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

16 May 2023

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. 

Resource information

Respiratory topics
  • Spirometry
Type of resource
Abstract
Conference
Munich 2023
Author(s)
Gillian Doe 1, Steph Taylor 2, Marko Topalovic 3, Richard Russell 4, Rachael Evans 1, Julie Maes 3, Karolien Van Orshoven 3, Anthony Sunjaya 5, David Scott 6, Toby Prevost 7, Ethaar El-Emir 8, Jennifer Harvey 8, Nick Hopkinson 9, Samantha Kon 8, Suhani Patel 8,9, Ian Jarrold 11, Nannette Spain 12, William Man 8,9,10, Ann Hutchinson 13 1 Department of Respiratory Sciences, University of Leicester, Leicester, United Kingdom, 2 Wolfson Institution of Population Health, Queen Mary University, London, United Kingdom, 3 ARTIQ, Leuven, Belgium, 4 Nuffield Department of Medicine, University of Oxford, Oxford, United Kingdom, 5 The George Institute for Global Health, UNSW , Sydney, Australia, 6 Southampton Health Technology Assessments Centre, University of Southampton, Southampton, United Kingdom, 7 Kings College London, London, United Kingdom, 8 Harefield Respiratory Research Group, Guy’s and St Thomas’ NHS Foundation Trust, London, United Kingdom, 9 National Heart & Lung Institute, Imperial College London, London, United Kingdom, 10 Faculty of Life Sciences and Medicine, King’s College London, London, United Kingdom, 11 Asthma + Lung UK, London, United Kingdom, 12 Patient and public involvement representative, London, United Kingdom, 13 Wolfson Palliative Care Research Centre, Hull and York Medical School, University of Hull, Hull, United Kingdom