Review of Acoustic Features and Computational Models in Lung Disease Diagnosis

Abstract

Respiratory diseases are increasingly prevalent, necessitating efficient diagnostic methods for healthcare providers to manage patient care effectively. This review addresses the growing need for non-invasive, cost-effective diagnostic techniques focused on acoustic properties of lung sounds. The primary objective is to explore contemporary methodologies and models used in the acoustic analysis of lung sounds for disease identification and characterization. The review examines and contrasts current signal processing techniques and machine learning algorithms applied to lung sound analysis, highlighting their strengths and limitations. By evaluating these methods, the review aims to identify promising applications for clinical settings and provide insights into how these technologies can be optimized. Additionally, the review offers recommendations for future research and practical applications of lung sound analysis to enhance differential diagnosis and prognosis of respiratory disorders. This work aims to contribute to the development of advanced, accessible diagnostic tools that can improve patient outcomes and streamline respiratory disease management.

Topics & Concepts