Bidirectional RNN based early prediction of CVDs using ECG Signals for Type 2 diabetic patients

Abstract

The ECG signal is important for early diagnosis of heart abnormalities. Type 2 Diabetic individuals’ ECG signals provide pertinent data about their hearts and are one of the most important diagnostic techniques used by doctors to identify cardiovascular diseases. The suggested study uses feature extraction and Bi-RNN based classification to analyse ECG signals of Type 2 patients. To reduce noise from the ECG signal, a hybrid preprocessing filter made up of a Median and Savitzky-Golay filter. Undecimated dual tree complex wavelet transform (UDTCWT) along with Detrended fluctuation (DA) analysis and empirical orthogonal function (EOF) analysis are then used to extract features. These features are classified with Bidirectional RNN. The proposed method was tested on the MIT-BIH, Physionet and DICARDIA databases, and the findings show that it achieves an average accuracy of 97.6% when compared to conventional techniques.