Decoding breath: Clinician perspectives on AI-powered Smartphone Audio Applications for Chronic Respiratory Disease using Insights from Eupnoos (ID 660)
Nuffield Dept of Primary Care Health Sciences, University of Oxford
Abstract
Background and Aim: Chronic respiratory diseases (CRDs), including COPD and asthma, may cause airway obstruction and symptoms of breathlessness, cough, and wheeze. Accurate and timely diagnosis of CRDs is critical for improving health outcomes and quality of life. However, patients may not notice symptoms or delay presentation, and current diagnostic approaches such as spirometry are time-consuming, difficult to perform, and require specialist training, potentially leading to misdiagnosis and high costs. Solutions using Smartphone audio and artificial intelligence (AI) are being proposed to fulfil the urgent need for an accurate and scalable solution to be used in the community, directly by patients or in clinical settings with healthcare professionals (HCPs)
Eupnoos is such a tool, which analyses audio biomarkers from forced exhalation into a Smartphone. Preliminary data suggest that Eupnoos can detect airway obstruction, with potential applications across CRD screening, diagnosis and monitoring. Successful future adoption of Eupnoos will depend on sociotechnical factors including usability, integration into existing workflows, and acceptability among end-users. Therefore, this qualitative study aims to explore clinicians’ perspectives on the potential role of a Smartphone audio AI tool for detecting airway obstruction in community care, including challenges and gaps in existing clinical pathways it could overcome.
Methods: Up to twenty HCPs caring for patients with CRDs in primary care will be purposively recruited to participate in semi-structured interviews to explore current diagnostic practices, experiences with digital tools, and attitudes toward AI in supporting CRD care. All interviews will be audio-recorded, transcribed verbatim, and analysed using reflexive thematic analysis. Transcripts will be analysed inductively to identify key themes and contextual factors. Recruitment is beginning shortly and will continue until thematic saturation is reached; preliminary data will be presented at the conference.
Conclusion: There is growing recognition that involving clinicians early in the development of AI tools enhances user-centred design, real-world implementation, and sustainable scale-up. The findings of this study will contribute to a better understanding of the sociotechnical factors influencing how AI-powered tools for CRDs are perceived by primary care clinicians and provide valuable insights for the development and implementation of Eupnoos and similar technologies.
Funding: This project is funded through an NIHR Invention for Innovation (i4i) FAST (Funding At the Speed of Translation) award (NIHR 207332) which provides funding for collaborative research between industry and academia to further health technology development. Eupnoos Ltd are the grant holders and University of Oxford are sub-contracted to undertake the research under a collaboration agreement. Eupnoos Ltd provided input into the overall project aims but have had no role in detailed topic guide development, data collection, analysis or interpretation, which have all been independently conducted by the authors. The views expressed are those of the authors and not necessarily those of the NHS, the NIHR or the Department of Health and Social Care.
Conflicts of interest: ZO, GH, PT, and HA work within, and receive funding from, the National Institute for Health and Care Research (NIHR) HealthTech Research Centre for Community Healthcare at Oxford Health NHS Foundation Trust. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health and Social Care. In this role they conduct studies and evaluations involving respiratory technologies, where these have been provided at reduced price or free-of-charge by the companies, but they have no financial interest in these companies, or direct payments from them.
The conference has been instigated and organised by PCRS. We are grateful to sponsors and exhibitors who have contributed funding towards this event in return for exhibition space. Neither sponsors or exhibitors have had any input into the agenda or the selection of speakers with the exception of any sponsored satellite symposia which are clearly indicated. View the full list of sponsors.
The conference social programme - dinner, drinks and disco - is not covered by sponsorship or exhibition fees.