Computerised respiratory sounds can differentiate smokers and non-smokers

Digital Pulmonology Practice with Phonopulmography Leveraging Artificial Intelligence: Future Perspectives Using Dual Microwave Acoustic Sensing and Imaging

Respiratory disorders, being one of the leading causes of disability worldwide, account for constant evolution in management technologies, resulting in the incorporation of artificial intelligence (AI) in the recording and analysis of lung sounds to aid diagnosis in clinical pulmonology practice. Although lung sound auscultation is a common clinical practice, its use in diagnosis is limited due to its high variability and subjectivity. We review the origin of lung sounds, various auscultation and processing methods over the years and their clinical applications to understand the potential for a lung sound auscultation and analysis device. Respiratory sounds result from the intra-pulmonary collision of molecules contained in the air, leading to turbulent flow and subsequent sound production. These sounds have been recorded via an electronic stethoscope and analyzed using back-propagation neural networks, wavelet transform models, Gaussian mixture models and recently with machine learning and deep learning models with possible use in asthma, COVID-19, asbestosis and interstitial lung disease. The purpose of this review was to summarize lung sound physiology, recording technologies and diagnostics methods using AI for digital pulmonology practice. Future research and development in recording and analyzing respiratory sounds in real time could revolutionize clinical practice for both the patients and the healthcare personnel.

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.

Minimal Important and Detectable Differences of Respiratory Measures in Outpatients with AECOPD†

Interpreting clinical changes during acute exacerbations of chronic obstructive pulmonary disease (AECOPD) is challenging due to the absence of established minimal detectable (MDD) and important (MID) differences for most respiratory measures. This study established MDD and MID for respiratory measures in outpatients with AECOPD following pharmacological treatment. COPD assessment test (CAT), modified Borg scale (MBS), modified British Medical Research Council (mMRC) questionnaire, peripheral oxygen saturation (SpO₂), computerised respiratory sounds and forced expiratory volume in one second (FEV₁) were collected within 24-48 hour of an AECOPD and after 45 days of pharmacological treatment. MID and MDD were calculated using anchor- (receiver operating characteristic and linear regression analysis) and distribution-based methods (effect size, SEM, 0.5*SD and MDC95) and pooled using Meta XL. Forty-four outpatients with AECOPD (31♂; 68.2 ± 9.1 years; FEV₁ 51.1 ± 20.3%predicted) participated. Significant correlations with CAT were found for the MBS (r = 0.34), mMRC (r = 0.39) and FEV₁ (r = 0.33), resulting in MIDs of 0.8, 0.5-0.6 and 0.03L, respectively. MDD of 0.5-1.4 (MBS), 0.4-1.2 (mMRC), 0.10-0.28L (FEV₁), 3.6-10.1% (FEV₁%predicted), 0.9-2.4% (SpO₂), 0.7-1.9 (number of inspiratory crackles), 1.1-4.5 (number of expiratory crackles), 7.1-25.8% (inspiratory wheeze rate) and 11.8-63.0% (expiratory wheeze rate) were found. Pooled data of MID/MDD showed that improvements of 0.9 for the MBS, 0.6 for the mMRC, 0.15L for the FEV₁, 7.6% for the FEV₁%predicted, 1.5% for the SpO₂, 1.1 for the inspiratory and 2.4 for the number of expiratory number of crackles, 14.1% for the inspiratory and 32.5% for the expiratory wheeze rate are meaningful following an AECOPD managed with pharmacological treatment on an outpatient basis.

Reliability, validity and minimal detectable change of computerized respiratory sounds in patients with chronic obstructive pulmonary disease

INTRODUCTION

Computerized respiratory sounds (CRS) are closely related to the movement of air within the tracheobronchial tree and are promising outcome measures in patients with chronic obstructive pulmonary disease (COPD). However, CRS measurement properties have been poorly tested.

OBJECTIVE

The aim of this study was to assess the reliability, validity and the minimal detectable changes (MDC) of CRS in patients with stable COPD.

METHODS

Fifty patients (36♂, 67.26 ± 9.31y, FEV₁ 49.52 ± 19.67%predicted) were enrolled. CRS were recorded simultaneously at seven anatomic locations (trachea; right and left anterior, lateral and posterior chest). The number of crackles, wheeze occupation rate, median frequency (F50) and maximum intensity (Imax) were processed using validated algorithms. Within-day and between-days reliability, criterion and construct validity, validity to predict exacerbations and MDC were established.

RESULTS

CRS presented moderate-to-excellent within-day reliability (ICC_1,3  ≥ 0.51; P < .05) and moderate-to-good between-days reliability (ICC_1,2  ≥ 0.47; P < .05) for most locations. Negligible-to-moderate correlations with FEV₁ %predicted were found (-0.53 < r_s  < -0.28; P < .05), and the inspiratory number of crackles were the best discriminator between mild-to-moderate and severe-to-very severe airflow limitations (area under the curve >0.78). CRS correlated poorly with patient-reported outcomes (r_s  < 0.48; P < .05) and did not predict exacerbations. Inspiratory number of crackles at posterior right chest, inspiratory F50 at trachea and anterior left chest and expiratory Imax at anterior right chest were simultaneously reliable and valid, and their MDC were 2.41, 55.27, 29.55 and 3.98, respectively.

CONCLUSION

CRS are reliable and valid. Their use, integrated with other clinical and patient-reported measures, may fill the gap of assessing small airways and contribute toward a patient's comprehensive evaluation.