A quantum-based oversampling method for classification of highly imbalanced and overlapped data.

Data imbalance is a challenging problem in classification tasks, and when combined with class overlapping, it further deteriorates classification performance. However, existing studies have rarely addressed both issues simultaneously. In this article, we propose a novel quantum-based oversampling method (QOSM) to effectively tackle data imbalance and class overlapping, thereby improving classification performance. QOSM utilizes the quantum potential theory to calculate the potential energy of each sample and selects the sample with the lowest potential as the center of each cover generated by a constructive covering algorithm. This approach optimizes cover center selection and better captures the distribution of the original samples, particularly in the overlapping regions. In addition, oversampling is performed on the samples of the minority class covers to mitigate the imbalance ratio (IR). We evaluated QOSM using three traditional classifiers (support vector machines [SVM], k-nearest neighbor [KNN], and naive Bayes [NB] classifier) on 10 publicly available KEEL data sets characterized by high IRs and varying degrees of overlap. Experimental results demonstrate that QOSM significantly improves classification accuracy compared to approaches that do not address class imbalance and overlapping. Moreover, QOSM consistently outperforms existing oversampling methods tested. With its compatibility with different classifiers, QOSM exhibits promising potential to improve the classification performance of highly imbalanced and overlapped data.

Promoter methylation of p16 and RASSF1A genes may contribute to the risk of papillary thyroid cancer: A meta-analysis.

The aim of the present meta-analysis was to investigate the correlation of promoter methylation of the p16 and Ras association domain family 1 isoform A (RASSF1A) genes with the risk of the development of papillary thyroid cancer (PTC). A number of electronic databases were searched without language restrictions as follows: Medline (1966-2013), the Cochrane Library database (Issue 12, 2013), Embase (1980-2013), CINAHL (1982-2013), Web of Science (1945-2013) and the Chinese Biomedical Database (CBM; 1982-2013). A meta-analysis was performed with the use of Stata statistical software. The odds ratios (ORs), ratio differences (RDs) and 95% confidence intervals (95% CIs) were calculated. In the present meta-analysis, eleven clinical cohort studies with a total of 734 patients with PTC were included. The results of the current meta-analysis indicated that the frequency of promoter methylation of p16 in cancer tissues was significantly higher compared with that in normal, adjacent and benign tissues (cancer tissues vs. normal tissues: OR=7.14; 95% CI, 3.30-15.47; P<0.001; cancer tissues vs. adjacent tissues: OR=11.90; 95% CI, 5.55-25.52; P<0.001; cancer tissues vs. benign tissues: OR=2.25; 95% CI, 1.67-3.03; P<0.001, respectively). The results also suggest that RASSF1A promoter methylation may be implicated in the pathogenesis of PTC (cancer tissues vs. normal tissues: RD=0.53; 95% CI, 0.42-0.64; P<0.001; cancer tissues vs. adjacent tissues: RD=0.39; 95% CI, 0.31-0.48; P<0.001; cancer tissues vs. benign tissues: RD=0.39; 95% CI, 0.31-0.47; P<0.001; respectively). Thus, the present meta-analysis indicates that aberrant promoter methylation of p16 and RASSF1A genes may play a crucial role in the pathogenesis of PTC.