A Nomogram for the Diagnosis of Plaque Psoriasis Using Histopathological Characteristics

BACKGROUND AND OBJECTIVES: Diagnostic uncertainty of plaque psoriasis (PP) persists when dermatopathologists encounter clinicopathologically ambiguous cases. We aim to develop a nomogram based on histopathological features to improve the accuracy of the diagnosis of PP. METHOD: A total of 192 samples from 186 patients with PP and 170 samples from 166 control patients were used in the derivation cohort. Their histopathological features were described, and their sensitivity and specificity in diagnosing PP were calculated. Histopathological variables of the study cohort selected by least absolute shrinkage and selection operator regression were compared by multivariate logistic regression analysis. The Akaike information criterion was used to select variables for the nomogram. In total, 170 samples (75 PP and 95 controls) were included in the validation of the diagnostic model. The performance of the nomogram was evaluated regarding its discrimination, calibration, and clinical utility. RESULT: Nine variables were selected for a diagnostic nomogram of PP. The area under the receiver operating characteristic curve of the nomogram was 0.983 [95% confidence interval (CI), 0.971-0.995] in the derivation cohort and 0.971 (95% CI, 0.951-0.992) in the validation cohort, respectively. The calibration plot showed strong agreement between the prediction of the nomogram and the actual diagnosed PP. The decision curve analysis revealed that the nomogram had good clinical utility. CONCLUSION: The sensitivity and specificity of histopathological features were investigated and a well-performing nomogram was developed to aid diagnosing PP. However, broader application awaits further fine tuning of the model.