Nearest neighbor search with locally weighted linear regression for heartbeat classification
- 216 Downloads
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 non-life-threatening 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 MIT-BIH arrhythmia database indicate that the proposed method has a sensitivity of 93.68 %, a positive predictive value of 96.62 %, and an accuracy of 98.07 % for type-oriented evaluation; and a sensitivity of 74.15 %, a positive predictive value of 72.5 %, and an accuracy of 88.69 % for patient-oriented 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 support.
KeywordsHeartbeat classification Electrocardiogram monitoring Locally weighted linear regression Nearest neighbor search
This work was partly supported by the MSIP (Ministry of Science, ICT and Future Planning), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2016-H8501-16-1018)) supervised by the IITP (Institute for Information & communications Technology Promotion), and partly supported by IITP grant funded by the Korea government (MSIP) (No. B0101-15-0557, Resilient Cyber-Physical Systems Research).
Compliance with ethical standards
Conflict of interest
No competing financial interests exist.
- AAMI (1998) Testing and reporting Performance results of cardiac rhythm and ST-segment measurement algorithms. Association for the Advancement of Medical Instrumentation, ANSI/AAMI Std. EC57:1998Google Scholar
- Almeida R, Martínez JP, Olmos S et al (2003) Automatic delineation of T and P wave using a wavelet-based multiscale approach. In: Presented at the international congress on computational bioengineering, Espan̄aGoogle Scholar
- Belgacem N, Bereksi-Reguig F (2011) Bluetooth portable device for ECG and patient motion monitoring. Nat Technol 4:19–23Google Scholar
- D’Angelo LT, Tarita E, Zywietz TK et al (2010) A system for intelligent home care ECG upload and priorisation. In: Presented at the 32nd international conference of the IEEE engineering in medicine and biology society, MinneapolisGoogle Scholar
- de Oliveira LSC, Andreo RV, Sarcinelli-Filho M (2011) Premature ventricular beat classification using a dynamic Bayesian network. In: Presented at the 33nd international conference of the IEEE engineering in medicine and biology society, BostonGoogle Scholar
- Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. SIGKDD Explor 11:10–18Google Scholar
- Hu YH, Palreddy S, Tompkins WJ (1997) A patient-adaptable ECG beat classifier using a mixture of experts approach. IEEE Trans Biomed Eng 44:891–900Google Scholar
- Ko SY, Wang KM, Lian WC et al. (2012) A portable ECG recorder. In: Presented at the 2nd international conference on consumer electronics, communications and networks, YichangGoogle Scholar
- Park J, Lee K, Kang K (2013) Arrhythmia detection from heartbeat using k-nearest neighbor classifier. IEEE international conference on bioinformatics and biomedicine, ShanghaiGoogle Scholar
- Prasad GK, Sahambi JS (2003) Classification of ECG arrhythmias using multi-resolution analysis and neural networks. In: Presented at the international conference on convergent technologies for the Asia-Pacific region, BangaloreGoogle Scholar
- Tello PJP, Manjarres O, Quijano M et al (2012) Remote monitoring system of ECG and temperature signals using Bluetooth. In: Presented at the IEEE symposium on information technology in medicine and education, HokodateGoogle Scholar
- Vohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Presented at the international joint conference on artificial intelligence, MontrealGoogle Scholar
- Yeap TH, Johnson F, Rachniowski M (1990) ECG beat classification by a neural network. In: Presented at the international conference of the IEEE engineering in medicine and biology society, PhiladelphiaGoogle Scholar
- Zhang L, Peng H, Yu C (2010) An approach for ECG classification based on wavelet feature extraction and decision tree. In: Presented at the international conference on wireless communications and signal processing, SuzhouGoogle Scholar