Fig. 7From: Using an artificial neural network to map cancer common data elements to the biomedical research integrated domain group model in a semi-automated mannerBest match rates per testing set. Bars refer to the best matching rate for testing sets with different degrees of semantic similarity compared to the training set: similar, moderately different, and different. The blue bars represent the situation in which the testing set contains only CDEs mapped to BRIDG classes with sufficient training data. The orange bars represent the situation that the testing set contains all CDEsBack to article page