Pilot study on nocturnal monitoring of crackles in children with pneumonia

BackgroundThe clinical diagnosis of pneumonia is usually based on crackles at auscultation but it is not yet clear what kind of crackles are the characteristic features of pneumonia in children. Lung sound monitoring can be used as a “longtime stethoscope”. Therefore, it was the aim of this pilot study to use a lung sound monitor system to detect crackles and to differentiate between fine and coarse crackles in children with acute pneumonia. The change of crackles during the course of the disease shall be investigated in a follow-up study.Patients and methodsCrackles were recorded overnight from 22.00 to 06.00 h in 30 children with radiographically confirmed pneumonia. The data of a total of 28 800 recorded 30-second-epochs were audiovisually analysed for fine and coarse crackles.ResultsFine crackles and coarse crackles were recognised in every patient with pneumonia but the number of epochs with and without crackles varied widely among the different patients: Fine crackles were detected in 40% (mean, sd 22), coarse crackles in 76% (sd 20). The predominant localisation of crackles as recorded during overnight monitoring was in accordance with the radiographic infiltrates and the classical auscultation in most patients. The distribution of crackles was fairly equal throughout the night. However, there were time periods without any crackle in the single patients so that the diagnosis of pneumonia might be missed at sporadic auscultation.ConclusionNocturnal monitoring can be beneficial to reliably detect fine and coarse crackles in children with pneumonia.

Validation of the LEOSound Cough Detection Algorithm

Background Cough is an important respiratory symptom being of great interest to many researchers. Up to now, most knowledge about cough has been collected through standardized questionnaires. Objective, and reliable detection of cough assessed by automated lung sound monitoring are becoming increasingly important. The aim of this study is to validate the LEOSound lung sound monitor by using previously determined and investigated COPD datasets (1,2). Methods Based on multiple recordings of 48 patients with stable COPD II-IV, we validated the cough detection algorithm of LEOSound by using a contingency table. Sensitivity, specificity, positive and negative predictive values were used as quantitative measures. Results We found the overall accuracy to be 87.3% with sensitivity and specificity of 98.7% and 80.2%, respectively. Major reasons for midsections in descending order were throat cleaning, snoring and movement artifacts. Conclusion In comparison to other full-automated cough monitoring systems, the LEOSound performs the best in sensitivity, but shows slightly poor specificity. Misdetections were mainly caused due to morphological similar noises and can be withdrawn while scanning through the recording manually.