimination, in particular to a classification detection system for various apnea syndromes based on EfficientNeT neural network. Background technique [0002] Sleep apnea syndrome (OSAHS) is a sleep disorder in which breathing stops during sleep. It is characterized by more than 30 apnea during continuous 7h sleep, each time the air flow is stopped for more than 10s (including 10s), or the average hourly low The number of ventilations (respiratory disorder index) exceeds 5 times, which causes the clinical syndrome of chronic hypoxemia and hypercapnia. Generally, it can be divided into central type, obstructive type and mixed type. Due to repeated episodes of hypoxemia and hypercapnia, neurological dysfunction, catecholamine, endothelin and renin-angiotensin system disorders, endocrine dysfunction and hemodynamic changes will occur in this disease, which will be more serious...

AI Technical Summary

Problems solved by technology

Although the device is accurate and reliable, it has many shortcomings such as inconvenient to carry, high price, and influence on sleep, so that most patients cannot be diagnosed in time.

Images