Annals of Biomedical Engineering

, Volume 41, Issue 5, pp 1016–1028 | Cite as

Automatic Identification of Wet and Dry Cough in Pediatric Patients with Respiratory Diseases

  • Vinayak Swarnkar
  • Udantha R. Abeyratne
  • Anne B. Chang
  • Yusuf A. Amrulloh
  • Amalia Setyati
  • Rina Triasih


Cough is the most common symptom of several respiratory diseases. It is a defense mechanism of the body to clear the respiratory tract from foreign materials inhaled accidentally or produced internally by infections. The identification of wet and dry cough is an important clinical finding, aiding in the differential diagnosis especially in children. Wet coughs are more likely to be associated with lower respiratory track bacterial infections. At present during a typical consultation session, the wet/dry decision is based on the subjective judgment of a physician. It is not available for the non-trained person, long term monitoring or in the assessment of treatment efficacy. In this paper we address these issues and develop an automated technology to classify cough into ‘wet’ and ‘dry’ categories. We propose novel features and a Logistic regression model (LRM) for the classification of coughs into wet/dry classes. The performance of the method was evaluated on a clinical database of pediatric coughs (C = 536) recorded using a bed-side non-contact microphone from N = 78 patients. Results of the automatic classification were compared against two expert human scorers. The sensitivity and specificity of the LRM in picking wet coughs were between 87 and 88% with 95% confidence interval on training/validation dataset (310 cough events from 60 patients) and 84 and 76% respectively on prospective dataset (117 cough events from 18 patients). The kappa agreement with two expert human scorers on prospective dataset was 0.51. These results indicate the potential of the method as a useful clinical tool for cough monitoring, especially at home settings.


Childhood cough Cough quality Dry and wet cough Automated cough assessment Pneumonia 


  1. 1.
    Abeyratne, U. R. Blind reconstruction of non-minimum-phase systems from 1-D oblique slices of bispectrum. In: IEE Proceedings of Vision, Image and Signal Processing. IET, 1999.Google Scholar
  2. 2.
    Chang, A. B. Pediatric cough: children are not miniature adults. Lung 188:33–40, 2010.CrossRefGoogle Scholar
  3. 3.
    Chang, A. B., J. T. Gaffney, M. M. Eastburn, J. Faoagali, N. C. Cox, and I. B. Masters. Cough quality in children: a comparison of subjective versus bronchoscopic findings. Respir. Res. 6, 2005.Google Scholar
  4. 4.
    Chang, A., G. Redding, and M. Everard. Chronic wet cough: protracted bronchitis, chronic suppurative lung disease and bronchiectasis. Pediatr. Pulmonol. 43:519–531, 2008.PubMedCrossRefGoogle Scholar
  5. 5.
    Chatrzarrin, H., A. Arcelus, R. Goubran, and F. Knoefel. Feature extraction for the differentiation of dry and wet cough sounds. In: IEEE International Workshop on Medical Measurements and Applications Proceedings (MeMeA), IEEE, 2011, pp. 162–166.Google Scholar
  6. 6.
    Chung, K. F., and I. D. Pavord. Prevalence, pathogenesis, and causes of chronic cough. Lancet 371:1364–1374, 2008.PubMedCrossRefGoogle Scholar
  7. 7.
    Ghaemmaghami, H., U. Abeyratne, and C. Hukins. Normal probability testing of snore signals for diagnosis of obstructive sleep apnea. In: Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE, IEEE, 2009.Google Scholar
  8. 8.
    Hartigan, J. A., and M. A. Wong. Algorithm AS 136: a k-means clustering algorithm. Appl. Stat. 100–108, 1979.Google Scholar
  9. 9.
    Ishikawa, S., R. Kasparian, J. Blanco, D. Sotherland, R. Clubb, L. Kenny, J. Workowicz, and K. MacDonell. Observer variability in interpretation of voluntary cough of ‘bronchitics’ and ‘asthmatics’. In: ILSA Proceedings Paris, vol. 10, 1987.Google Scholar
  10. 10.
    Korpá, J., J. Sadloová, and M. Vrabec. Analysis of the cough sound: an overview. Pulm. Pharmacol. 9:261–268, 1996.CrossRefGoogle Scholar
  11. 11.
    Lee, T., U. Abeyratne, K. Puvanendran, and K. Goh. Formant-structure and phase-coupling analysis of human snoring sounds for detection of obstructive sleep apnea. Comput. Methods Biomech. Biomed. Eng. 3, 2000.Google Scholar
  12. 12.
    Logan, B. Mel frequency cepstral coefficients for music modeling. In: International Symposium on Music Information Retrieval, 2000.Google Scholar
  13. 13.
    Mendel, J. M. Tutorial on higher-order statistics (spectra) in signal processing and system theory: theoretical results and some applications. Proc. IEEE 79:278–305, 1991.CrossRefGoogle Scholar
  14. 14.
    Murata, A., Y. Taniguchi, Y. Hashimoto, K. Y., Y. Takasaki, and S. Kudoh. Discrimination of productive and non-productive cough by sound analysis. Intern. Med. 37:732–735, 1998.Google Scholar
  15. 15.
    Ng, A. K., T. S. Koh, E. Baey, T. H. Lee, U. R. Abeyratne, and K. Puvanendran. Could formant frequencies of snore signals be an alternative means for the diagnosis of obstructive sleep apnea? Sleep Med. 9:894–898, 2008.PubMedCrossRefGoogle Scholar
  16. 16.
    Oppenheim, A. V., R. W. Schafer, and J. R. Buck. Discrete-Time Signal Processing, Vol. 1999. Englewood Cliffs, NJ: Prentice hall, 1989.Google Scholar
  17. 17.
    Piirilä, P., and A. Sovijärvi. Differences in acoustic and dynamic characteristics of spontaneous cough in pulmonary diseases. Chest 96:46–53, 1989.PubMedCrossRefGoogle Scholar
  18. 18.
    Quatieri, T. F. Discrete-Time Speech Signal Processing: Principles and Practice. Pearson Education India, 2002.Google Scholar
  19. 19.
    Smith, J. A., H. L. Ashurst, S. Jack, A. A. Woodcock, and J. E. Earis. The description of cough sounds by healthcare professionals. Cough 2:1, 2006.PubMedCrossRefGoogle Scholar
  20. 20.
    Sondhi, M. New methods of pitch extraction. IEEE Trans. Audio Electroacoust. 16:262–266, 1968.CrossRefGoogle Scholar
  21. 21.
    Soto Quiros, M. E., M. Soto Martinez, and L. Å. Hanson. Epidemiological studies of the very high prevalence of asthma and related symptoms among school children in Costa Rica from 1989 to 1998. Pediatr. Allergy immunol. 13:342–349, 2002.Google Scholar
  22. 22.
    Spengler, J. D., J. J. K. Jaakkola, H. Parise, B. A. Katsnelson, L. I. Privalova, and A. A. Kosheleva. Housing characteristics and children’s respiratory health in the Russian Federation. J. Inf. 94, 2004.Google Scholar
  23. 23.
    The Global Burden of Disease 2004 Update. World Health Organization, 2008.Google Scholar
  24. 24.
    Thorpe, C., L. Toop, and K. Dawson. Towards a quantitative description of asthmatic cough sounds. Eur. Respir. J. 5:685–692, 1992.PubMedGoogle Scholar
  25. 25.
    Thorpe, W., M. Kurver, G. King, and C. Salome. Acoustic analysis of cough. In: Intelligent Information Systems Conference, the Seventh Australian and New Zealand 2001, IEEE, 2001.Google Scholar
  26. 26.
    Zgherea, D., S. Pagala, M. Mendiratta, M. G. Marcus, S. P. Shelov, and M. Kazachkov. Bronchoscopic findings in children with chronic wet cough. Pediatrics 129:e364–e369, 2012.PubMedCrossRefGoogle Scholar
  27. 27.
    Zheng, F., G. Zhang, and Z. Song. Comparison of different implementations of MFCC. J. Comput. Sci. Technol. 16:582–589, 2001.CrossRefGoogle Scholar

Copyright information

© Biomedical Engineering Society 2013

Authors and Affiliations

  • Vinayak Swarnkar
    • 1
  • Udantha R. Abeyratne
    • 1
  • Anne B. Chang
    • 2
  • Yusuf A. Amrulloh
    • 1
  • Amalia Setyati
    • 3
  • Rina Triasih
    • 3
  1. 1.School of Information Technology and Electrical EngineeringThe University of QueenslandSt Lucia Campus, BrisbaneAustralia
  2. 2.Queensland Children’s Respiratory Centre, QLD, Children’s Medical Research InstituteRoyal Children’s HospitalBrisbaneAustralia
  3. 3.Respiratory Medicine Unit, Sardjito HospitalGadjah Mada UniversityYogyakartaIndonesia

Personalised recommendations