Smartphone Enabled Detection of Nocturnal Cough Rate and Sleep Quality as a Prognostic Marker for Asthma Control

Asthma Clinical Trial

Official title:

Measuring the Prevalence of Nocturnal Cough in Asthmatics by Means of Smartphone-enabled Acoustic Recording and Evaluating the Potential of Nocturnal Cough Rate as a Prognostic Marker for Asthma Control: An Observational Two-Stage Study

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT03635710
• Other study ID #: EKOS 17/164
• Status: Completed
• Start date: January 1, 2018
• Est. completion date: December 31, 2019

Study information

• Verified date: January 2020
• Source: Cantonal Hospital of St. Gallen
• Contact: n/a
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

The purpose of the study is to explore the value which cough rate might provide for asthma self-management. In this study, the focus will be specifically on nocturnal cough rate. The plan is to use a longitudinal study design, in order to investigate to which extent trends in the nocturnal cough rates might have meaningful implications for future asthma control and asthma exacerbations of patients. The incidence of nocturnal cough in asthmatics will be described and visualized over the course of one month in the first stage of the study. Additionally, the aim will be to identify and model trends in nocturnal cough rates.

Measuring cough is very time-consuming. Currently, there are no cough frequency monitors available, which measure cough rates in a fully automated and unobtrusive way. Consequently, manual labeling of cough based on video or sound recordings is still considered to be the gold standard for measuring cough rates by medical guidelines. Recently, a machine learning algorithm was successfully designed to automatically detect cough in a proof of concept study. This machine learning algorithm will be further developed in order to provide robust results in the field. The focus of this study will be the cough during the night time due to the limited interfering noise, which greatly facilitates manual labeling and enables a more reliable detection rate of the machine learning algorithm.

Apart from developing a machine learning algorithm for cough detection, data will be gathered for the assessment of patient's sleep quality based on data obtained from smartphone's sensors.

Description:

Asthma, a chronic respiratory disease, belongs to the most prevalent chronic conditions. In Switzerland, 7-15% of all children and 6-7% of all adults suffer from it. Common symptoms are breathlessness, coughing and wheezing. The symptoms often get worse at night and often cause awakenings. Cough is a particularly important symptom in asthma because it predicts asthma severity, indicates a worse prognosis and is perceived to be a troublesome symptom. Additionally, asthma is the leading cause for chronic cough, responsible for 24-29% of cases.

However, little is known about the utility of cough tracking for self-monitoring purposes in asthmatics. A first cross-sectional study has indicated that the cough rate during both day and night might be a valid marker for asthma control, rendering it a potentially useful parameter for self-monitoring. Unfortunately, due to considerable variance of cough rates within each category of asthma control (i.e. uncontrolled, partially controlled and controlled asthma), the statistically significant relationship between cough rate and asthma control might not be clinically meaningful. Additionally, due to the cross-sectional design of existing studies, it remains unclear whether the cough rate might have any prognostic value for predicting future asthma control.

Therefore, the purpose of this study is to explore the value which cough rate might provide for asthma self-management in more detail. In This study, the focus will be put specifically on nocturnal cough rate due to the technical reasons. In general, the plan of this study is as follows: With a longitudinal study design, it is possible to investigate to which extent trends in the nocturnal cough rates might have meaningful implications for future asthma control and asthma exacerbations of patients. However, in order to analyze the predictive value of trends in nocturnal cough rate, the symptom has to persist over multiple nights. There is no research available on the prevalence of nocturnal cough in asthmatics over multiple nights. Therefore, the incidence of nocturnal cough in asthmatics will be described and visualized over the course of one month in the first stage of our study. Additionally, the aim will be to identify and model trends in nocturnal cough rates.

Measuring cough is very time-consuming. Currently, there are no cough frequency monitors available, which measure cough rates in a fully automated and unobtrusive way. Consequently, manual labeling of cough based on video or sound recordings is still considered to be the gold standard for measuring cough rates by medical guidelines. Nevertheless, a machine learning algorithm has been successfully designed to automatically detect cough in a proof of concept study. Despite using only very limited data for algorithm development (80 coughs from 5 healthy subjects), the accuracy reached 83%. However, the data were gathered in a laboratory setting, which limits the generalizability of the results and thus applicability in practice. Therefore, the aim is to develop a machine learning algorithm which is also capable to provide robust results in the field. This study will focus on cough during the night time due to the limited interfering noise, which greatly facilitates manual labeling and enables a more reliable detection rate of the machine learning algorithm. It is important to point out that the analysis of nocturnal cough prevalence described above will not be based on cough detected by an algorithm, but on the manually labeled coughs in the audio track recorded during the night by a study smartphone, which will be provided to subjects for the course of the study.

Apart from developing a machine learning algorithm for cough detection, data will be gathered for an algorithm assessing patient's sleep quality. For this purpose, sleep quality will be predicted based on data obtained from the smartphone's sensors.

After concluding the first study stage, the prevalence of nocturnal cough in the study will determine whether further analyses of the recorded data will be needed and thereby initiate the second stage of the study. If nocturnal cough does not occur more frequently than could be explained by chance alone, no additional analysis will be conducted implying that the conclusion of the first stage and the end of the project. However, given a sufficient prevalence of nocturnal cough in the first stage (i.e. nocturnal cough prevalence differs from zero with statistical significance); the second stage of the study will focus on the value of nocturnal cough as a prognostic marker for asthma control. The considerable variance within categories of asthma control shown in suggests that the relationship between nocturnal cough rate and asthma control might be moderated by other variables. Prior research has demonstrated that sleep quality is associated with asthma control and quality of life: Even if accounted for concomitant diseases (e.g. gastroesophageal reflux disease and obstructive sleep apnea), poorer sleep quality is associated with worse asthma control and quality of life. One reason for the association between sleep quality and asthma control might be that nocturnal asthma symptoms frequently cause awakenings. Considering the importance of sleep quality for asthma control, the (predictive) value of the nocturnal cough rate and its influence on sleep quality will be explored.

In summary, the following asthma-related research question will be explored within each stage of this study: (1) what is the prevalence of nocturnal cough in asthmatics over the course of one month? (2) Is nocturnal cough, accounted for sleep quality, a valid prognostic marker for asthma control? Additionally, the study addresses two technical objectives: gather data to develop two machine learning algorithms, which are able to detect nocturnal cough and sleep quality fully automated by means of a smartphone in real-life conditions.

Answering these research questions results in multiple contributions: in terms of asthma-related questions, the hope will be to provide context on the symptom of nocturnal cough in order to increase interpretability of cough rates and to successfully replicate and expand the findings of, which would support the validity of nocturnal cough as a (prognostic) marker for asthma control. In terms of technical objectives, the hope will be to provide a proof of concept that smartphones are suitable devices for sensing asthma symptoms in an automated fashion under real-life conditions.

The expected results could enable a novel therapeutic option, namely fully automated tele-monitoring of asthmatics. Using the smartphone of a patient, an unobtrusive early warning system for asthma worsening/exacerbations could be envisioned. Such an system could lower the burden of asthma for both the individual patient (e.g. higher quality of life and asthma control by identifying windows of opportunity, in which patients can change their medication according to their asthma action plan to prevent asthma worsening and exacerbations) as well as the healthcare system (i.e. cost savings due to reduced hospitalizations and emergency room visits). Considering the wide spread availability of smartphones, such a novel therapeutic option might enable large scale and cost-efficient asthma tele-monitoring. Prior research has indicated the need for such a novel therapeutic option: the majority of asthmatics suffers from uncontrolled asthma. Half of asthmatics are not able to assess their symptom severity properly and would thus benefit from an early warning system. Additionally, automated systems seem to have a higher long term engagement compared to traditional interventions, making them particularly suitable for early warning systems in chronic diseases. Furthermore, tele-monitoring of symptoms could provide physicians with valuable insights regarding a patient's asthma symptoms between visits. In summary, an automated early warning system might help patients register asthma worsening earlier and inform their physicians in time, so that adverse health consequences can be prevented.

The planned study falls into the risk category of health related personal data collection with only minimal risk and burdens. It is a prospective observational study, no intervention will be administered. Only a slight and temporary impact on the participant's health can be expected, if at all.

Throughout the study, a patient's asthma symptoms will be monitored unobtrusively using the smartphone; thus, minimal risk and burdens are ensured. Between both doctoral visits at the beginning and end of the study, all control questions and questionnaires will be administered via smartphones that we will provide for this study. Thus, the burden should be minimal for patients as their daily routine will not be disrupted.

No invasive procedure will be conducted in the two doctoral visits. The medical examination follows the standard protocol for asthma. Additionally, patients will be reimbursed for any inconveniences encountered during the study.

Recruitment information / eligibility

• Status: Completed
• Enrollment: 94
• Est. completion date: December 31, 2019
• Est. primary completion date: December 31, 2019
• Accepts healthy volunteers: No
• Gender: All
• Age group: 18 Years and older

Eligibility

Inclusion Criteria:

• all patients with physician-diagnosed asthma (obtained through self-reports)

• minimum age 18 years

• proficient in using a smartphone (e.g. for the daily smartphone-based self-

Exclusion Criteria:

• patients with mental diseases resulting in cognitive impairments such as depression, dementia, and Alzheimer's disease

• patients for whom it would not be feasible to obtain reliable nighttime measurements (i.e. patients with severe insomnia or shift workers) or for whom we cannot ensure the correct allocation of nocturnal coughs to the patient in the rating process (i.e. patients who usually share the bed with a person from the same sex).

Related Conditions & MeSH terms

• Asthma
• Cough

Intervention

Device:
• The patient will undergo no intervention
Night coughs will be monitored using smartphone a app and interpreted using machine learning algorithm.

Locations

Country	Name	City	State
Switzerland	Cantonal Hospital St. Gallen	St. Gallen	SG
Switzerland	Cantonal Hospital St. Gallen	St. Gallen
Switzerland	University of Zürich	Zürich	ZH

Sponsors (3)

Lead Sponsor	Collaborator
Cantonal Hospital of St. Gallen	University of St.Gallen, University of Zurich

Country where clinical trial is conducted

Switzerland, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Coughs per night assessed by smartphone audio recording	Number of coughs per night measured by means of smartphone audio recording	28 days
Secondary	Detection rates of two machine learning algorithms	Detection rates of two machine learning algorithms for automated detection of nocturnal cough (sensitivity, specificity and accuracy)	28 days
Secondary	Sleep quality (Pittsburgh sleep quality index)	Sleep quality measured using the Pittsburgh sleep quality index filled out daily	28 days