Respiratory Sound Analysis for Detection of Pulmonary Diseases

Large number of people die every year of Pulmonary chronic lung diseases irrespective of their age. Lung sound analysis has been a key diagnostic aid to accurately detect Pulmonary Diseases. Earlier, manual detection was used which was not a dependable method to detect lung diseases due to various reasons like low audibility and difference in perceptions of different physicians for different sounds. Modern computerized analysis yield results with much higher accuracy and thus a better treatment can be given to patients suffering from various kinds of lung diseases. These disorders include Asthma, Bronchitis, Emphysema, Tuberculosis and Pneumonia. Some of the symptoms are wheezing, shortness of breath, rhonchi and chronic cough. In general, the analysis is carried out in two stages- Separation of Heart Sound (HS) from the Lung Sound (LS) and the characterization of waveform of the filtered LS. In this paper, we propose a very simple yet effective method for the second stage analysis- characterization of waveform of the filtered LS for some of the male and female age groups. We have taken the filtered Lung sounds from different online repositories and performed Welch method. This method helps to obtain power spectrum plot of a particular LS. Different diseases have peaks in different frequency ranges of the power spectrum plot. This helps in identification of a particular disease.