[LEOSound, an innovative procedure for acoustic long-term monitoring of asthma symptoms (wheezing and coughing) in children and adults]

Nighttime Continuous Contactless Smartphone-Based Cough Monitoring for the Ward: Validation Study

BACKGROUND

Clinical deterioration can go unnoticed in hospital wards for hours. Mobile technologies such as wearables and smartphones enable automated, continuous, noninvasive ward monitoring and allow the detection of subtle changes in vital signs. Cough can be effectively monitored through mobile technologies in the ward, as it is not only a symptom of prevalent respiratory diseases such as asthma, lung cancer, and COVID-19 but also a predictor of acute health deterioration. In past decades, many efforts have been made to develop an automatic cough counting tool. To date, however, there is neither a standardized, sufficiently validated method nor a scalable cough monitor that can be deployed on a consumer-centric device that reports cough counts continuously. These shortcomings limit the tracking of coughing and, consequently, hinder the monitoring of disease progression in prevalent respiratory diseases such as asthma, chronic obstructive pulmonary disease, and COVID-19 in the ward.

OBJECTIVE

This exploratory study involved the validation of an automated smartphone-based monitoring system for continuous cough counting in 2 different modes in the ward. Unlike previous studies that focused on evaluating cough detection models on unseen data, the focus of this work is to validate a holistic smartphone-based cough detection system operating in near real time.

METHODS

Automated cough counts were measured consistently on devices and on computers and compared with cough and noncough sounds counted manually over 8-hour long nocturnal recordings in 9 patients with pneumonia in the ward. The proposed cough detection system consists primarily of an Android app running on a smartphone that detects coughs and records sounds and secondarily of a backend that continuously receives the cough detection information and displays the hourly cough counts. Cough detection is based on an ensemble convolutional neural network developed and trained on asthmatic cough data.

RESULTS

In this validation study, a total of 72 hours of recordings from 9 participants with pneumonia, 4 of whom were infected with SARS-CoV-2, were analyzed. All the recordings were subjected to manual analysis by 2 blinded raters. The proposed system yielded a sensitivity and specificity of 72% and 99% on the device and 82% and 99% on the computer, respectively, for detecting coughs. The mean differences between the automated and human rater cough counts were -1.0 (95% CI -12.3 to 10.2) and -0.9 (95% CI -6.5 to 4.8) coughs per hour within subject for the on-device and on-computer modes, respectively.

CONCLUSIONS

The proposed system thus represents a smartphone cough counter that can be used for continuous hourly assessment of cough frequency in the ward.

[Analysis of Snoring in Patients with Obstructive Sleep Apnea (OSA) by Polysomnography and LEOSound]

INTRODUCTION

Snoring was monitored in patients with obstructive sleep apnea (OSA) using the LEOSound-Monitor and simultaneously polysomnographic (PSG) recording. In obstructive apneas snoring is normally apparent after apnea termination and the beginning of ventilation. We wanted to know how often obstructive apneas are terminated by ventilation in combination with snoring.

METHODS AND INTENTION

In 40 patients with OSA (AHI > 15/h) simultaneous polysomnographic recordings were performed amongst long-term respiratory sound monitoring using the LEOSound monitor. Patients' average age was 57±11 years. Average weight was 100±19 kg by a mean body mass index (BMI) of 33±7 kg/m². 12 out of 40 recordings had to be rejected for further analysis because of artifacts. Snoring recorded by polysomnography was compared with snoring monitored by LEOSound.

RESULTS

3778 obstructive apnea episodes were monitored. LEOSound identified snoring in 1921 (51,0%), polysomnography in 2229 (58,8%) obstructive apneas. Only in one patient there was a higher difference in snoring episodes between PSG and LEOSound.

DISCUSSION

In nearly 60% of obstructive apnea events we found snoring during apnea-terminating hyperpnoea. LEOSound is a good diagnostic tool to monitor snoring. It is necessary to clarify why only 60% of all obstructive events/hyperpnoea develop snoring. From a pathophysiological point of view opening of collapsed upper airway should lead in a very high percentage to turbulences in airstream and committed snoring.

Methods for Adventitious Respiratory Sound Analyzing Applications Based on Smartphones: A Survey

Detection and classification of adventitious acoustic lung sounds plays an important role in diagnosing, monitoring, controlling and, caring the patients with lung diseases. Such systems can be presented as different platforms like medical devices, standalone software or smartphone application. Ubiquity of smartphones and widespread use of the corresponding applications make such a device an attractive platform for hosting the detection and classification systems for adventitious lung sounds. In this paper, the smartphone-based systems for automatic detection and classification of the adventitious lung sounds are surveyed. Such adventitious sounds include cough, wheeze, crackle and, snore. Relevant sounds related to abnormal respiratory activities are considered as well. The methods are shortly described and the analyzing algorithms are explained. The analysis includes detection and/or classification of the sound events. A summary of the main surveyed methods together with the classification parameters and used features for the sake of comparison is given. Existing challenges, open issues and future trends will be discussed as well.

Wheeze and cough measurements at night in children with respiratory symptoms

Background

Nocturnal cough and wheeze are important symptoms when diagnosing any respiratory disease in a child, but objective measurements of these symptoms are not performed.

Methods

The aim of our study was to analyze the use of an automated detection system to assess breath sounds objectively in comparison to cough and wheeze questionnaires and to evaluate its feasibility in clinical practice.

Results

Forty-nine recordings of thirty-nine children were processed (asthma n = 13; cystic fibrosis n = 2; pneumonia n = 5; suspicion of habit cough n = 7; prolonged, recurrent or chronic cough n = 13), and cough and asthma scores were compared to the objective nocturnal recordings. Time for audio-validation of recordings took between 2 and 40 min (mean: 14.22 min, (SD): 10.72). Accuracy of the automated measurement was higher for cough than for wheezing sounds. Nocturnal cough readings but not wheeze readings correlated with some of the corresponding scores.

Conclusion

To our knowledge this is the first study using a new device to assess nocturnal cough and obstructive breath sounds objectively in children with a wide variety of respiratory diseases. The assessment proved user friendly. We obtained additional information on nighttime symptoms, which would otherwise have remained obscure. Further studies to assess possible diagnostic and therapeutic benefits of this device are needed.

Disease control in patients with asthma and respiratory symptoms (wheezing, cough) during sleep

INTRODUCTION

The Global Initiative for Asthma (GINA)-defined criteria for asthma control include questions about daytime symptoms, limitation of activity, nocturnal symptoms, need for reliever treatment and patients' satisfaction. Patients with nocturnal symptoms like wheezing and cough often suffer from lower sleep quality and impaired daytime performance. The lack of an appropriate method for standardized and objective monitoring of respiratory symptoms leads to difficulties in asthma management. The aim of this study is to present a new method for automated wheeze and cough detection during sleep and to assess the actual level of asthma control by the Asthma Control Test (ACT).

METHODS

Respiratory symptoms like wheezing and cough were recorded with the LEOSound-Monitor for one night in 55 asthmatic patients in their individual domestic setting. Patients were asked to assess their level of asthma subjectively with the ACT. The study consisted of 37 women and 18 men, with a mean age of 41 years, and a mean BMI of 27 kg/m2. Most of the patients had been taking an ICS/LABA combination and would resort to a SABA as their rescue medication.

RESULTS

60% of the participants were classed as having controlled, and 40% were classed as having partially- or uncontrolled asthma. During sleep wheezing was found in 8 of the 55 asthma patients (14.5%) and coughing was found in 30 patients (54.5%). The median ACT score in wheezing-patients was 14, while in non-wheezing patients it was 21. Uncontrolled asthma was found in 6 of the 8 wheezing-patients. Coughing versus non-coughing patients did not show a significant difference in the ACT-score (20, 22 respectively).

CONCLUSION

Wheezing is a sign of uncontrolled asthma. The ACT-score in wheezing patients is worse compared to patients without wheezing. LEOSound proofed to be a useful tool in providing an objective evaluation of respiratory symptoms, like coughing and wheezing. In clinical practice, this may allow an improvement in asthma therapy.

[Analysis of Snoring in Patients with Obstructive Sleep Apnea (OSA) by Polysomnography and LEOSound]

INTRODUCTION

 Snoring was monitored in patients with obstructive sleep apnea (OSA) using the LEOSound-Monitor and simultaneously polysomnographic (PSG) recording. In obstructive apneas snoring is normally apparent after apnea termination and the beginning of ventilation. We wanted to know how often obstructive apneas are terminated by ventilation in combination with snoring.

METHODS AND INTENTION

 In 40 patients with OSA (AHI > 15/h) simultaneous polysomnographic recordings were performed amongst long-term respiratory sound monitoring using the LEOSound monitor. Patients' average age was 57 ± 11 years. Average weight was 100 ± 19 kg by a mean body  mass  index (BMI) of 33 ± 7 kg/m². 12 out of 40 recordings had to be rejected for further analysis because of artifacts. Snoring recorded by polysomnography was compared with snoring monitored by LEOSound.

RESULTS

 3778 obstructive apnea episodes were monitored. LEOSound identified snoring in 1921 (51,0 %), polysomnography in 2229 (58,8 %) obstructive apneas. Only in one patient there was a higher difference in snoring episodes between PSG and LEOSound.

DISCUSSION

 In nearly 60 % of obstructive apnea events we found snoring during apnea-terminating hyperpnoea. LEOSound is a good diagnostic tool to monitor snoring. It is necessary to clarify why only 60 % of all obstructive events/hyperpnoea develop snoring. From a pathophysiological point of view opening of collapsed upper airway should lead in a very high percentage to turbulences in airstream and committed snoring.

Day and Night Control of COPD and Role of Pharmacotherapy: A Review

The topic of 24-hour management of COPD is related to day-to-night symptoms management, specific follow-up and patients' adherence to therapy. COPD symptoms strongly vary during day and night, being worse in the night and early morning. This variability is not always adequately considered in the trials. Night-time symptoms are predictive of higher mortality and more frequent exacerbations; therefore, they should be a target of therapy. During night-time, in COPD patients the supine position is responsible for a different thoracic physiology; moreover, during some sleep phases the vagal stimulation determines increased bronchial secretions, increased blood flow in the bronchial circulation (enhancing inflammation) and increased airway resistance (broncho-motor tone). Moreover, in COPD patients the circadian rhythm may be impaired. The role of pharmacotherapy in this regard is still poorly investigated. Symptoms can be grossly differentiated according to the different phenotypes of the disease: wheezing recalls asthma, while dyspnea is strongly related to emphysema (dynamic hyperinflation) or obstructive bronchiolitis (secretions). Those symptoms may be different targets of therapy. In this regard, GOLD recommendations for the first time introduced the concept of phenotype distinction suggesting the use of inhaled corticosteroids (ICS) particularly when an asthmatic pattern or eosiophilic inflammations are present, and hypothesized different approaches to target symptoms (ie, dyspnea) or exacerbations. Pharmacotherapy should be evaluated and possibly directed on the basis of circadian variations, for instance, supporting the use of twice-daily rapid-action bronchodilators and evening dose of ICS. Recommendations on day and night symptoms monitoring strategies and choice of the specific drug according to patient's profile are still not systematically investigated or established. This review is the summary of an advisory board on the topic "24-hour control of COPD and role of pharmacotherapy", held by five pulmonologists, experts in respiratory pathophysiology, pharmacology and sleep medicine.

Time course of nocturnal cough and wheezing in children with acute bronchitis monitored by lung sound analysis

Cough and wheezing are the predominant symptoms of acute bronchitis. Hitherto, the evaluation of respiratory symptoms was limited to subjective methods such as questionnaires. The main objective of this study was to objectively determine the time course of cough and wheezing in children with acute bronchitis. The impact of nocturnal cough on parent's quality of life was assessed as secondary outcome. In 36 children (2-8 years), the frequency of nocturnal cough and wheezing was recorded during three nights by automated lung sound monitoring. Additionally, parents completed symptom logs, i.e., the Bronchitis Severity Score (BSS), as well as the Parent-proxy Children's Acute Cough-specific Quality of Life Questionnaire (PAC-QoL). During the first night, patients had 34.4 ± 52.3 (mean ± SD) cough epochs, which were significantly reduced in night 5 (13.5 ± 26.5; p < 0.001) and night 9 (12.8 ± 28.1; p < 0.001). Twenty-two patients had concomitant wheezing, which declined within the observation period as well. All subjective parameters (BSS, Cough log and PAC-QoL) were found to be significantly correlated with the objectively assessed cough parameters.Conclusion: Long-term recording of cough and wheezing offers a useful opportunity to objectively evaluate the time course of respiratory symptoms in children with acute bronchitis. To assess putative effects of pharmacotherapy on nocturnal bronchitis symptoms, future studies in more homogeneous patient groups are needed. What is Known: • Cough and wheezing are the predominant symptoms of acute bronchitis. • There is a diagnostic gap in long-term assessment of these respiratory symptoms, which needs to be closed to optimize individual therapies. What is New: • Long-term recording of nocturnal cough and wheezing allows for objective evaluation of respiratory symptoms in children with acute bronchitis and provides a tool to validate the efficacy of symptomatic bronchitis therapies.

Description of nighttime cough epochs in patients with stable COPD GOLD II-IV

Purpose

Chronic cough is one of the main symptoms of COPD. Ambulatory objective monitoring provides novel insights into the determinants and characteristics of nighttime cough in COPD.

Materials and methods

Nighttime cough was monitored objectively by LEOSound lung sound monitor in patients with stable COPD II–IV. In 30 patients, with 10 patients in each stage group, nighttime cough was analyzed for epoch frequency, epoch severity (epoch length and coughs per epoch), and pattern (productive or nonproductive).

Results

Cough was found in all patients ranging from 1 to 294 events over the recording period. In 29 patients, cough epochs were monitored, ranging from 1 to 75 epochs. The highest amount of cough epochs was found in patients with COPD stage III. Active smokers had significantly more productive cough epochs (61%) than nonsmokers (24%).

Conclusion

We found a high rate of nighttime cough epochs in patients with COPD, especially in those in stage III. Productive cough was predominantly found in patients with persistent smoking. LEOSound lung sound monitor offers a practical and valuable opportunity to evaluate cough objectively.

Long-term Recording of Night-Time Respiratory Symptoms in Patients with Stable COPD II-IV

INTRODUCTION

Night-time respiratory symptoms have a considerable impact on sleep and life quality in patients with chronic obstructive pulmonary disease (COPD). Lack of awareness of night-time symptoms can lead to worsened COPD control. Automated long-term monitoring of respiratory symptoms with LEOSound enables assessment of nocturnal wheezing and cough.

METHODS

In this observational study we investigated the prevalence and severity of cough and wheezing in patients with stable COPD [Global Initiative for Chronic Obstructive Lung Disease (GOLD) II-IV] disease for two consecutive nights with the LEOSound system. 48 patients (30 males, 63%) were eligible for inclusion, median age was 67 years, and body mass index (BMI) was 25.3 kg/m².

RESULTS

In 15 out of 48 patients (31%), we found wheezing periods for at least 10-minute duration. Wheezing periods >30 minutes were monitored in seven patients and wheezing periods >60 minutes were monitored in three patients. The maximum duration of wheezing was 470 minutes in one patient with COPD II. The median wheezing rate differed between the COPD stages and between active and non-active smokers. Cough was found in 42 patients (87.5%) with a range of 1-326 events. The cough-period-index in night one was 0.83 n/hour (P25:0.33||P75: 2.04) and night two 0.97 n/hour (P25:0.25||P75: 1.9). Most of the cough events were non-productive with a median of 0.86.

CONCLUSIONS

Night-time symptoms are common in COPD patients. LEOSound offers an opportunity to evaluate objectively night-time symptoms like wheezing and cough in patients with COPD which remain otherwise unnoticed. We found a high incidence of night-time wheezing in these patients, which was related to persistant smoking.

Protocol for studying cough frequency in people with pulmonary tuberculosis

INTRODUCTION

Cough is a key symptom of tuberculosis (TB) as well as the main cause of transmission. However, a recent literature review found that cough frequency (number of coughs per hour) in patients with TB has only been studied once, in 1969. The main aim of this study is to describe cough frequency patterns before and after the start of TB treatment and to determine baseline factors that affect cough frequency in these patients. Secondarily, we will evaluate the correlation between cough frequency and TB microbiological resolution.

METHODS

This study will select participants with culture confirmed TB from 2 tertiary hospitals in Lima, Peru. We estimated that a sample size of 107 patients was sufficient to detect clinically significant changes in cough frequency. Participants will initially be evaluated through questionnaires, radiology, microscopic observation drug susceptibility broth TB-culture, auramine smear microscopy and cough recordings. This cohort will be followed for the initial 60 days of anti-TB treatment, and throughout the study several microbiological samples as well as 24 h recordings will be collected. We will describe the variability of cough episodes and determine its association with baseline laboratory parameters of pulmonary TB. In addition, we will analyse the reduction of cough frequency in predicting TB cure, adjusted for potential confounders.

ETHICS AND DISSEMINATION

Ethical approval has been obtained from the ethics committees at each participating hospital in Lima, Peru, Asociación Benéfica PRISMA in Lima, Peru, the Universidad Peruana Cayetano Heredia in Lima, Peru and Johns Hopkins University in Baltimore, USA. We aim to publish and disseminate our findings in peer-reviewed journals. We also expect to create and maintain an online repository for TB cough sounds as well as the statistical analysis employed.