Comparing Performance of Primary Care Clinicians in the Interpretation of SPIROmetry with or without Artificial Intelligence Decision Support Software (SPIRO-AID): A Protocol for a Randomised Controlled Trial
ABSTRACT
Spirometry, a lung function test, is crucial for diagnosing and monitoring chronic lung disease. However, its interpretation in primary care varies in quality and accuracy. This study aims to assess whether artificial intelligence (AI) decision support software can enhance primary care clinicians’ performance in interpreting spirometry.
METHODS AND ANALYSIS
A randomised controlled trial will involve primary care clinicians in the UK, assessing their interpretation of fifty de-identified patient spirometry sessions with or without AI decision support software. The study will evaluate spirometry interpretation performance, including technical quality assessment, pattern recognition, diagnostic prediction, and clinicians’ confidence. The primary outcome is the proportion of spirometry sessions where the participant’s diagnosis matches the reference diagnosis.
ETHICS AND DISSEMINATION
The study has received approval from the Health Research Authority Wales. Results will be published in peer-reviewed journals, presented at national and international conferences, and shared through various channels.
TRIAL REGISTRATION NUMBER
NCT05933694
