Clinical Evaluation of a Digital Biomarker for Joint Swelling in Inflammatory Arthritis based on Automated Quantification of Dorsal Finger Fold Patterns

ObjectiveTo clinically evaluate a digital biomarker, the Finger Fold Index (FFI), derived from the ratio of joint diameter to finger fold surface area in hand photographs, for assessing joint swelling in inflammatory arthritis. MethodsSmartphone hand photographs from two routine care cohorts of patients with rheumatoid (RA) and psoriatic arthritis (PsA) were analyzed using a machine learning pipeline for automated detection and processing of proximal interphalangeal (PIP) joints. The FFI was clinically evaluated by correlation with joint swelling scores (0-3) and DAS28-CRP. A healthy cohort was used to establish FFI reference ranges, which were then compared to the arthritis cohorts. ResultsA total of 1275 PIP joint images of 124 arthritis patients and 53 healthy individuals were included. FFI values correlated with swelling scores in the arthritis population with r = 0.443 (95% CI 0.384-0.498). A correlation was observed between the mean FFI and DAS28-CRP dichotomized at 3.2 (r = 0.310, 95% CI 0.123-0.475). FFI values exceeding the healthy reference ranges were associated with swelling (Cramers V = 0.400-0.631; p < 0.001). ConclusionFFI values derived from hand photographs showed a significant association with clinical joint swelling and disease activity in RA and PsA patients. Longitudinal studies are needed to assess sensitivity to change and to establish whether this biomarker can be reliably used for remote patient monitoring.