The Breathe Easy Study. Developing diagnostic tests for respiratory disease using sound measurement and machine learning techniques.
The Breathe Easy Study: Developing digital diagnostic tests for respiratory diseases using non-contact sound recordings in children and adults. Initial technical training and development phase and secondary blinded prospective diagnostic accuracy studies.
ResApp Health
5,000 participants
Mar 23, 2015
Interventional
Conditions
Summary
This study is designed to develop accurate digital diagnostic tests, used on a smart device, for common respiratory illnesses in children and adults including asthma, croup, bronchiolitis, COPD and pneumonia. These tests can then be used in resource-poor communities, emergency departments or via telehealth applications. The aim is to develop tests that are as accurate as an expert clinical assessment but do not need a clinical examination or other investigations such as x-rays to be performed.
Eligibility
Inclusion Criteria1
- Patients with a history of a chronic respiratory condition or who have symptoms of an acute respiratory disease.
Exclusion Criteria4
- Inability to Provide a cough either spontaneously or voluntarily.
- Unable to provide informed consent or assent
- Severe respiratory distress including the use of CPAP or BiPAP
- Abdominal or eye surgery within 3 months
Interested in this trial?
Get notified about updates and connect with the research team.
Interventions
Patients with defined respiratory conditions (including Asthma, COPD, Bronchiolitis, Croup, Interstitial Lung Disease, Pneumonia, Upper and Lower Respiratory infections, Bronchiectasis, Emphysema), confirmed by expert review, will provide one series of (5-10) coughs, recorded by a smartphone for analysis and technical development of an algorithm to produce a digital diagnostic test. This procedure takes 30 seconds when the patient can provide a voluntary cough and up to 5 minutes if spontaneous. Children (who are able to cough on demand or are doing so spontaneously) and adults will be approached. This development phase will develop tests for each of the conditions examined as well as measures of severity and complications. Once the algorithms have been developed and the diagnostic tests refined to appropriate accuracy levels [Predicted Positive and Negative Percent Agreement with expert consenus clinical adjudication to be greater than 80% using a total (n=number needed to have lower limit 95% CI above agreed regulatory body requirements] enrolled cohort with mixed respiratory diseases) further subjects will be enrolled for formal diagnostic accuracy studies with the teams determining clinical results by expert consensus adjudication panel using all available information from clinical notes, digital diagnosis and statistical analysis being blinded from each other. The enrollment and data collection (including cough recording) will be identical to the development phase however the clinical diagnostic teams adjudication will be blinded from the App algorithm developer and the algorithms will be run by a third party. Clinical diagnosis and algorithm diagnosis will be provided separately to a statistical group from Curtin University for analysis. Development of the diagnostic algorithms and the subsequent testing for accuracy is a continuum and ongoing process and is considered the same development program.
Locations(2)
View Full Details on ANZCTR
For the most up-to-date information, visit the official listing.
ACTRN12618001521213