Fully Automated Identification of Heart Sounds for the Analysis of Cardiovascular Pathology
Cardiac disorders are spreading rapidly all over the world, and as per the World Health Organization (WHO), 17.5 million people die each year due to cardiovascular diseases (CVD). So there is a dire need to develop cost-effective, time-efficient, and fully automated solutions to diagnose cardiovascular abnormalities. Many researchers have worked on detecting CVD from electrocardiogram (ECG) signals. ECG signals give reliable information about cardiac pathology; however phonocardiogram (PCG) signal provides an easy, cost-effective, objective, and comprehensive information about cardiovascular abnormalities by measuring heartbeats. This paper presents a fully automated robust clinical decision support system that can identify cardiovascular pathology by analyzing heart sounds from PCG signals. The proposed system was tested on 55 PCG signals from which 24 samples contained healthy and 31 samples contained abnormal heart sounds. The proposed system correctly classified healthy and diseased samples with the accuracy, sensitivity, and negative predictive value (NPV) of 87.2%, 96.7%, and 94.7%, respectively.
KeywordsPhonocardiogram (PCG) Savitzky-Golay filter K-nearest neighbors (KNN) Naïve Bayes Support vector machines (SVM)
We are very thankful to PASCAL team for providing an online database of annotated PCG signals.
- 1.WHO Eastern Mediterranean Region, Cardiovascular Diseases, World Health Organization. Retrieved from http://www.who.int/mediacentre/factsheets/fs317/en/ in September 2016.
- 2.CDC 24–7 Organization, Heart Disease Fact Sheet, Centers for Disease Control and Prevention. https://www.cdc.gov/dhdsp/data_statistics/fact_sheets/fs_heart_disease.htm in September 2016.
- 3.United Health Foundation, Public Health Impact: Heart Disease, Americans Health Organization. http://www.americashealthrankings.org/explore/2015-annual-report/measure/CHD/state/ALL in September 2016.
- 5.Bassiouni, M., Khalifa, W., El Dahshan, E. S. A., & Salam, A. B. M. (2015). A study on PCG as a biometric approach, 2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS), Cairo, pp. 161–166.Google Scholar
- 6.Agrawal, K., Jha, A. K., Sharma, S., Kumar, A., & Chourasia, V. S. (2013) Wavelet subband dependent thresholding for denoising of phonocardiographic signals, 2013 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), Poznan, pp. 158–162.Google Scholar
- 7.Shankar, N., & Sangeetha, M.S. (2013). Analysis of Phonocardiogram for detection of cardiac murmurs using wavelet transform. 2013 International Journal of Advanced Scientific and Technical Research, pp. 350–357.Google Scholar
- 8.Bhogawar, S. (2014) Cardiac sound analyzer and monitor, 2014 International Journal of Research in Engineering and Applied Sciences (IJREAS).Google Scholar
- 9.Sankar, D. S. V., & ARoy, L. P. (2014). Principal component analysis (PCA) approach to segment primary components from pathological phonocardiogram, 2014 International Conference on Communication and Signal Processing, Melmaruvathur, pp. 910–914.Google Scholar
- 10.Vernekar, S., Nair, S., Vijaysenan, D., & Ranjan, R. (2016). A novel approach for classification of normal/ abnormal phonocardiogram recordings using temporal signal analysis and machine learning, 2016 Computing in Cardiology Conference (CinC), Vancouver, BC, pp. 1141–1144.Google Scholar
- 11.Springer, D. B., Tarassenko, L., & Clifford, G. D. (2014). Support vector machine hidden semi-Markov model-based heart sound segmentation, Computing in Cardiology 2014, Cambridge, MA, pp. 625–628.Google Scholar
- 12.Pedrosa, J., Castro, A., & Vinhoza, T. T. V. (2014). Automatic heart sound segmentation and murmur detection in pediatric phonocardiograms, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL, pp. 2294–2297.Google Scholar
- 13.Langley, P., & Murray, A. (2016). Abnormal heart sounds detected from short duration unsegmented phonocardiograms by wavelet entropy, 2016 Computing in Cardiology Conference (CinC), Vancouver, BC, pp. 545–548.Google Scholar
- 14.Suhas, K., Kumar, R. H., Nayak, S. H., & Krupa, B. N. (2016). A hybrid model for recognizing cardiac murmurs from phonocardiogram signal, 2016 IEEE Annual India Conference (INDICON), Bangalore, pp. 1–6.Google Scholar
- 15.Yazdani, S., Schlatter, S., Atyabi, S. A., & Vesin, J. M. (2016). Identification of Abnormal Heart Sounds, 2016 Computing in Cardiology, pp. 1157–1160.Google Scholar
- 16.Springer, D. B., Brennan, T., Ntusi, N., Abdelrahman, H. Y., Zuhlke, L. J., Mayosi, B. M., Tarassenko, L., & Clifford, G. D. (2016). Automated signal quality assessment of mobile phone-recorded heart sound signals. Journal of Medical Engineering and Technology, 40(7–8), 342–355.CrossRefGoogle Scholar
- 17.Bentley, P., Nordehn, G., Coimbra, M., Mannor, S., & Getz, R. Classifying Heart Sounds Challenge, Sponsored by PASCAL. Retrieved from: http://www.peterjbentley.com/heartchallenge/ in September 2016.
- 18.Fan, R. E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., & Lin, C.-J. (2008). LIBLINEAR: A library for large linear classification. Journal of Machine Learning Research, 9.Google Scholar