Approaches for Respiratory Sound Analysis in Identification of Respiratory Diseases

Abstract

Purpose: Medical Professionals throughout the world prefer to use conventional stethoscope to listen to respiratory sounds. Listening to respiratory sounds through stethoscope is a subjective matter and proper diagnosis of the disease depends on skills and ability of the doctor. Computerized analysis of respiratory sounds can help doctors and researchers to characterize different abnormal respiratory patterns and make informed decision. Methods: This study includes previously reported work in different normal and abnormal respiratory sounds. Detailed characteristics of abnormal respiratory sounds are mentioned. In addition, Time-Amplitude characteristics of different respiratory sound plots are obtained using MATLAB and ICBHI Database. This study systematically discusses different approaches for respiratory sounds analysis like visual analysis of the time-amplitude signals, frequency analysis, spectral analysis using FFT, statistical analysis and, Machine Learning approach. List of relevant datasets are mentioned that can help researchers to do further analysis in this domain. Results: The careful observations and analysis shows the possibility of analyzing respiratory sounds by extracting suitable parameters and clinical applications for identification of diseases. Conclusion: Computer based respiratory sound analysis can help medical professionals in making informed decision this will help in early diagnosis and devise effective treatment plan for the patients.

Keywords

• Respiratory Sounds
• Adventitious Respiratory Sounds (ARS)
• Datasets
• Spectral Analysis
• Time Frequency Analysis
• Review.