Classifying Heart Sounds Using Images of Motifs, MFCC and Temporal Features
- 110 Downloads
Cardiovascular disease is the leading cause of death in the world, and its early detection is a key to improving long-term health outcomes. The auscultation of the heart is still an important method in the medical process because it is very simple and cheap. To detect possible heart anomalies at an early stage, an automatic method enabling cardiac health low-cost screening for the general population would be highly valuable. By analyzing the phonocardiogram signals, it is possible to perform cardiac diagnosis and find possible anomalies at an early-term. Therefore, the development of intelligent and automated analysis tools of the phonocardiogram is very relevant. In this work, we use simultaneously collected electrocardiograms and phonocardiograms from the Physionet Challenge database with the main objective of determining whether a phonocardiogram corresponds to a “normal” or “abnormal” physiological state. Our main contribution is the methodological combination of time domain features and frequency domain features of phonocardiogram signals to improve cardiac disease automatic classification. This novel approach is developed using both features. First, the phonocardiogram signals are segmented with an algorithm based on a logistic regression hidden semi-Markov model, which uses electrocardiogram signals as a reference. Then, two groups of features from the time and frequency domain are extracted from the phonocardiogram segments. One group is based on motifs and the other on Mel-frequency cepstral coefficients. After that, we combine these features into a two-dimensional time-frequency heat map representation. Lastly, a binary classifier is applied to both groups of features to learn a model that discriminates between normal and abnormal phonocardiogram signals. In the experiments, three classification algorithms are used: Support Vector Machines, Convolutional Neural Network, and Random Forest. The best results are achieved when both time and Mel-frequency cepstral coefficients features are considered using a Support Vector Machines with a radial kernel.
KeywordsPhonocardiogram Electrocardiogram Mel-frequency cepstral coefficients Motifs Time features
This work is supported by the NanoSTIMA Project: Macro-to-Nano Human Sensing: Towards Integrated Multimodal Health Monitoring and Analytics/NORTE-01-0145-FEDER-000016 which is financed by the North Portugal Regional Operational Programme (NORTE 2020), under the PORTUGAL 2020 Partnership Agreement, and through the European Regional Development Fund (ERDF).
This study was funded by the NanoSTIMA Project: Macro-to-Nano Human Sensing: Towards Integrated Multimodal Health Monitoring and Analytics/ NORTE-01-0145-FEDER-000016 which is financed by the North Portugal Regional Operational Programme (NORTE 2020), under the PORTUGAL 2020 Partnership Agreement, and through the European Regional Development Fund (ERDF).
Compliance with Ethical Standards
Conflict of interests
Informed consent was obtained from all individual participants included in the study.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
- 1.Physiobank atm. https://physionet.org/cgi-bin/atm/ATM
- 2.Balili, C.C., Sobrepena, M.C.C., and Naval, P.C.: Classification of heart sounds using discrete and continuous wavelet transform and random forests. In: 2015 3Rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 655–659, 2015Google Scholar
- 3.Barschdorff, D., Bothe, A., and Rengshausen, U.: Heart sound analysis using neural and statistical classifiers: a comparison. In:  Proceedings. Computers in Cardiology, pp. 415–418, 1989Google Scholar
- 4.Boussaa, M., Atouf, I., Atibi, M., and Bennis, A.: Ecg signals classification using mfcc coefficients and ann classifier. In: 2016 International Conference on Electrical and Information Technologies, pp. 480–484, 2016Google Scholar
- 5.Castro, N., and Azevedo, P.: Multiresolution Motif Discovery in Time Series, pp. 665–676. https://doi.org/10.1137/1.9781611972801.73
- 7.Clifford, G.D., Liu, C., Moody, B., Springer, D., Silva, I., Li, Q., and Mark, R.G.: Classification of normal/abnormal heart sound recordings: The physionet/computing in cardiology challenge 2016. In: 2016 Computing in Cardiology Conference (cinc), pp. 609–612, 2016Google Scholar
- 8.Colonna, J., Peet, T., Ferreira, C.A., Jorge, A.M., Gomes, E.F., and Gama, J.A.: Automatic classification of anuran sounds using convolutional neural networks. In: Proceedings of the Ninth International C* Conference on Computer Science & Software Engineering, C3S2E ’16, pp. 73–78. ACM, 2016Google Scholar
- 10.Gomes, E., Bentley, P., Coimbra, M., Pereira, E., and Deng, Y.: Classifying heart sounds: Approaches to the pascal challenge pp 337–340, 2013Google Scholar
- 11.Gomes, E.F., Jorge, A.M., and Azevedo, P.J.: Classifying heart sounds using multiresolution time series motifs: an exploratory study. In: Proceedings of the International C* Conference on Computer Science and Software Engineering, pp. 23–30. ACM, 2013Google Scholar
- 12.Gomes, E.F., Jorge, A.M., and Azevedo, P.J.: Classifying heart sounds using sax motifs, random forests and text mining techniques. In: Proceedings of the 18th International Database Engineering & Applications Symposium, pp. 334–337. ACM, 2014Google Scholar
- 13.Huiying, L., Sakari, L., and Iiro, H.: A heart sound segmentation algorithm using wavelet decomposition and reconstruction. In: Engineering in Medicine and Biology Society, 1997. Proceedings of the 19th Annual International Conference of the IEEE, vol. 4, pp. 1630–1633, 1997Google Scholar
- 14.Inc., P.T.: Collaborative data science. https://plot.ly, 2015
- 15.Kishore, K.V.K., and Satish, P.K.: Emotion recognition in speech using mfcc and wavelet features. In: 2013 3rd IEEE International Advance Computing Conference (IACC), pp. 842–847, 2013Google Scholar
- 16.Kumar, D., Carvalho, P., Antunes, M., Paiva, R.P., and Henriques, J.: Heart murmur classification with feature selection. In: 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, pp. 4566–4569, 2010Google Scholar
- 18.Lin, J., Keogh, E., Lonardi, S., and Patel, P.: Finding motifs in time series. In: Proceedings of the 2nd Workshop on Temporal Data Mining, pp. 53–68, 2002Google Scholar
- 21.Malarvili, M.B., Kamarulafizam, I., Hussain, S., and Helmi, D.: Heart sound segmentation algorithm based on instantaneous energy of electrocardiogram. In: Computers in Cardiology, pp. 327–330, 2003Google Scholar
- 22.Mozaffarian, D., Benjamin, E.J., and Go Alan, S.: E.a.: Heart disease and stroke statistics–2016 update. Circulation, 2015Google Scholar
- 26.Rubin, J., Abreu, R., Ganguli, A., Nelaturi, S., Matei, I., and Sricharan, K.: Classifying heart sound recordings using deep convolutional neural networks and mel-frequency cepstral coefficients. In: Computing in Cardiology Conference (cinc), 2016, pp. 813–816. IEEE, 2016Google Scholar
- 28.Shi, W., Gong, Y., and Wang, J.: Improving cnn performance with min-max objective. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI’16, pp. 2004–2010, 2016Google Scholar
- 30.White, P.R., Collis, W.B., and Salmon, A.P.: Time-frequency analysis of heart murmurs in children. In: IEE Colloquium on Time-Frequency Analysis of Biomedical Signals (Digest No. 1997/006), pp. 3/1–3/4Google Scholar
- 31.Wu, J., Zhou, S., Wu, Z.M., and Wu, X.: Research on the method of characteristic extraction and classification of phonocardiogram. In: 2012 International Conference on Systems and Informatics, pp. 1732–1735, 2012.Google Scholar