Authors: Juyoung Park Md Zakirul Alam Bhuiyan Mingon Kang Junggab Son Kyungtae Kang
Publish Date: 2016/10/21
Volume: 22, Issue: 4, Pages: 1225-1236
Abstract
Automatic interpretation of electrocardiograms provides a noninvasive and inexpensive technique for analyzing the heart activity of patients with a range of cardiac conditions We propose a method that combines locally weighted linear regression with nearest neighbor search for heartbeat detection and classification in the management of nonlifethreatening arrhythmia In the proposed method heartbeats are detected and their features are found using the Pan–Tompkins algorithm then they are classified by locally weighted linear regression on their nearest neighbors in a training set The results of evaluation on data from the MITBIH arrhythmia database indicate that the proposed method has a sensitivity of 9368 a positive predictive value of 9662 and an accuracy of 9807 for typeoriented evaluation and a sensitivity of 7415 a positive predictive value of 725 and an accuracy of 8869 for patientoriented evaluation These results are comparable to those from existing search schemes and contribute to the systematic design of automatic heartbeat classification systems for clinical decision supportThis work was partly supported by the MSIP Ministry of Science ICT and Future Planning Korea under the ITRC Information Technology Research Center support program IITP2016H8501161018 supervised by the IITP Institute for Information communications Technology Promotion and partly supported by IITP grant funded by the Korea government MSIP No B0101150557 Resilient CyberPhysical Systems Research
Keywords: