Capi-score: a quantitative algorithm for identifying disease patterns in nailfold videocapillaroscopy.

Abstract

The European Alliance of Associations for Rheumatology (EULAR) supports the use of nailfold videocapillaroscopy (NVC) to identify disease patterns (DPs) associated with systemic sclerosis (SSc) and Raynaud's phenomenon (RP). Recently, EULAR proposed an easy-to-manage procedure, a so-called Fast Track algorithm, to differentiate SSc from non-SSc patterns in NVC specimens. However, subjectivity among capillaroscopists remains a limitation. Our aim was to perform a software-based analysis of NVC peculiarities in a cohort of samples from SSc and RP patients and, subsequently, build a Fast Track-inspired algorithm to identify DPs without the constraint of interobserver variability. NVCs were examined by 9 capillaroscopists. Those NVCs whose DPs were consensually agreed (≥2 out of 3 interobservers) were subsequently analysed with an in-house developed software. Each variable's results were grouped according to the consensually agreed DPs in order to identify useful hallmarks to categorise them. Eight-hundred and fifty-one NVCs (21 957 images) whose DPs had been consensually agreed were software-analysed. Appropriate cut-offs set in capillary density and percentage of abnormal and giant capillaries, tortuosities and hemorrhages allowed DP categorization and the development of the CAPI-Score algorithm. This consisted of 4 rules: Rule 1, SSc vs non-SSc, accuracy 0.88; Rules 2 and 3, SSc-early vs SSc-active vs SSc-late, accuracy 0.82; Rule 4, non-SSc normal vs non-SSc non-specific, accuracy 0.73. Accuracy improved when the analysis was limited to NVCs whose DPs had achieved full consensus among interobservers. The CAPI-Score algorithm may become a useful tool to assign DPs by overcoming the limitations of subjectivity.