Medical Diagnosis of Ailments Through Supervised Learning Techniques on Sounds of the Heart and Lungs

  • Shantanu PatilEmail author
  • Abha Saxena
  • Tarun Talreja
  • Vidushi Bhatti
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 898)


Auscultation is a medical technique to decipher ailments of human body through careful observation of heart and lung sounds. This project is a sincere effort to develop a low-cost stethoscope solution which can record and store the internal body sounds of patients’ heart and lungs which will assist physicians in taking careful observations and tagging illnesses to the sounds, and training a machine learning model on recorded and tagged sounds to autosuggest the illness. There exist much matured medical diagnostic solutions in the country, but all of these solutions require a specific amount of time as well as incur a great cost to the patient. Machine learning in computation has evolved as a key driving force in the industry nowadays serving in a range of applications. Hence, we have extensively used various classifiers to train and test the audio data of patients and generate a viable diagnostic output which will serve as a primary guide to a medical practitioner. We hope this project serves its cause and has an impact on society through proper channelization of resources.


Telemedicine Auscultation Supervised learning Sound classification 



We declare that we have taken the required permissions for use of patients’ involvement in the study and taken responsibility if any issues arise later.


  1. 1.
    Thinklabs One Digital Stethoscope.
  2. 2.
    Wu, M., Der-Khachadourian, G.: Digital Stethoscope—A Portable, Electronic Auscultation Device. Cornell University (2012)Google Scholar
  3. 3.
    Leng, S., Tan, R., Chai, K., Wang, C., Ghista, D., Zhong, L.: The electronic stethoscope. Biomed. Eng. Online (2015)Google Scholar
  4. 4.
    Moriarty, M.: Heart and breath sounds: listening with skill. RN, BSN, Modern Medicine Network online (May 01, 2002)Google Scholar
  5. 5.
    PhysioNet/CinC Challenge 2016: Training Sets.
  6. 6.
    Lippmann, R.P.: An introduction to computing with neural nets. In: IEEE ASSP Magazine, pp. 4–22 (1987)CrossRefGoogle Scholar
  7. 7.
    Salamon, J., Bello, J.: Deep convolutional neural networks and data augmentation for environmental sound classification. In: IEEE Signal Processing Letters (Accepted November 2016)Google Scholar
  8. 8.
    Geurts, P., Ernst, D., Wehenkel, L.: Extremely Randomized Trees. Springer (2 March 2006)Google Scholar
  9. 9.
    Fernando, C.: Mobile diagnostics for rural patients in Columbia. Telemed. E-Health 23(11), 934–937 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Shantanu Patil
    • 1
    Email author
  • Abha Saxena
    • 1
  • Tarun Talreja
    • 1
  • Vidushi Bhatti
    • 1
  1. 1.National Institute of Technology DelhiNew DelhiIndia

Personalised recommendations