ARTICLE IN PRESS JID: KNOSYS [m5G;February 22, 2016;21:22] Knowledge-Based Systems 000 (2016) 1–11 Contents lists available at ScienceDirect Knowledge-Based Systems journal homepage: www.elsevier.com/locate/knosys Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads U. Rajendra Acharya a,b,c , Hamido Fujita d , Vidya K. Sudarshan a,∗ , Shu Lih Oh a , Muhammad Adam a , Joel E.W. Koh a , Jen Hong Tan a , Dhanjoo N. Ghista e , Roshan Joy Martis f , Chua K. Chua a , Chua Kok Poo a , Ru San Tan g a Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore b Department of Biomedical Engineering, School of Science and Technology, SIM University, Singapore c Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Malaysia d Faculty of Software and Information Science, Iwate Prefectural University (IPU), Iwate, Japan e University 2020 Foundation, MA, USA f Department of Electronics and Communication Engineering, St. Joseph Engineering College, Mangalore, India g Department of Cardiology, National Heart Centre, Singapore a r t i c l e i n f o Article history: Received 23 September 2015 Revised 7 January 2016 Accepted 29 January 2016 Available online xxx Keywords: Electrocardiogram Discrete wavelet transform Myocardial infarction Classifier Entropy a b s t r a c t Identification and timely interpretation of changes occurring in the 12 electrocardiogram (ECG) leads is crucial to identify the types of myocardial infarction (MI). However, manual annotation of this complex nonlinear ECG signal is not only cumbersome and time consuming but also inaccurate. Hence, there is a need of computer aided techniques to be applied for the ECG signal analysis process. Going further, there is a need for incorporating this computerized software into the ECG equipment, so as to enable automated detection of MIs in clinics. Therefore, this paper proposes a novel method of automated de- tection and localization of MI by using ECG signal analysis. In our study, a total of 200 twelve lead ECG subjects (52 normal and 148 with MI) involving 611,405 beats (125,652 normal beats and 485,753 beats of MI ECG) are segmented from the 12 lead ECG signals. Firstly, ECG signal obtained from 12 ECG leads are subjected to discrete wavelet transform (DWT) up to four levels of decomposition. Then, 12 nonlin- ear features namely, approximate entropy (E x a ), signal energy ( x ), fuzzy entropy (E x f ), Kolmogorov–Sinai entropy (E x ks ), permutation entropy (E x p ), Renyi entropy (E x r ), Shannon entropy (E x sh ), Tsallis entropy (E x ts ), wavelet entropy (E x w ), fractal dimension (F x D ), Kolmogorov complexity (C x k ), and largest Lyapunov exponent (E x LLE ) are extracted from these DWT coefficients. The extracted features are then ranked based on the t value. Then these features are fed into the k-nearest neighbor (KNN) classifier one by one to get the high- est classification performance by using minimum number of features. Our proposed method has achieved the highest average accuracy of 98.80%, sensitivity of 99.45% and specificity of 96.27% in classifying nor- mal and MI ECG (two classes), by using 47 features obtained from lead 11 (V 5 ). We have also obtained the highest average accuracy of 98.74%, sensitivity of 99.55% and specificity of 99.16% in differentiating the 10 types of MI and normal ECG beats (11 class), by using 25 features obtained from lead 9 (V 3 ). In ad- dition, our study results achieved an accuracy of 99.97% in locating inferior posterior infarction by using only lead 9 (V 3 ) ECG signal. Our proposed method can be used as an automated diagnostic tool for (i) the detection of different (10 types of) MI by using 12 lead ECG signal, and also (ii) to locate the MI by analyzing only one lead without the need to analyze other leads. Thus, our proposed algorithm and com- puterized system software (incorporated into the ECG equipment) can aid the physicians and clinicians in accurate and faster location of MIs, and thereby providing adequate time available for the requisite treatment decision. © 2016 Elsevier B.V. All rights reserved. ∗ Corresponding author. Tel.: +65 91761371. E-mail address: vidya.2kus@gmail.com (V.K. Sudarshan). http://dx.doi.org/10.1016/j.knosys.2016.01.040 0950-7051/© 2016 Elsevier B.V. All rights reserved. Please cite this article as: U.R. Acharya et al., Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads, Knowledge-Based Systems (2016), http://dx.doi.org/10.1016/j.knosys.2016.01.040