EPISODE
Research type
Research Study
Full title
Exploring patterns of speech and breathing to indicates the presence of Obstructive respiratory disease
IRAS ID
256266
Contact name
Sandra Davies
Contact email
Sponsor organisation
Cwm Taf University Health Board
Duration of Study in the UK
0 years, 7 months, 31 days
Research summary
Chronic respiratory diseases such as chronic obstructive pulmonary disease (COPD) often manifest with abnormal breathing and speech patterns that become more pronounced under periods of physiological stress such as exercising or talking. With increasing severity, these are more evident and subjectively recognisable, but can be difficult to accurately quantify.
There is a growing body of work on human speech breathing patterns in various diseases (e.g. Parkinson’s, Muscle Wasting conditions) and following stroke, but these primarily focus on breathing patterns whilst speaking. Advances in speech analysis and transcription allows breathing patterns, language and articulation to be analysed concurrently which could provide more useful diagnostic information of patients with chronic respiratory diseases in settings where completing spirometry is not possible.
Recent advances in computing power and artificial intelligence now offer great potential to derive clinically relevant information from existing physiological signals that have previously been overlooked. New innovative digital approaches for non-specialist settings (i.e. the home and primary care) are envisaged that will provide diagnostic chronic disease insight. There are many benefits to 'closer to the patient' approaches that have the potential to reduce the burden on patients and health services by: early intervention in chronic disease trajectories; reducing impact and cost of hospital admissions; through preventing of disease exacerbations.
To allow this to happen an anonymised database of patients with respiratory disease at variety of disease severity talking under a range of modalities e.g. reciting a piece of text, describing an image for example is required. This will allow colleagues in the School of Computing at Swansea University to begin comparing a variety of derived indices that can then be compared to the severity of chronic disease.REC name
Wales REC 6
REC reference
18/WA/0415
Date of REC Opinion
14 Jan 2019
REC opinion
Further Information Favourable Opinion