Detection of borderline mental disorder on electrocardiosignals using EMD

Abstract

The goal is to develop a method for determining the final number of intrinsic mode functions (IMF) in electrocardiosignals (ECG) in patients under borderline mental disorder (BMD) to increase the reliability of diagnosis of cardiovascular diseases. Informative parameters of ECG, namely, IMFs, were used as the source materials. The empirical mode decomposition method of the Hilbert-Huang theory was used for effective processing of ECG. A method for determining the final number of IMFs in ECG in patients under BMD has been developed. The nature of the method is the adaptive processing of ECG using the EMD method, and determination of the finite number of IMFs and comparison with the threshold value. A block diagram of the developed method and a mathematical description are presented. The study of the method using the formed verified signal base of conditionally healthy patients and patients under BMD was carried out. In accordance with the results of the study, the developed method for determining the finite number of IMFs provides an increase in the accuracy of the determination of the BMD with a sensitivity factor of 93,7%, and a specificity of 96,9%.