Validation of manual and automated wheezing detection from audio recordings

Abstract

Introduction: Presently human experts must diagnose wheezing at the bedside using real-time analog tools (ear, stethoscope). Human experts could diagnose wheezing from digital audio files. Further, automated wheezing detection from unattended digital recordings would obviate bedside human diagnosis.

Aim: To validate the detection of wheezing from unattended digital recordings.

Methods: 189 digital audio recordings of 30 s duration were obtained using a dedicated digital microphone device (Wheezo, Respiri Limited, Melbourne) from 56 hospitalized patients (38 F; age 21 to 87 - mean 63.5 years; 26 COPD, 27 asthma, 1 vocal cord dysfunction, and 2 other) and 20 ambulatory normal adult controls. Wheezes were scored manually by two respirologists (KP, NS) and by a biomedical engineer (RSP). Their consensus was compared to an automated wheeze scoring algorithm. The accuracy, sensitivity, and specificity of automated wheeze rate detection were calculated along with Cohen's κ coefficient (R 3.4.4). We further plan to apply the algorithm to the ERS reference database of lung sounds.

Results: The accuracy, sensitivity, and specificity of automated wheeze rate detection were 90.5, 87.1, and 93.3%. Cohen's κ coefficient was 0.81. Breath-by-breath comparison of human and automated scoring showed near-perfect agreement for the presence, absence, and duration of wheezes.

Conclusion: Wheezing can be diagnosed from digital audio recordings either manually by human experts or automatically by a computer algorithm. Diagnosing wheezing remotely increases assessment capacity while reducing viral transmission risk during epidemics.