We computed the proportion of classifications in the MR that received concordant classifications by TMA and computed Kappa statistics for each of the four ER/PR subtypes (similar to the analysis in the GEM dataset).
The relationship between the SI index and the proportion of classifications of the Eff stimulus across the population of cells (Fig. 3A) shows a robust correlation between the SI of individual neurons and the classification of the AS image (r = 0.45, P = 0.0001, n = 67).
This therefore generated k sets of SVM training and test sets that produced overall classification accuracy from the proportion of correct classification "guesses" across all k folds of the cross-validation.
The distribution patterns of GeneChip 500K and Hap550 are very similar (Figure 3): similar high proportion of intron classification and similar distribution in other classifications.
The accuracy of the classification obtained was evaluated by ten-fold cross validation [ 47], using the following parameters: proportion of correct classification (PCC) and the area under the curve (AUC).
The true positive rate (y-axis) gives the proportion of correct classification of two syllables belonging to the same class (true positive).
In computing the proportion of incorrect classification by the ensemble, one should therefore divide not by as in (12), but rather by minus the number of times when the out-of-bag ensembles are empty, which leads to the following modified out-of-bag estimator: (13).
The unbiased diagnostic accuracy (proportion of correct classification) was estimated to 91.24 %, against 92.65 % initially computed on the original dataset.
The proportion of correct classification (0.926), the kappa index (0.853), and the AUC (0.974) confirm the good performance of the model.
