Key points are not available for this paper at this time.
The data in electronic medical records (EMR) are complex in structure. They are independent, yet related to each other. In order to improve information access through the use of EMR, annotating work on these data is necessary. The annotation on metadata, the resource data which contain a meta-model of the database, is the basis of the annotating work if a semi-automated or an automated annotating approach which aims at making the database more accessible is expected. In this study, a method has been proposed to transform the terms which cannot be matched directly by changing them literally but maintaining their semantics, and then annotating them indirectly. After the transforming work, a refinement method which is reducible to phrase sense disambiguation (PSD) is employed to ensure accuracy. A pilot study on a hospital database has been conducted to test the accuracy and effectiveness of the proposed method.
Xu et al. (Wed,) studied this question.