Ultrasound-based detection of inflammatory changes for early diagnosis and risk model construction of psoriatic arthritis.

Objectives: PsA is the most prevalent coexisting condition associated with psoriasis. Early-stage PsA patients always present unspecific and subtle clinical manifestations causing delayed diagnosis and leading to unfavourable health outcomes. The application of US enables precise identification of inflammatory changes in musculoskeletal structures. Hence, we constructed US models to aid early diagnosis of PsA.

Methods: This was a cross-sectional study carried out in the Department of Dermatology at West China Hospital (October 2018-April 2021). All participants underwent thorough US examinations. Participants were classified into the under 45 group (18 ≤ age ≤ 45 years) and over 45 (age >45 years) group and then randomly grouped into derivation and test cohort (7:3). Univariable logistic regression, least absolute shrinkage and selection operator, and multivariable logistic regression visualized by nomogram were conducted in order. Receiver operating characteristic (ROC), calibration curve, decision curve analysis (DCA) and clinical impact curve analysis (CICA) were performed for model verification.

Results: A total of 1256 participants were included, with 767 participants in the under 45 group and 489 in the over 45 group. Eleven and 16 independent ultrasonic variables were finally selected to construct the under 45 and over 45 model with the area under the ROC of 0.83 (95% CI 0.78-0.87) and 0.83 (95% CI 0.78-0.88) in derivation cohort, respectively. The DCA and CICA analyses showed good clinical utility of the two models.

Conclusion: The implementation of the US models could streamline the diagnostic process for PsA in psoriasis patients, leading to expedited evaluations while maintaining diagnostic accuracy.