Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads
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,...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Published: |
Elsevier
2016
|
| Subjects: |
| _version_ | 1796960418137112576 |
|---|---|
| author | Acharya, U.R. Fujita, H. Sudarshan, V.K. Oh, S.L. Adam, M. Koh, J.E.W. Tan, J.H. Ghista, D.N. Martis, R.J. Chua, C.K. Poo, C.K. Tan, R.S. |
| author_facet | Acharya, U.R. Fujita, H. Sudarshan, V.K. Oh, S.L. Adam, M. Koh, J.E.W. Tan, J.H. Ghista, D.N. Martis, R.J. Chua, C.K. Poo, C.K. Tan, R.S. |
| author_sort | Acharya, U.R. |
| collection | UM |
| description | 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 detection 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 nonlinear features namely, approximate entropy (Eax), signal energy (Ωx), fuzzy entropy (Efx), Kolmogorov-Sinai entropy (Eksx), permutation entropy (Epx), Renyi entropy (Erx), Shannon entropy (Eshx), Tsallis entropy (Etsx), wavelet entropy (Ewx), fractal dimension (FDx), Kolmogorov complexity (Ckx), and largest Lyapunov exponent (ELLEx) 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 highest 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 normal and MI ECG (two classes), by using 47 features obtained from lead 11 (V5). 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 (V3). In addition, our study results achieved an accuracy of 99.97% in locating inferior posterior infarction by using only lead 9 (V3) 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 computerized 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. |
| first_indexed | 2024-03-06T05:44:17Z |
| format | Article |
| id | um.eprints-18048 |
| institution | Universiti Malaya |
| last_indexed | 2024-03-06T05:44:17Z |
| publishDate | 2016 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | um.eprints-180482017-10-23T03:25:35Z http://eprints.um.edu.my/18048/ Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads Acharya, U.R. Fujita, H. Sudarshan, V.K. Oh, S.L. Adam, M. Koh, J.E.W. Tan, J.H. Ghista, D.N. Martis, R.J. Chua, C.K. Poo, C.K. Tan, R.S. TA Engineering (General). Civil engineering (General) 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 detection 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 nonlinear features namely, approximate entropy (Eax), signal energy (Ωx), fuzzy entropy (Efx), Kolmogorov-Sinai entropy (Eksx), permutation entropy (Epx), Renyi entropy (Erx), Shannon entropy (Eshx), Tsallis entropy (Etsx), wavelet entropy (Ewx), fractal dimension (FDx), Kolmogorov complexity (Ckx), and largest Lyapunov exponent (ELLEx) 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 highest 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 normal and MI ECG (two classes), by using 47 features obtained from lead 11 (V5). 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 (V3). In addition, our study results achieved an accuracy of 99.97% in locating inferior posterior infarction by using only lead 9 (V3) 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 computerized 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. Elsevier 2016 Article PeerReviewed Acharya, U.R. and Fujita, H. and Sudarshan, V.K. and Oh, S.L. and Adam, M. and Koh, J.E.W. and Tan, J.H. and Ghista, D.N. and Martis, R.J. and Chua, C.K. and Poo, C.K. and Tan, R.S. (2016) Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads. Knowledge-Based Systems, 99. pp. 146-156. ISSN 0950-7051, DOI https://doi.org/10.1016/j.knosys.2016.01.040 <https://doi.org/10.1016/j.knosys.2016.01.040>. http://dx.doi.org/10.1016/j.knosys.2016.01.040 doi:10.1016/j.knosys.2016.01.040 |
| spellingShingle | TA Engineering (General). Civil engineering (General) Acharya, U.R. Fujita, H. Sudarshan, V.K. Oh, S.L. Adam, M. Koh, J.E.W. Tan, J.H. Ghista, D.N. Martis, R.J. Chua, C.K. Poo, C.K. Tan, R.S. Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads |
| title | Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads |
| title_full | Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads |
| title_fullStr | Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads |
| title_full_unstemmed | Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads |
| title_short | Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads |
| title_sort | automated detection and localization of myocardial infarction using electrocardiogram a comparative study of different leads |
| topic | TA Engineering (General). Civil engineering (General) |
| work_keys_str_mv | AT acharyaur automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads AT fujitah automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads AT sudarshanvk automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads AT ohsl automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads AT adamm automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads AT kohjew automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads AT tanjh automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads AT ghistadn automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads AT martisrj automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads AT chuack automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads AT poock automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads AT tanrs automateddetectionandlocalizationofmyocardialinfarctionusingelectrocardiogramacomparativestudyofdifferentleads |