Classification of pulmonary pathology from breath sounds using the wavelet packet transform and an extreme learning machine.

BACKGROUND: Auscultation is a medical procedure used for the initial diagnosis and assessment of lung and heart diseases. From this perspective, we propose assessing the performance of the extreme learning machine (ELM) classifiers for the diagnosis of pulmonary pathology using breath sounds. METHODS: Energy and entropy features were extracted from the breath sound using the wavelet packet transform. The statistical significance of the extracted features was evaluated by one-way analysis of variance (ANOVA). The extracted features were inputted into the ELM classifier. RESULTS: The maximum classification accuracies obtained for the conventional validation (CV) of the energy and entropy features were 97.36% and 98.37%, respectively, whereas the accuracies obtained for the cross validation (CRV) of the energy and entropy features were 96.80% and 97.91%, respectively. In addition, maximum classification accuracies of 98.25% and 99.25% were obtained for the CV and CRV of the ensemble features, respectively. CONCLUSION: The results indicate that the classification accuracy obtained with the ensemble features was higher than those obtained with the energy and entropy features.

A novel approach to detect respiratory phases from pulmonary acoustic signals using normalised power spectral density and fuzzy inference system.

BACKGROUND: Monitoring respiration is important in several medical applications. One such application is respiratory rate monitoring in patients with sleep apnoea. The respiratory rate in patients with sleep apnoea disorder is irregular compared with the controls. Respiratory phase detection is required for a proper monitoring of respiration in patients with sleep apnoea. AIMS: To develop a model to detect the respiratory phases present in the pulmonary acoustic signals and to evaluate the performance of the model in detecting the respiratory phases. METHODS: Normalised averaged power spectral density for each frame and change in normalised averaged power spectral density between the adjacent frames were fuzzified and fuzzy rules were formulated. The fuzzy inference system (FIS) was developed with both Mamdani and Sugeno methods. To evaluate the performance of both Mamdani and Sugeno methods, correlation coefficient and root mean square error (RMSE) were calculated. RESULTS: In the correlation coefficient analysis in evaluating the fuzzy model using Mamdani and Sugeno method, the strength of the correlation was found to be r = 0.9892 and r = 0.9964, respectively. The RMSE for Mamdani and Sugeno methods are RMSE = 0.0853 and RMSE = 0.0817, respectively. CONCLUSION: The correlation coefficient and the RMSE of the proposed fuzzy models in detecting the respiratory phases reveals that Sugeno method performs better compared with the Mamdani method.

Prevalence of chronic obstructive pulmonary disease and its association with tobacco smoking and environmental tobacco smoke exposure among rural population.

A field survey was conducted for chronic obstructive pulmonary disease (COPD) epidemiology in the rural field practice area of Kempegowda Institute of Medical Sciences, Bangalore, India, which covers a population of 44,387 to find out the prevalence of COPD in adult subjects of 35 years and above using cluster sampling technique and to determine the association of tobacco smoking, environmental tobacco smoking (ETS) exposure and type of cooking fuel used with COPD. The overall prevalence of COPD was 4.36%. The prevalence among males and females were 5.32% and 3.41% respectively. The prevalence was found to be increasing with an increase in age. The tobacco smoke and exposure to ETS was significantly associated with higher odds of COPD with adjusted odds ratio 2.97 and 2.67 respectively. Thus, there was a significant association between tobacco smoking and ETS exposure with COPD.

Prevalence of bronchial asthma and its association with smoking habits among adult population in rural area.

A cross-sectional study was conducted in the rural field practice area of Kempegowda Institute of Medical Sciences, Bangalore. A total of 3194 adult individuals (18-70 years) were selected from 30 villages (clusters) using a cluster-sampling technique. Individuals with symptoms suggestive of asthma were subjected for clinical examination for the diagnosis of asthma. Among the 3194 respondents, 1518 (47.5%) were males and 1676 (52.5%) were females. The prevalence of bronchial asthma was 2.88%. The prevalence of asthma was higher among those reporting a history of current smoking. Among current smokers, the number of cigarettes/bidis/hookah smoked daily did not differ (P > 0.05) between individuals without asthma and with asthma, whereas the mean number of years of smoking did differ (P < 0.001). There was significant association between tobacco smoking and bronchial asthma.