The accurate biomarker for diagnosing psoriasis vulgaris has always remained a challenge as no reliable disease-specific biomarkers have been identified yet.

Several different chronic inflammatory skin diseases represent almost similar clinical and dermoscopy features to psoriasis vulgaris that can make the accurate diagnosis very difficult. A literature-based and data-driven selection of biomarker was performed to select candidates for a multicomponent biomarker for psoriasis vulgaris. Support vector machine-based classification models were also trained by using gene expression data from the local neighborhood enrolled patients and validated on seven public datasets that comprised gene expression data of other inflammatory skin diseases besides psoriasis vulgaris.

The resultant accuracy of the best classification model based on the expression levels of 4 genes (IL36G, CCL27, NOS2 and C10orf99) was 96.4%. This diagnostic model surpassed the classification based on other gene markers combinations that were more affected by variability in gene expression profiles in different datasets and patient groups. This method has the ability to fill the void of clinically relevant diagnostic biomarkers for psoriasis vulgaris and other inflammatory skin diseases.

Source: Reimann E, Lättekivi F, Keermann M, et al. Multicomponent Biomarker Approach Improves the Accuracy of Diagnostic Biomarkers for Psoriasis Vulgaris. Acta Derm Venereol. 2019;99(13):1258-1265. doi:10.2340/00015555-3337