Annals of Biomedical Engineering

, Volume 41, Issue 11, pp 2448–2462

Cough Sound Analysis Can Rapidly Diagnose Childhood Pneumonia

  • Udantha R. Abeyratne
  • Vinayak Swarnkar
  • Amalia Setyati
  • Rina Triasih
Article

Abstract

Pneumonia annually kills over 1,800,000 children throughout the world. The vast majority of these deaths occur in resource poor regions such as the sub-Saharan Africa and remote Asia. Prompt diagnosis and proper treatment are essential to prevent these unnecessary deaths. The reliable diagnosis of childhood pneumonia in remote regions is fraught with difficulties arising from the lack of field-deployable imaging and laboratory facilities as well as the scarcity of trained community healthcare workers. In this paper, we present a pioneering class of technology addressing both of these problems. Our approach is centred on the automated analysis of cough and respiratory sounds, collected via microphones that do not require physical contact with subjects. Cough is a cardinal symptom of pneumonia but the current clinical routines used in remote settings do not make use of coughs beyond noting its existence as a screening-in criterion. We hypothesized that cough carries vital information to diagnose pneumonia, and developed mathematical features and a pattern classifier system suited for the task. We collected cough sounds from 91 patients suspected of acute respiratory illness such as pneumonia, bronchiolitis and asthma. Non-contact microphones kept by the patient’s bedside were used for data acquisition. We extracted features such as non-Gaussianity and Mel Cepstra from cough sounds and used them to train a Logistic Regression classifier. We used the clinical diagnosis provided by the paediatric respiratory clinician as the gold standard to train and validate our classifier. The methods proposed in this paper could separate pneumonia from other diseases at a sensitivity and specificity of 94 and 75% respectively, based on parameters extracted from cough sounds alone. The inclusion of other simple measurements such as the presence of fever further increased the performance. These results show that cough sounds indeed carry critical information on the lower respiratory tract, and can be used to diagnose pneumonia. The performance of our method is far superior to those of existing WHO clinical algorithms for resource-poor regions. To the best of our knowledge, this is the first attempt in the world to diagnose pneumonia in humans using cough sound analysis. Our method has the potential to revolutionize the management of childhood pneumonia in remote regions of the world.

Keywords

Pneumonia Childhood cough Automated cough analysis 

References

  1. 1.
    Abaza, A. A., J. B. Day, J. S. Reynolds, A. M. Mahmoud, W. T. Goldsmith, W. G. McKinney, E. L. Petsonk, and D. G. Frazer. Classification of voluntary cough sound and airflow patterns for detecting abnormal pulmonary function. Cough 5:8, 2009.PubMedCrossRefGoogle Scholar
  2. 2.
    Abeyratne, U. Blind Reconstruction of Non-minimum-phase Systems from 1-D Oblique Slices of Bispectrum. IET, 1999. Google Scholar
  3. 3.
    Bhutta, Z. A. Childhood pneumonia in developing countries: refinement of clinical algorithms is a priority. BMJ 333:612, 2006.PubMedCrossRefGoogle Scholar
  4. 4.
    Cardoso, M. R. A., C. M. Nascimento-Carvalho, F. Ferrero, F. M. Alves, and S. N. Cousens. Adding fever to WHO criteria for diagnosing pneumonia enhances the ability to identify pneumonia cases among wheezing children. Arch. Dis. Child. 96:58, 2011.PubMedCrossRefGoogle Scholar
  5. 5.
    Falade, A., H. Tschäppeler, B. M. Greenwood, and E. K. Mulholland. Use of simple clinical signs to predict pneumonia in young Gambian children: the influence of malnutrition. Bull. World Health Organ. 73:299, 1995.PubMedGoogle Scholar
  6. 6.
    Frosh, A. Pediatric airway: cry, stridor, and cough. JAMA 301:2392–2392 (2009).Google Scholar
  7. 7.
    Gold, B., N. Morgan, and D. Ellis. Speech and Audio Signal Processing: Processing and Perception of Speech and Music. Wiley-Interscience, 2011.Google Scholar
  8. 8.
    Harari, M., V. Spooner, S. Meisner, M. Carney, F. Shann, and J. De Campo. Clinical signs of pneumonia in children. Lancet 338:928–930, 1991.PubMedCrossRefGoogle Scholar
  9. 9.
    Hirschberg, J., I. Lelli, and Z. Garay. The Pediatric Airway: Cry, Stridor, and Cough. Plural Pub., 2009.Google Scholar
  10. 10.
    IMCI Integrated Management of Childhood Illness. World Health Organization, 2005.Google Scholar
  11. 11.
    Knocikova, J., J. Korpas, M. Vrabec, and M. Javorka. Wavelet analysis of voluntary cough sounds in patients with respiratory diseases. J. Physiol. Pharmacol. 59:331–340, 2008.PubMedGoogle Scholar
  12. 12.
    Kosasih, K., U. Abeyratne, and V. Swarnkar. High frequency analysis of cough sounds in pediatric patients with respiratory diseases. In: Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE. 2012. IEEE.Google Scholar
  13. 13.
    Lozano, J., M. Steinhoff, J. Ruiz, M. Mesa, N. Martinez, and B. Dussan. Clinical predictors of acute radiological pneumonia and hypoxaemia at high altitude. Arch. Dis. Child. 71:323–327, 1994.PubMedCrossRefGoogle Scholar
  14. 14.
    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
  15. 15.
    Mulholland, E., E. Simoes, M. Costales, E. McGrath, E. Manalac, and S. Gove. Standardized diagnosis of pneumonia in developing countries. Pediatr. Infect. Dis. J. 11:77, 1992.PubMedCrossRefGoogle Scholar
  16. 16.
    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
  17. 17.
    Oppenheim, A. V., R. W. Schafer, and J. R. Buck. Discrete-Time Signal Processing. Vol. 1999. Englewood Cliffs, NJ: Prentice Hall, 1989.Google Scholar
  18. 18.
    Palafox, M., H. Guiscafré, H. Reyes, O. Muñoz, and H. Martínez. Diagnostic value of tachypnoea in pneumonia defined radiologically. Arch. Dis. Child. 82:41–45, 2000.PubMedCrossRefGoogle Scholar
  19. 19.
    Piirilä, P., and A. Sovijärvi. Differences in acoustic and dynamic characteristics of spontaneous cough in pulmonary diseases. Chest 96:46–53, 1989.PubMedCrossRefGoogle Scholar
  20. 20.
    Pneumonia Strategy Overview. Bill & Melinda Gates Foundation (November 2009).Google Scholar
  21. 21.
    Smith, J. A., J. E. Earis, and A. A. Woodcock. Establishing a gold standard for manual cough counting: video versus digital audio recordings. Cough 2:6, 2006.PubMedCrossRefGoogle Scholar
  22. 22.
    Suttorp, N., T. Welte, and R. Marre. Community-Acquired Pneumonia. Springer, 2007.Google Scholar
  23. 23.
    Swarnkar, V., U. Abeyratne, A. Chang, Y. Amrulloh, A. Setyati, and R. Triasih. Automatic identification of wet and dry cough in pediatric patients with respiratory diseases. Ann. Biomed. Eng. 41, 2013. doi:10.1007/s10439-013-0741-6.
  24. 24.
    Wardlaw, T., E. W. Johansson, and M. Hodge. Pneumonia: The Forgotten Killer of Children. UNICEF/WHO, 2006.Google 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. 2001. IEEE.Google Scholar
  26. 26.
    WHO/UNICEF. Global Action Plan for the Prevention and Control of Pneumonia (GAPP). WHO Reference Number: WHO/FCH/CAH/NCH/09.04, 23 (2009).Google Scholar

Copyright information

© Biomedical Engineering Society 2013

Authors and Affiliations

  • Udantha R. Abeyratne
    • 1
  • Vinayak Swarnkar
    • 1
  • Amalia Setyati
    • 2
  • Rina Triasih
    • 2
  1. 1.School of Information Technology and Electrical EngineeringThe University of QueenslandBrisbaneAustralia
  2. 2.Respiratory Medicine Unit, Sardjito HospitalGadjah Mada UniversityYogyakartaIndonesia

Personalised recommendations