A wearable multi-modal acoustic system for breathing analysis

Abstract

Chronic obstructive pulmonary disease (COPD) is the third leading cause of death worldwide with over 3 × 10 6 deaths in 2019. Such an alarming figure becomes frightening when combined with the number of lost lives resulting from COVID-caused respiratory failure. Because COPD exacerbations identified early can commonly be treated at home, early symptom detections may enable a major reduction of COPD patient readmission and associated healthcare costs; this is particularly important during pandemics such as COVID-19 in which healthcare facilities are overwhelmed. The standard adjuncts used to assess lung function (e.g., spirometry, plethysmography, and CT scan) are expensive, time consuming, and cannot be used in remote patient monitoring of an acute exacerbation. In this paper, a wearable multi-modal system for breathing analysis is presented, which can be used in quantifying various airflow obstructions. The wearable multi-modal electroacoustic system employs a body area sensor network with each sensor-node having a multi-modal sensing capability, such as a digital stethoscope, electrocardiogram monitor, thermometer, and goniometer. The signal-to-noise ratio (SNR) of the resulting acoustic spectrum is used as a measure of breathing intensity. The results are shown from data collected from over 35 healthy subjects and 3 COPD subjects, demonstrating a positive correlation of SNR values to the health-scale score.

Enabling effective breathing sound analysis for automated diagnosis of lung diseases

“…Segmenting a breathing sound signal is complicated by the background noise ( Emokpae et al, 2021 ). Some work has focused on tackling the noise effect at the sensor level by factoring in other modality ( Gupta et al, 2021 ).…”

“…Jacome et al ( Jácome Cristina et al, 2019 ) propose a model for breathing phase detection based on Faster R–CNN object detection system. However, these dynamic segmentation approaches are limited to detecting respiratory periods and cannot be applied to assess lung function status ( Emokpae et al, 2022 ). For patients with COPD, being able to assess changes in lung function will enable early treatment intervention.…”

“…Whereby the ratio of FEV1 to FVC can be used to diagnose if a patient has COPD ( Pellegrino et al, 2005 ). In our recent publication ( Emokpae et al, 2022 ), we show that we can leverage features of breathing cycles with normal and deep breaths to estimate lung function status. The proposed AUDAS approach enables automated segmentation of breathing features which can be used to compute FEV1 and FVC, for effective COPD diagnosis.…”

“…This is illustrated in Fig. 2 , which shows a combination of breathing sounds with S1/S2 heart sounds collected by our wearable sensor used in breathing analysis ( Emokpae et al, 2021 ). Ensuring accurate anomaly detection in presence of noise is necessary for accurate diagnosis.…”

Wearable pulmonary monitoring system with integrated functional lung imaging and chest sound recording: a clinical investigation in healthy subjects

“…forced expiratory volume in 1 s (FEV 1 ) or forced vital capacity (FVC)) and peripheral transcutaneous oxygen saturation, respectively. Another add-on method that might expand the information content generated by wearables in a remote setting employs electronic stethoscopes to register acoustic signals (Au et al 2022, Emokpae et al 2022. Through the stated add-on methods, the conventional pulmonary function parameters, the gas exchange efficiency and the presence of pathological lung sounds can be assessed.…”