What happened
The National Institute for Health and Care Excellence (NICE) published an early-use assessment of software that applies algorithms to spirometry on 2 April 2026. Clario's ArtiQ.Spiro checks the quality of a spirometry test, recognizes the pattern and suggests a diagnosis. NICE classes its algorithms as AI and rules-based. The strongest evidence came from SPIRO-AID, a UK randomized trial. In it, 133 primary care professionals reviewed 50 past spirometry records with or without the software. The external assessment group calculated sensitivity and specificity from trial data that the authors supplied in confidence. The committee found that sensitivity for asthma and COPD was higher with ArtiQ.Spiro and that specificity was similar in both arms. NICE allowed its use in the NHS for a three-year period of evidence generation, with a clinician making the final diagnosis. The committee noted that the trial sample was small and that few of its records showed normal spirometry. In a separate UK validation study, the software's sensitivity for normal cases was 33.3%. Its effect on long-term outcomes is unknown.
Sources
-
Assessment report, by authors with no tie to the system.
The evidence for ArtiQ.Spiro is stronger than that for the other technologies included in this assessment. This evidence includes a UK-based randomised controlled trial using real-world evidence from primary care reviewed by primary care healthcare professionals. Most of the evidence suggests that using ArtiQ.Spiro could lead to better outcomes for people needing diagnostic spirometry and provide benefits to the NHS.
-
Assessment report, by authors with no tie to the system.
It included 133 primary care healthcare professionals (who refer for, perform, or interpret spirometry) who were randomised to review 50 retrospective spirometry records with or without ArtiQ.Spiro.
Details
AI system
- Workflow
-
Primary care professionals reviewed 50 past spirometry records each, with or without the software. The software checked test quality, recognized the spirometry pattern and suggested a diagnosis.
Follow-up
- Conditions for replication
-
A healthcare professional makes the final diagnosis after a clinical assessment. Accuracy holds in people whose rate of disease matches those seen in primary care and community diagnostic centers.
Entry details
- Sector
-
Healthcare.
- Purpose
-
Clario built ArtiQ.Spiro to check the quality of spirometry tests, interpret the results and suggest a diagnosis for lung conditions such as asthma and COPD.
Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.
Cite this record
Peter H. Vartanian. (2026). ArtiQ.Spiro raised sensitivity for asthma and COPD in a UK trial (AIBD-0741). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0741.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)