A Comprehensive Respiratory Evaluation: Incorporating Lung Sound and Disease Classification Along with Spirometry Assessment

Respiratory disease, also known as pulmonary disease or lung disease mainly affects the airways and hinders important functions of the lungs (NCI Dictionary of Cancer Terms). Lung sounds are acoustic signals generated during breathing, commonly referred to as breath noises or respiratory sounds. They can offer insightful information about the condition of a patient's lungs. Wheezing, crackles, or other abnormal lung noises can be a sign of underlying respiratory problems. On the other hand, procedures like Spirometry analyze the volume and flow of air as a person breathes in and out to determine lung function. In this paper, we conducted a comparative analysis of five models for lung disease and four models for lung sound classification using the respiratory sound database. In the case of lung disease classification, the models we used included SVM with MFCC, CNN with MFCC and Linked features, Decision tree, and LSTM/GRU. Among these, CNN with linked features achieved the highest accuracy, reaching 95%. On the other hand, for lung sound classification, we employed SVM with MFCC, CNN, Stacked Denoising Autoencoder with CNN, and Deit base+Att+CNN. In this context, SVM with MFCC emerged as the best-performing model with an accuracy of 74.06%, delivering the highest accuracy across the board. Additionally, we explored how incorporating the GLI-2012 equations for Spirometry calculations can enhance the accuracy of lung disease diagnosis.