Deteksi Aritmia pada Elektrokardiogram dengan Metode Jaringan Syaraf Tiruan Kelas Jamak menggunakan Fitur Interval RR, Lebar QRS, dan Gradien Gelombang R

Abstract

Intisari Penelitian untuk deteksi aritmia pada elektrokardiogram dengan metode Jaringan Syaraf Tiruan (JST) Multi-layer Perceptron-Backpropagation (MLP-BP) kelas jamak menggunakan fitur interval RR, interval QRS, serta gradien gelombang R telah berhasil dilaksanakan. Tipe aritmia yang dideteksi dalam penelitian adalah Premature Ventricular Contraction (PVC), Premature Atrial Contraction (PAC), dan Left Bundle Branch Block (LBBB). Pada penelitian ini dilakukan variasi jumlah fitur sebagai masukan JST, yaitu tiga macam fitur dan dua macam fitur. Hasil penelitian terbaik ditunjukkan pada variasi tiga macam fitur (interval RR, interval QRS, gradien gelombang R) dengan kinerja berupa sensitivitas, spesifisitas, serta akurasi cukup baik yaitu 94,63%, 93,94%, serta 94,49%. Abstract Research for arrhythmias detection using Multilayer Perceptron-Backpropagation (MLP-BP) Artificial Neural Network (ANN) multiclass method has been successfully implemented. It utilized RR interval, QRS width, and R wave gradient features. Arrhythmia types used in this study were Premature Ventricular Contraction (PVC), Premature Atrial Contraction (PAC), and Left Bundle Branch Block (LBBB). This study was conducted by varying features number as the input of ANN. The variation includes two and three kinds of features. The best results were found when three features were included. The best performance were 94.63%, 93.94%, and 94.49% in terms of sensitivity, sprcificity and accuracy, respectively. KATA KUNCI: Arrythmia, artificial neural network, electrocardiogram (ECG)