Thyroid carcinoma (TC) is the most common malignancy of the endocrine system, and papillary thyroid carcinoma (PTC) accounts for the largest proportion of cases with TC. Although histology is considered the gold standard in the diagnosis of PTC, the sensitivity and specificity of this method is low. Therefore, developing novel diagnostic and prognostic biomarkers for PTC is essential. MicroRNAs (miRNAs or miRs) and their target RNAs play critical roles in tumorigenesis and tumor progression. Thus, the characteristic miRNA and mRNA expression profiles may function as diagnostic biomarkers for tumors, making it possible to predict the tumor stage and the prognosis of patients. In the present study, we detected miRNAs and mRNAs which can function as novel biomarkers for the diagnosis of PTC. The sensitivity of the diagnostic tests was evaluated by receiver operating characteristic curve analysis. Pearson's correlation analysis was used to determine the correlation between mRNAs and miRNAs, and cancer types. We found that the area under the curve (AUC) values of 8 miRNAs (miR-106a, miR-15a, miR-30a, miR-30b, miR-20a, miR-20b, miR-30d and miR-30e) and 8 mRNAs [axis inhibition protein 2 (AXIN2), integrin, alpha 3 (antigen CD49C, alpha 3 subunit of VLA-3 receptor) (ITGA3), tumor protein p53 inducible nuclear protein (TP53INP)1, TP53INP2, B-cell CLL/lymphoma 2 (BCL2), phosphatase and tensin homolog (PTEN), FOS and K(lysine) acetyltransferase 2B (KAT2B)] were >0.90. The combination of miR-15a and AXIN2 significantly improved the diagnostic accuracy. Therefore, our data indicate that the differential expression of miRNAs combined with that of their target mRNAs may serve as a powerful biomarker for distinguishing PTC from benign tissues.