Attention-guided feature importance-powered chronic obstructive pulmonary disease screening using lung sounds
Abstract
Chronic obstructive pulmonary disease (COPD) leads to progressive airflow obstruction, impairing respiratory function. In this study, a deep-learning framework is developed in order to analyze lung sounds (LS) and to support COPD screening through an explainable approach. In the proposed methodology, the LS signals are transformed into spectrograms, highlighting crucial acoustic features. Convolutional neural networks (CNNs) and vision transformers (ViTs) models are introduced to extract diverse features, enhancing feature representation. Subsequently, an attention-guided feature importance (AGFI) is employed to refine the features. An ensemble architecture leveraging TabNet and Support Vector Machine (SVM) with radial basis function (RBF) as base learners and Neural Oblivious Decision Ensembles (NODE) as a meta learner, is proposed to classify the features into COPD and normal classes. Experimental outcomes validated on internal and external datasets demonstrate the model’s exceptional classification performance. The proposed model achieves outstanding generalization performance on the external dataset with an accuracy of 96.31% and an F1-score of 96.55%, outperforming the traditional ensemble methods. Through the innovative artificial intelligence-powered COPD screening approach, the shortcomings of conventional screening approaches are addressed. The feature extraction architecture and ensemble classification enable the proposed model to offer a scalable, explainable, and clinically reliable solution for diverse healthcare environments.