Skip to main content
Fig. 4 | BMC Medical Informatics and Decision Making

Fig. 4

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

Fig. 4

Example of word similarity matrix. This is the similarity matrix of the question text corresponding to the CDE Acute Myeloid Leukemia Classification Type and the CDE Chronic Myelogenous Leukemia Classification Type. Their corresponding question text is “What was the classification of the acute myelogenous leukemia?” and “What was the classification of the chronic myelogenous leukemia?” respectively. After calculating the similarity between every word and generating the word similarity matrix, we build the word similarity list by sorting and obtaining the maximum similarity from the matrix. The maximum similarity is represented by grey background. Note that after obtaining the maximum similarity, the similarities of this column and this row will be ignored, meaning that they will not participate in the sorting any more

Back to article page