India houses nearly 100 million people who suffer from various respiratory problems of the global 1–1.2 billion. Lack of cost-effective and lab-free methods for early diagnosis may be the prime reason behind this. Spirometry remains the standard clinical test procedure for its detection of respiratory problems, but its limitations affect its optimum use.

Numerous relevant pieces of information about respiratory condition and etiology can be ruled out through the Cough sounds. Establishing a relationship between cough pattern and respiratory conditions with widened airway, narrowed airway, fluid-filled air sacs, and stiff lungs may help correct management of the condition. Rudraraju G. et al carried out a study to establish the same.

They provided a summarized chart for the Respiratory disease pattern and their corresponding conditions.

They summarized cough analysis and relation to lung conditions of different disorders as follows-

Through their study, they showed a strong correlation of coughing sound characteristics with airflow characteristics including FEV1, FVC and their ratios, which are important in identifying the type of lung diseases as either obstructive (obstruction in the airway) or restrictive (restricts lung expansion). They also invented a machine learning model to predict obstructive versus restrictive pattern and validated it using K-fold cross-validation based on ground truth data, with an accuracy of 91.97%, the sensitivity of 87.2%, and specificity of 93.69%.

Source: Rudraraju G, Palreddy SD, Mamidgi B, Sripada NR, Sai YP, Vodnala NK, Haranath SP. Cough sound analysis and objective correlation with spirometry and clinical diagnosis, Informatics in Medicine Unlocked, 2020;19:100319, https://doi.org/10.1016/j.imu.2020.100319.