计算普通的 average/macro AUC 即可。多分类问题下,每个正类都画一条 ROC 曲线,然后选择不同的方法(macro / micro / weighted),得到最终多分类的 ROC 曲线,从而计算 AUC。
The ROC curve negative data was created in the same way as the negative dataset for the 100nt sequence test. Accuracy versus Sequence Length To investigate whether there was any correlation between sequence length and accuracy a series of sequence datasets were generated ranging in length from 100...
Analysis of the ROC curve showed enhanced predictive ability; the AUC was measured at 0.933 as opposed to 0.789. Discriminating patients with GO is facilitated by a statistically significant biomarker cluster, containing three blood metabolites. The pathogenesis, diagnostic criteria, and potential ...
ROC curves to estimate model performance The models with the highest accuracy score for DT and NB were applied to human pre-miRNAs from miRBase and pseudo negative data set to estimate true and false positive rates and to construct ROC curves. Along with the study-based models, AverageDTand ...
The mean AUC for the averaged ROC curves are presented. The data are presented as the AUC and 95% CI and corresponding sensitivity for a range of specificities. The AUC is 0.96 (95% CI: 0.884–1.00; p < 0.001). Abbreviations: AUC, area under the curve; CI, confidence interval; ...
ROC curve analyses revealed that miR-31, miR-29a and miR-148a all had significant potential diagnostic value for critically ill patients infected with H1N1 influenza virus, which yielded AUC of 0.9510, 0.8951 and 0.8811, respectively. In addition, we found that a number of genes and signaling ...
7 b and d. most of softmax values of the targeted mirnas are greater than 0.9 and the area under the roc curve for one-hot encoding matrix is very close to 1. by using one-hot encoding matrix, we can find an appropriate probability threshold to reject a majority of the negative ...
Another key consideration for the fair comparison of prediction performance is the choice of the approach used to evaluate performance. The use of standard methods for evaluating a binary classifier, such as a receiver operating characteristic (ROC) curve, is not appropriate for several reasons. Firs...
We tested BRWHNHA on 22 diseases based on five-fold cross-validation and achieves reliable performance with average AUC of 0.857, which an area under the ROC curve ranging from 0.807 to 0.924. As a result, BRWHNHA significantly improves the performance of inferring potential miRNA-disease ...
Moreover, we observe that the weighted rank average can obtain better performance than the not weighted rank average (p-value = 1.27E-2 for AUC scores of ROC curve, p-value = 2.46E-2 for AUC scores of PR curve). These results show that the ensemble-based method can ...