Ahmad Thariq, Mohd Shahrizal Sunar, Herman Tolle
Current methods for arrhythmia detection often lack accessible, educational tools for understanding heart conditions. This study addresses that gap by developing a minimalist, user-friendly arrhythmia detection system, particularly suited for educational purposes, utilizing a three-dimensional human heart model in a Unity environment. The model receives electrocardiogram (ECG) data from a CSV file containing timestamps and mV values from two leads (based on the MIT-BIH arrhythmia database) and visualizes the heart’s beat-by-beat activity. The system can detect four types of arrhythmias, although the visualizations currently focus on Premature Atrial Contractions (PAC) and Premature Ventricular Contractions (PVC). A convolutional neural network (CNN) is used to detect arrhythmias with an overall accuracy of 99.7%. This tool enhances understanding of cardiac activity, offering a more engaging, educational alternative to traditional ECG readings, helping users visualize and learn about heart function more effectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
Informatics Engineering Department, Faculty of Computer Science, Universitas Brawijaya, Malang, 65145, Indonesia; Media and Game Innovation Centre of Excellence, Institute of Human Centered Engineering, Universiti Teknologi Malaysia, Johor Bahru, 81310, Malaysia; Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, 81310, Malaysia
