Preprocessing for Extracting Information from Medical Record to Add XML Tags

The purpose of this paper is to propose preprocessing procedures from handwritten medical records, of which words are omitted, to translate contents of the records into formatted data such as XML data. From the viewpoint, we performed an experiment, which physicians freely described patients' problems to reveal the characteristics in the handwritten record. As a result, we obtained five characteristics. Based on these characteristics, we considered eight preprocessing steps. Then, we confirmed that our proposed preprocessing worked well from a computational experiment although not all sub-procedures are effective due to lack of a large amount of corpora.