Type 2 diabetes mellitus (T2DM) is a multifactorial disorder that leads to alterations in gene regulation. ncRNAs have the characteristics of tissue specificity, disease specificity, timing specificity, high stability and post transcriptional regulation effect. These preconditions are more conducive to promote ncRNA to become a new biomarker for clinical diagnosis. Our study aims to explore the relationship between circRNA, lncRNA, miRNA and T2DM, and to evaluate their diagnostic value for T2DM. A total of 101 pairs of T2DM and controls were conducted in the study. QRT-PCR was used to study the differential expression of circRNAs, miRNAs and lncRNAs. ROC curve was used to estimate their diagnostic value in T2DM. Compared with healthy controls, the expression levels of hsa_circ_0071106, hsa_circ_0000284, hsa_circ_0071271, hsa-miR-29a-5p, hsa-miR-3690, hsa-miR-607, lncRNA MEG3 and lncRNA TUG1were higher in T2DM (all P < 0.05). The AUCs of hsa_circ_0071106, hsa-miR-607 and lncRNA TUG1 for diagnosis of T2DM were 0.563,0.645 and 0.642, respectively. The combined AUC of hsa-miR-607, lncRNA TUG1 and hsa_circ_0071106 was 0.798 ([0.720~0.875], P < 0.001). Moreover, the sensitivity of combined diagnosis was 75.2% and the specificity was 100.0%. The levels of lncRNA TUG1, hsa-miR-607 and hsa_circ_0071106 in peripheral blood have potential clinical diagnostic value for T2DM.

The classical belief rule-based (BRB) systems are usually constructed by arranging and combining referential values of antecedent attributes or by setting special fixed values, which can lead to overly large size of BRB systems in complex problems. This paper combines the decision tree classification method to analyze the information of data and extract the rules. Based on this, a new rule representation method with referential interval is proposed and the rule base is constructed according to the support degree and belief degree of the data. In the newly proposed method, the introduction of decision tree ensures that the size of the rule base is reasonable. Moreover, the rule parameters trained by the differential evolution (DE) algorithm are optimized and adjusted to further improve the system performance. The experiments are conducted on several commonly used public classification datasets. And the proposed algorithm can achieve the best accuracy results compared with classical classification methods and the existing classification methods of BRB systems on average. The experimental results validate the reasonableness and effectiveness of the BRB construction method proposed in this paper.

No abstract