Assessment of four screening tools and retrieval of key questions to detect undiagnosed psoriatic arthritis in Chinese patients with psoriasis: A multicenter study. Issue 6 (22nd March 2022)

• Record Type: Journal Article
• Authors: Cui, Ran; Chen, Miao; Li, Xia; Wang, Qian; Tong, Qiang; Zhang, Hua; Chen, Zhiyong; Tao, Yi‐Li; Bi, Xin‐Ling; Deng, Hui; Yuan, Ding‐Fen; He, Dong‐Yi; Ding, Yang‐Feng; Dai, Sheng‐Ming
• Is Part Of: Journal of dermatology. Volume 49:Issue 6(2022)
• Page Start: 615
• Page End: 623
• Publication Date: 2022-03-22
• Subjects: least absolute shrinkage and selection operator -- nomogram -- psoriasis -- psoriatic arthritis -- screening tools -- sensitivity -- specificity; Dermatology -- Periodicals; Dermatology -- Japan -- Periodicals; Skin -- Diseases -- Periodicals; 616.5005
• DOI: 10.1111/1346-8138.16355
• Languages: English
• ISSNs: 0385-2407

Abstract

Abstract: Several screening tools have been developed to facilitate early diagnosis of psoriatic arthritis (PsA); however, their performance varied greatly across different studies. In this study, we validated and compared the performance of four screening tools in detecting undiagnosed PsA Chinese patients with psoriasis, and determined the key questions and their weights. The four screening tools were the Early Arthritis for Psoriatic Patients (EARP) questionnaire, Psoriatic Arthritis Screening and Evaluation (PASE) questionnaire, Psoriasis and Arthritis Screening Questionnaire (PASQ), and Psoriasis Epidemiology Screening Tool (PEST). The receiver–operator curve (ROC) with area under curve (AUC) was used to determine sensitivity, specificity, and accuracy. Least absolute shrinkage and selection operator and logistic regression were utilized to retrieve key questions, and a nomogram was utilized to visualize their weights. Of 482 psoriasis patients from dermatology clinics, 77 were newly diagnosed with PsA. Another 68 patients with newly diagnosed PsA from rheumatology clinics were incorporated in the analysis. ROC analysis indicated that the optimal cut‐off values for EARP, PASE, PASQ, and PEST were 3, 40, 7, and 3, with corresponding sensitivities of 91.4%, 88.6%, 86.2%, and 88.5%, and specificities of 88.6%, 75.2%, 80.2%, and 83.6%, respectively. The AUC of EARP (0.925) was higher than those of PASE (0.885), PASQ (0.905), and PEST (0.827). However, none of them were sufficiently sensitive to identify pure axial PsA (sensitivities of EARP, PASQ, and PASE were 25.0%, 36.8%, and 42.1%, respectively). Twelve key questions were retrieved from these four tools to establish a nomogram with a high discrimination (C‐index = 0.993) and a good calibration (mean absolute error = 0.014). In conclusion, to screen undiagnosed PsA, EARP has slightly better balanced sensitivity and specificity, and higher accuracy. The retrieval of key questions and nomogram signify the necessity of attributing different scores to differently weighted questions when developing a new screening tool to make it function more efficiently.