***Recruitment for the study has now been completed, results of the study will be disseminated on this page at a later date***
The purpose of the SPIRO-AID study is to evaluate whether an Artificial Intelligence (AI) decision support software (ArtiQ.Spiro) improves the diagnostic accuracy and quality assessment of spirometry by primary care clinicians.
What is the reason for this study?
Lung disease is the third biggest cause of death in the UK. It is a national health priority in The NHS Long Term Plan for England.
Spirometry is a breathing test that measures how much air a person can breathe in and then empty their lungs. It is important for the diagnosis of common lung conditions. Sometimes it is difficult to perform good quality spirometry in the community and it can be difficult to interpret the results.
ArtiQ.Spiro is an artificial intelligence (AI) software which has been developed to help with the quality assessment and interpretation of spirometry. This software has previously been tested and is currently used successfully in European hospitals. AI uses pattern recognition with the results from the breathing tests to provide a report for your GP.
We want to see whether adding the ArtiQ.Spiro AI software to spirometry improves quality assessment and diagnostic accuracy of spirometry by primary care clinicians.
Who can take part?
We are currently recruiting clinicians working in primary care who refer for spirometry or receive spirometry reports (typically GP, practice nurse). Clinicians need to be able to access spirometry traces on the study platform (Qualtrics) and provide written informed consent via study platform. Clinicians can be based anywhere in the UK.
What the trial involves
If clinicians decide to take part, they will be asked about their job role and any previous experience with spirometry, which will help the study team to randomise participants into each arm of the study. Some participants will be randomised to receive 50 spirometry traces for review in the usual format that they would be received. Some participants will be randomised to receive 50 spirometry traces plus an AI report (ArtiQ.Spiro).
The 50 spirometry traces will be from a de-identified retrospective dataset. Participating clinicians will independently examine the same 50 spirometry records through a bespoke designed trial platform (Qualtrics) and asked to complete specific questions about diagnosis and quality assessment. We anticipate that reviewing the traces will take approximately one hour.
Participants will be offered reimbursement (£150) for their time. Reimbursement details are provided via the Qualtrics study platform after you have completed review of the 50 traces. We may ask you to provide your professional registration number.
Contact us to find out more
Study contact: Ethaar El-Emir, George Edwards, Gillian Doe
Contact email: rbh-tr.spiro-aid@nhs.net
Principal investigator: Professor William Man
Principal investigator email: lungresearch@rbht.nhs.uk
Research Project Information
| Specialty category | Chronic respiratory disease (including COPD, Asthma, Bronchiectasis, Interstitial Lung Disease) |
| Research title | A randomised controlled trial comparing diagnostic performance of primary care clinicians in the interpretation of SPIROmetry with or without Artificial Intelligence Decision support software |
| IRAS number | 323361 |