Hackathon

Intro

Respiratory sounds are important indicators of respiratory health and respiratory disorders. The sound that comes out of a person’s breath is directly related to the movement of air, changes within the lung tissue and the area of secretion within the lungs. Snoring, for example, is a common sign that a patient has asthma such as asthma or chronic obstructive pulmonary disease (COPD).

Individuals are unaware of the importance of sleep breathing, that it can be tracked, and that it can be treated to improve health.

These sounds can be recorded using digital stethoscopes and other recording techniques. This digital data opens up the possibility of using machine learning to automatically diagnose respiratory disorders such as asthma, pneumonia and bronchiolitis, to name a few

Problem Statement

Build a model to classify respiratory diseases.
Build a model to detect if a recording contains crackles, wheezes or both.
Annotation is a time-consuming process. Create a model to automatically annotate respiratory sound recordings.
Deployment and other details will be provided during the event

Data Sharing:

It will be released in three parts;

Training
Validation
Test

Acknowledgements

Many thanks to the research teams at the University of Coimbra, Portugal; the University de Aveiro, Portugal and the Aristotle University of Thessaloniki, Greece for making this dataset publicly available & Kaggle. Due to all their effort we have opensource dataset to work upon