Classification of Cardiovascular Disease Using Machine Learning Model Aditya Wisnugraha Sugiyarto (a), Aminatus Saadah (a*), Vina Nurmadani (a), Prihantini (a)
a) Faculty of Mathematics and Natural Sciences, Bandung Institute of Technology
Jalan Ganesha 10, Bandung 40132, Indonesia
* aminatussaadah.math[at]gmail.com
Abstract
Cardiovascular disease (CVD), such as heart attack, coronary heart disease and stroke, is a disease that attacks the heart or blood vessels. According to the World Heart Federation (WHF), CVD is the number 1 killer in the world with 18.6 million deaths each year worldwide. CVD is detected based on an electrocardiogram (ECG), a recording of the heart^s electrical activity. It requires proper analysis and diagnosis of ECG signals to determine the type of abnormality or disease of the heart. In this research, a classification of heart disease was carried out using a machine learning model based on ECG signal data. The ECG signal is first denoised (cleaning the noise in the signal) using the Fast Fourier Transform (FFT). Then the signal data is extracted in the time-frequency domain using the Autoregressive Power Spectral Density (AR-PSD) transformation to obtain three main ones, namely magnitude, amplitude, and time. The data obtained are then classified using a machine learning model to determine the type of heart disease.
