ArtiQ.Spiro AI spirometry
The NHS Long Term Plan aims for earlier and more accurate diagnosis of lung conditions. An important diagnostic tool for lung conditions is spirometry (a forceful blowing test). Previous research has shown that spirometry performed in general practice is of poor quality, in particular the interpretation of tests.
In addition to this, especially in Primary care, there are challenges to attract health care professionals to train and achieve quality assured accreditation for performance and interpretation of spirometry. This is resulting in a workforce crisis in this space and therefore significantly impacts service provision for patients, which inevitably delays lung condition diagnoses such as Asthma or COPD and as such, delays access to treatment/management. Spirometry in Primary care is usually predominantly performed by HCAs/ Nurses and interpreted by Nurses or GPs.
Two GP practices (2 Clinicians with Spirometry accreditation) took part in a real-world evaluation case study to evaluate the experience and efficiencies that this solution may bring to the NHS, with the vision that if clinicians with experience in Spirometry have confidence the validated software (link to validations studies), this may provide an opportunity to consider utilising and training a different (lower band) workforce to deliver the performance of the test, with the Nurse freed up to deliver other important duties such as long term condition management. With the expectation that supporting primary care spirometry pathways with AI software (ArtiQ.Spiro) will improve the quality of spirometry and accuracy of diagnostic reports, improve patient well-being and experience, reduce dependency on secondary/tertiary care support, improve operational efficiency, address workforce issues and bring cost-savings to the NHS.
Contact Details
- Claire Adams - Programme Manager
- HI NENC
- [email protected]
Project Dates
Project Start 03/07/2023
Project End 29/02/2024
Programmes
Share
The software is helpful in supporting decision making and potentially confirming clinical decisions. It can also be helpful in alerting the clinician to other diagnoses that may not have been considered.
However, as it’s a software tool without the full patient history and clinical context and presentations I feel it's benefit is mainly in supporting clinicians in confirming those clear-cut cases that fit nicely within the diagnostic parameters rather than try to support complex case management or clinical uncertainties
Further work may be required to clarify the role and function of the Software tools within agreed clinical pathway which may help with clinician confidence and time in interpreting Spirometry.
The AI innovation is decision support software (ArtiQ.Spiro) which combines two sub-components – one focusing on quality assessment, and one on spirometry interpretation. The first element will support staff in evaluating immediately if the spirometry is of good enough quality for clinical interpretation. This timely support allows the user to immediately add one or multiple trials to the spirometry session when the patient is still present instead of sending of bad quality data onto the GP. Immediately after the spirometry session is performed the interpretation element will provide a description of the results according to the latest international guidelines (saving staff time and boosting consistency). In addition, the interpretation support also uses artificial intelligence to calculate disease probabilities and options for next steps to support the diagnostic process.
Anonymous data is sent from the spirometer software to the ArtiQ cloud and a report is send back in a matter of seconds.
The software is compatible with two commercially available spirometry software (Spiroconnect from MedChip, distributed by Numed in the UK and Spirotract from Vitalograph). No additional local installation is required.
Two ARTP-accredited healthcare professionals, a general practitioner and a nurse, used ArtiQ.Spiro over 5 months in the NENC areas. They evaluated spirometry quality and made a diagnostic interpretation first without the ArtiQ.Spiro software and then with AI support. For each, they recorded (i) the time it took to interpret the test, (ii) how confident they were in their interpretation.
The project has been extended and is ongoing with an evaluation on use of the ArtiQ.Spiro in a drug and alcohol service in Hartlepool, where patients have a higher prevalence of respiratory disease, yet undiagnosed, due to poor engagement with their own GP. Health care assistants in the service will be utilising the innovation and reporting will be sent to the patient’s own GP for consideration of a diagnosis.
Results: 51 spirometry sessions were collected.
The average time to evaluate the spirometry results decreased by using ArtiQ.Spiro from 10.6 ± 4.1 min. to 5.6 ± 5.6 min (p<0.001). The confidence level in the interpretation did not change, with a median of 4 on a 5-point Likert scale without and with AI support. The AI matched the quality assessment in 94% of the cases and matched the diagnosis in 86% of the cases (4% missing data). The final diagnosis needed further clinical consideration.
This study shows that AI has the potential to reduce the time for interpretation of spirometry traces and support healthcare professionals in the execution and interpretation of spirometry. This could improve access to spirometry services.
Patient – more accurate diagnosis resulting in reduced risk of harm and less recalls
Staff – increased confidence in diagnosing due to software reporting on the quality and suggested diagnosis
Cost – opportunity to utilise a lower band of workforce to conduct spirometry and ensure an interpreted report is made available to GPs. Cost savings in this small study demonstrated a saving of £10-15 per appointment if a lower band of staff were trained and this technology was utilised.
Application of this innovation in primary care may result in patients having a more accurate diagnosis in a shorter space of time, reducing the need for multiple visits to the GP surgery and therefore reducing travel.
Claire Adams, HI NENC and ICB NENC championed the project through the internal HI NENC triage process to help generate some evidence that this could help address an unmet need in spirometry.
She was involved in all aspects including evaluation set up, finding and bringing the team together, supporting the project as well as all write ups and coordination.
A large validation study SpiroAID is taking place in London with results available in Autumn 2024.
It’s a great tool to use in addition to interpreting spirometry skills, it can help us 'think outside the box' and consider alternative diagnosis, however if the user is not confident in their diagnostic skills, and they use only the AI to interpret, asthma diagnosis is going to go through the roof….I also found that checking the quality of blows on the AI really useful, as previously some I would have put through (possibly with a very slight cough), have not passed the AI quality control – I have found this extremely beneficial in improving the quality of the spirometry used to interpret.