Systemic sclerosis & Raynaud's
Artificial intelligence-based Raynaud’s quantification index (ARTIX): an objective mobile-based tool for patient-centered assessment of Raynaud’s phenomenon
Authors' conclusion
We developed and validated ARTIX, a novel machine learning-driven method for the objective quantification of RP.
Study context
- Population
- Patients with primary and secondary Raynaud's phenomenon (RP) (91.1% female, mean age 52.2 years, 75.5% secondary RP) and healthy controls (HC)
- Participants
- 45 vs 22
- Comparison
- RP patients vs HC, ARTIX score from mobile phone pictures during standardised cold challenge
- RPn = 45
- HCn = 22reference
- Outcome
- ARTIX ability to assess finger response to standardised cold challenge, compared with thermography
Methodological detailsdevelopment and validation, thermography as reference
- Development and validation
- Thermography as reference
Performance
As reported in the abstract
ARTIX values
- Similarly significant difference observed by thermography
- Good ability to discriminate between RP and HC response to cold challenge
- RP vs HC: P < 0.001
- RP vs HC: P < 0.01 for all
Further findings
ARTIX score by patient characteristics
- Higher in males and in patients taking vasoactive drugs
- Lower in late capillaroscopic pattern, diffuse cutaneous skin subset, or anti-centromere negative
Original publication
Artificial intelligence-based Raynaud’s quantification index (ARTIX): an objective mobile-based tool for patient-centered assessment of Raynaud’s phenomenon. Arthritis Res Ther. Published 3 June 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →