Wireless heart rhythm abnormality monitoring kit based on Raspberry PI

Abstract

According to statistics, heart diseases kill about 29,360 people every year in Malaysia and about 600,000 people in America. Heart monitoring kits are only available for bedridden patients, and the traditional heart monitoring kits have many wires that are obstacle patients’ mobility. Most of the existing heart monitoring kits can detect only one or two types of the heart diseases. Thus, the current study proposed a wireless heart monitoring kit to monitor patients with a heart abnormality. The proposed kit can detect and classify four arrhythmia types as well as normal ECG with high accuracy. The design and development of the wireless heart abnormality monitoring kit (WHAMK) in this research were divided into three stages. These stages are the development of an arrhythmias detection and classification method using artificial intelligence approach, design and implementation of the kit hardware, and design and coding of the kit software. Arrhythmias classification approach is divided into four stages, namely obtaining the electrocardiograph (ECG) signals, preprocessing, feature extraction and classification. The arrhythmia database of Massachusetts Institute of Technology (MIT) and signals from an ECG/arrhythmia simulator were used for training and testing of the WHAMK. There were 400 signals from MIT database and 116 signals from the ECG/arrhythmia were used. The ECG signals consist of normal sinus rhythm (NSR), premature atrial contraction (PAC), premature ventricles contraction (PVC), Bradycardia and Tachycardia. The features extraction methods are based on discrete wavelet transform (DWT) and statistical features. The statistical features are mean absolute value, root mean square, standard deviation, and median. The library support vector machine (LIBSVM) was used to classify the ECG signals. The results indicated that the statistical feature extraction approach gave a better result than the DWT when these two approaches were tested individually by using LIBSVM. The hardware of the kit is divided into two parts, namely ECG body sensor (EBS), and processing and displaying unit (PDU). EBS design involves ECG electrodes, ECG conditioning circuit, microcontroller, rechargeable battery, charging control module and Bluetooth module. PDU consists of Raspberry pi computer, Bluetooth module, 7-inch colored screen and power supply. Arrhythmias classification approach was developed by using statistical features and LIBSVM. They were implemented in the kit software to enable it to detect the arrhythmias in the real-time and fully automatically. The kit can detect and classify four arrhythmia types as well as NSR. These types of arrhythmia are PAC, PVC, Bradycardia and Tachycardia. The proposed kit gave a good accuracy for detecting and classifying Arrhythmia with the overall accuracy of 96.2%.