The landscape of spirometry services in England and the potential for Artificial Intelligence decision support software in primary care; a qualitative study.

Introduction: Spirometry services to diagnose and monitor lung disease in primary care were severely affected by the pandemic. Services are slowly restarting in England, however, evidence regarding best practice is limited. We aimed to explore perspectives on spirometry provision in primary care, and the potential for Artificial Intelligence (AI) decision support software to aid quality and interpretation in future pathways. Methods: Semi-structured interviews were conducted with key stakeholders in spirometry services across England. Participants were recruited by snowball sampling. Interviews explored the pre-pandemic delivery of spirometry, restarting of services and perceptions of the role of AI. Transcripts were analysed using thematic analysis supported by NVivo software. Results: 28 participants (mean [SD], 21.6 [9.4, range 3-40] years’ clinical experience) were interviewed between April and June 2022. Participants included clinicians (n=25) and commissioners (n=3); eight held regional and/or national respiratory network advisory roles. Four themes were identified (Figure 1): 1) Historical challenges in spirometry provision; 2) Inequity in post-pandemic spirometry provision and challenges to restarting spirometry in primary care; 3) Future delivery closer to patients’ homes by appropriately trained staff; 4) The potential for AI to have supportive roles in spirometry. There was an overall sense of urgent need to improve services. Regardless of the details of a spirometry service model, all participants expressed the importance of spirometry being accessible for patients. Despite some hesitancy around AI, Family doctors in particular were keen to explore its potential. Discussion: Stakeholders highlighted historic challenges and the damaging effects of the pandemic contributing to inequity in provision of spirometry nationally. Overall stakeholders were positive about the potential of AI to support clinicians in quality assessment and interpretation of spirometry. However, it was evident that validation of the software must be sufficiently robust for clinicians and healthcare commissioners to have trust in the process.