Spirometry parameter prediction using Acoustic characteristics of Cough

Spirometry evaluates lung function by measuring airflow post-maximal inspiration, using parameters like FEV1, FVC, and the FEV1/FVC ratio for respiratory disease classification and severity monitoring. Cough, by inducing intrathoracic pressure changes, reflects respiratory pathology, impacting airflow velocities and cough sound properties. A correlation exists between spirometry values representing air flow-volume properties and acoustic features of cough sounds. The present study explores the correlation between cough sounds and spirometry values (FEV1, FVC, and FEV1/FVC ratio) for assessing respiratory health. Utilizing machine learning models, trained on cough sound data labelled with corresponding spirometry pathologies, the research demonstrates, ability of swaasa in predicting spirometry values. The regression algorithm for predicting spirometry parameters, yields optimal results with FEV1/FVC prediction showing 70.47% accuracy, 77.37% sensitivity, and 68.54% specificity. FVC prediction demonstrates 66.04% accuracy, 87% sensitivity, and 48.38% specificity. The study underscores the potential of AI-based cough sound analysis for detecting respiratory abnormalities, offering a promising avenue for diagnosis in resource-limited settings.