Predicting Heart Health with Advanced Neural Networks

Coronary vascular disease (CHD) is one of the most fatal diseases worldwide. Cardiovascular diseases are not easily diagnosed in early disease stages. Early diagnosis is important for effective treatment, however, medical diagnoses are based on physician’s personal experiences of the disease which increase time and testing cost to reach diagnosis. Physicians assess patients’ condition based on electrocardiography, sonography and blood test results. In this research we develop a classification model of the functional state of the cardiovascular system based on the monitoring of the evolution of the amplitudes of the first and second harmonics of the system rhythm of ۰.۱ Hz. We separate the signal into three streams; the first stream works with natural electrocardio signal, the other two streams are obtained as a result of frequency analysis of the amplitude- and frequency-detected electrocardio signal. We use a sliding window of a demodulated electrocardio signal by means of amplitude and frequency detectors. The developed NN model showed an increase in accuracy of diagnostic efficiency by ۱۱%. The neural network model can be trained to give accurate early detection of disease class.

کلیدواژه ها:

System rhythms ، signal demodulation ، electrocardiosignal ، spectral analysis ، neural networks