The reliability of lung crackle characteristics in cystic fibrosis and bronchiectasis patients in a clinical setting

Reliability and Validity of Computerized Adventitious Respiratory Sounds in People with Bronchiectasis

Background: Computerized adventitious respiratory sounds (ARS), such as crackles and wheezes, have been poorly explored in bronchiectasis, especially their measurement properties. This study aimed to test the reliability and validity of ARS in bronchiectasis. Methods: Respiratory sounds were recorded twice at 4 chest locations on 2 assessment sessions (7 days apart) in people with bronchiectasis and daily sputum expectoration. The total number of crackles, number of wheezes and wheeze occupation rate (%) were the parameters extracted. Results: 28 participants (9 men; 62 ± 12 y) were included. Total number of crackles and wheezes showed moderate within-day (ICC 0.87, 95% CI 0.74−0.94; ICC 0.86, 95% CI 0.71−0.93) and between-day reliability (ICC 0.70, 95% CI 0.43−0.86; ICC 0.78, 95% CI 0.56−0.90) considering all chest locations and both respiratory phases; wheeze occupation rate showed moderate within-day reliability (ICC 0.86, 95% CI 0.71−0.93), but poor between-day reliability (ICC 0.71, 95% CI 0.33−0.87). Bland−Altman plots revealed no systematic bias, but wide limits of agreement, particularly in the between-days analysis. All ARS parameters correlated moderately with the amount of daily sputum expectoration (r > 0.4; p < 0.05). No other significant correlations were observed. Conclusion: ARS presented moderate reliability and were correlated with the daily sputum expectoration in bronchiectasis. The use of sequential measurements may be an option to achieve greater accuracy when ARS are used to monitor or assess the effects of physiotherapy interventions in this population.

LungAttn: advanced lung sound classification using attention mechanism with dual TQWT and triple STFT spectrogram

Objective. Auscultation of lung sound plays an important role in the early diagnosis of lung diseases. This work aims to develop an automated adventitious lung sound detection method to reduce the workload of physicians.Approach. We propose a deep learning architecture, LungAttn, which incorporates augmented attention convolution into ResNet block to improve the classification accuracy of lung sound. We adopt a feature extraction method based on dual tunableQ-factor wavelet transform and triple short-time Fourier transform to obtain a multi-channel spectrogram. Mixup method is introduced to augment adventitious lung sound recordings to address the imbalance dataset problem.Main results. Based on the ICBHI 2017 challenge dataset, we implement our framework and compare with the state-of-the-art works. Experimental results show that LungAttn has achieved theSensitivity, S_e,Specificity, S_pandScoreof 36.36%, 71.44% and 53.90%, respectively. Of which, our work has improved theScoreby 1.69% compared to the state-of-the-art models based on the official ICBHI 2017 dataset splitting method.Significance. Multi-channel spectrogram based on different oscillatory behavior of adventitious lung sound provides necessary information of lung sound recordings. Attention mechanism is introduced to lung sound classification methods and has proved to be effective. The proposed LungAttn model can potentially improve the speed and accuracy of lung sound classification in clinical practice.

Blind Equalization of Lung Crackle Sounds to Compensate Chest Attenuation

Diseased lungs generate adventitious sounds that propagate through the thorax, reaching the surface where they may be heard or recorded. The attenuation imposed to the lung sounds by the thorax depends on the physical characteristics of each patient, hampering the analysis of quantitative indexes measured to assist the diagnosis of cardiorespiratory disorders. This work proposes the application of a blind equalizer (eigenvector algorithm - EVA) to reduce the effects of thorax attenuation on indexes measured from crackle sounds. Computer simulated crackles (acquired on the posterior chest wall after being applied to volunteer's mouth) and actual crackles belonging to a database were equalized. Quantitative indexes were measured from crackles before and after equalization. Comparison of indexes measured from simulated crackles reveals that the equalizer improves the results due to attenuation compensation and removal of Gaussian noise. Effects of equalization on indexes measured from actual crackles were qualitatively assessed. Results point out that blind equalization of crackles recorded on the thorax provides more consistent quantitative indexes to assist the diagnosis of different cardiorespiratory diseases.

Accuracy of chest auscultation in detecting abnormal respiratory mechanics in the immediate postoperative period after cardiac surgery

Objective:

To investigate the accuracy of chest auscultation in detecting abnormal respiratory mechanics.

Methods:

We evaluated 200 mechanically ventilated patients in the immediate postoperative period after cardiac surgery. We assessed respiratory system mechanics - static compliance of the respiratory system (C_st,rs) and respiratory system resistance (R,rs) - after which two independent examiners, blinded to the respiratory system mechanics data, performed chest auscultation.

Results:

Neither decreased/abolished breath sounds nor crackles were associated with decreased C_st,rs (≤ 60 mL/cmH₂O), regardless of the examiner. The overall accuracy of chest auscultation was 34.0% and 42.0% for examiners A and B, respectively. The sensitivity and specificity of chest auscultation for detecting decreased/abolished breath sounds or crackles were 25.1% and 68.3%, respectively, for examiner A, versus 36.4% and 63.4%, respectively, for examiner B. Based on the judgments made by examiner A, there was a weak association between increased R,rs (≥ 15 cmH₂O/L/s) and rhonchi or wheezing (ϕ = 0.31, p < 0.01). The overall accuracy for detecting rhonchi or wheezing was 89.5% and 85.0% for examiners A and B, respectively. The sensitivity and specificity for detecting rhonchi or wheezing were 30.0% and 96.1%, respectively, for examiner A, versus 10.0% and 93.3%, respectively, for examiner B.

Conclusions:

Chest auscultation does not appear to be an accurate diagnostic method for detecting abnormal respiratory mechanics in mechanically ventilated patients in the immediate postoperative period after cardiac surgery.

Feasibility of computerized adventitious respiratory sounds to assess the effects of airway clearance techniques in patients with bronchiectasis

Objective: To examine the feasibility of adventitious respiratory sound (ARS) as an outcome measure to assess the effects of airway clearance techniques (ACTs) in outpatients with bronchiectasis. Methods: ARS were registered pre/post four ACTs sessions. Clinical outcomes included: number of crackles (coarse and fine), number of wheezes (monophonic and polyphonic), wheezes occupation rate (%) and sputum quantity. Feasibility outcomes of ARS included: reasons for exclusion, suitability, safety, equipment and time required, magnitude of change after intervention and sample size estimation. Results: Seven patients (49.7 ± 20.5 years; FEV₁ 69.3 ± 15.8% predicted) were included. Recordings from four patients were excluded due to excessive environment noise. All ARS measurements were completed without any adverse events. An electronic stethoscope was acquired and the time spent to complete each assessment was 6 ± 3.5 min. The largest changes were observed for number of expiratory coarse crackles [effect size (95%CI) ES = 0.40 (0.01-0.79)], which correlated moderately with sputum quantity (r = 0.56), and inspiratory monophonic wheezes [ES = 0.61 (0.22-1.00)]. The estimated sample size for a full crossover trial was 46. Conclusions: ARS is feasible to assess the effects of ACTs in patients with bronchiectasis. Expiratory coarse crackles seem to be the most appropriate ARS parameter, but this finding needs to be confirmed in an adequately powered trial.

Instantaneous frequency based index to characterize respiratory crackles

BACKGROUND

Crackle is a lung sound widely employed by health staff to identify respiratory diseases. The two-cycle duration (2CD) is a quantitative index pointed out by the American Thoracic Society and the European Respiratory Society to classify respiratory crackles as fine or coarse. However, this index, measured in the time domain, is highly affected by noise and filters of recording systems. Such factors hamper the analysis of data reported by different research groups. This work proposes a new index based on the instantaneous frequency of crackles estimated by means of discrete-time pseudo Wigner-Ville distribution.

METHOD

Comparisons between 2CD and the proposed index were carried out for simulated and actual crackles. Normal breathing sounds were added to simulated crackles; the resulting signals were then applied to a band-pass filter that mimics those belonging to lung sound acquisition systems. Thus, the impact of noise and filtering on these two indices was assessed for simulated crackles. Kruskal-Wallis and Dunn's tests as well as Gaussian mixture model (GMM) were applied to the two indices measured from 382 actual crackles belonging to open databases.

RESULTS

The proposed index is much less susceptible to waveform distortions due to noise and filtering when compared to the 2CD. Thus, the statistical analyses allow the identification of two classes of crackles from actual databases; the same does not occur when using 2CD.

CONCLUSIONS

The new proposed index has the potential to contribute for a better characterization of crackles generated by different respiratory diseases, assisting their diagnosis during clinical exams.