Diagnosis of Obstructive apnea disease AHI in chemical warfare veterans based on HRV signals analysis using the MLP neural network

Sleep apnea is very common in patients with heart failure and is considered a major cause of death. The main causes of this apnea are patients unawareness, lack of diagnosis and ignoring the disease without considering any treatment. Currently, sleep apnea is being diagnosed primarily based on night Polysomnography. A complete recording, which is based on the apnea occurrence, is costly, cumbersome and difficult to conduct. The aim of this study is to provide an algorithm for diagnosis of sleep apnea from electrocardiogram signals of under treatment chemical warfare veterans. For this purpose, a study has been conducted with a combination of extracted features from changes in heart rate and signals of the electrocardiogram. Reducing the computational effort and the number of features as well as maintaining the high performance of the classifier are the subjects that are considered in this report. In other words, using ECG signal processing, especially HRV and EDR signal, the apnea is examined and in order to diagnose, the designed neural network in this study achieved specificity of %65.59, sensitivity of %48.68 and accuracy of %63.38. This test was conducted in Baqiyatallah Hospital and the mean absolute error in detecting AHI for 96 patients was 5.9. In order to evaluate the performance, the comprehensive Physionet database with specificity of %65.99, sensitivity of %44.88 and accuracy of %68.64 has been used in the MLP model, and for further investigation of the AHI, Patients were also studied in the formerly designed neural networks.

Keywords:

Intelligent model , prediction , obstructive sleep apnea , chemical warfare veterans , combined learning models , neural networks , AHI , obstructive apnea , MLP ,