Abstract: ObjectiveTo analyze expression levels of differentially expressed miRNAs in sera of patients with occupational medicamentosa-like dermatitis induced by trichloroethylene (OMLDT) and establish diagnostic model for OMLDT using support vector machines (SVMs).MethodsSerum samples of patients with OMLDT and contacts were collected from January 1, 2009 to December 30, 2014. miRNAs were extracted and analyzed by microarrays. miR-21 and miR-193b were verified using qRT-PCR. From all the samples, 60% was randomly selected and used as a test set to establish the OMLDT diagnostic model by SVM algorithm, and the remaining 40% was used as verification set to evaluate the specificity and sensitivity of the model. ResultsThere were 34 patients in the OMLDT case group, including 23 males and 11 females, with an average age of (27.29 ± 10.43) years. There were 34 patients in the control group, including 26 males and 8 females, with an average age of (25.00 ± 6.14) years. There was no significant difference in gender composition or mean age between the two groups (both P> 0.05). The expression levels of miR-21 and miR-193b in the OMLDT case group were higher than those in the control group (both P< 0.01). The recognition rate of cross validation for the diagnostic model was 95%. The sensitivity, specificity and accuracy of SVM diagnostic model were 81.82%, 100.00%, and 92.86% respectively. ConclusionmiR-21 and miR-193b could be candidate serum biomarkers for OMLDT. The OMLDT diagnostic model based on SVM algorithm has a good fitting effect and can provide valuable clues for the early diagnosis of OMLDT.