A Review on Identifying Lung Disease Sounds using different ML and DL Models

Abstract

This comprehensive review explores the efficacy of various machine learning (ML) and deep learning (DL) models in identifying lung disease sounds, addressing the complex diagnostic challenges posed by the diverse acoustic patterns associated with lung diseases. ML algorithms like Support Vector Machines (SVM), Random Forests, and k-Nearest Neighbors (k-NN) offer robust classification frameworks, while DL architectures such as Convolutional Neural Networks (CNN) excel in extracting intricate audio patterns. By analyzing the performance metrics of these models, including accuracy, sensitivity, specificity, and area under the curve (AUC), the review aims to assess their comparative strengths and limitations in accurately identifying lung disease sounds. The insights gained from this review can significantly contribute to the development of more precise and effective diagnostic tools and interventions tailored to lung diseases, thus improving patient outcomes and healthcare efficiency in the realm of respiratory disorders.