Skip to main content

Table 2 Algorithm parameters

From: Using an artificial neural network to map cancer common data elements to the biomedical research integrated domain group model in a semi-automated manner

ParameterDescriptionValues TestedOptimal Values
Training ratioRatio of training to verification data75% training and 25% verification
90% training and 10% verification
75% training and 25% verification
Training CDEs per BRIDG classDetermines the training list4–108
Similarity thresholdDetermines the threshold for considering two words to be similar0.6–1.00.7 or 0.8