Prof. Dan Xie
Hubei University of Chinese Medicine, China
Speech Title: A Method of Text Information Normalization of Electronic Medical Records of Traditional Chinese Medicine
The electronic medical record (EMR) of Traditional Chinese Medicine (TCM) contains a wealth of content, which is an important reference point for TCM diagnosis. As this information is often conveyed in the form of natural language, there are many terminology and expression irregularities that pose a great obstacle to the in-depth application of EMR information at a later stage.In this paper, we propose a method to normalize the textual information of EMR of TCM and select the text of medical history with a strong narrative such as the history of present illness and past medical history, as well as the text of symptoms such as chief complaints and subcutaneous symptoms as the main research object. The text is then processed separately according to the type of text. For symptom texts, named entity recognition technology is directly applied to extract symptom entities directly; For the medical history text, the type of treatment event is first identified by analysing the original text of the history of present illness and past medical history, then event extraction is carried out to classify the treatment event according to the trigger word, then named entity recognition techniques are applied to extract nine types of entities such as symptoms and diseases, and finally these nine types of entities are stored in the database. Using this method, experiments are conducted on the EMR of the orthopedic injury department of a hospital, in which the recognition rate of the symptom entity in the symptom text reaches 92.28%, and the recognition rate of entities such as symptoms and diseases in the medical history text reaches 89.86%. The validity of this method is verified. This method normalizes the natural language writing part of the EMR and stores it in a structured way, which is convenient for the subsequent data analysis and mining, and lays a solid foundation for the intellectualization of TCM.
Dan Xie is a professor in the college of Information Engineering, Hubei University of Chinese Medicine in Wuhan, China. She received the PhD degree from the State Key Laboratory of Software Engineering of Wuhan University in 2008. Her current research interests include medical software development, machine learning, natural language processing in electronic medical records. She was a visiting scholar at the University of Tokyo in Japan and a postdoctoral fellow in the Department of Biostatistics at the Houston Health and Medical Center of the University of Texas in the United States. She is currently a member of the IEEE and a senior member of CCF, and the associate editor of the International Journal of Artificial Intelligence and Medical Sciences. She mainly participated projects in the National Institutes of Health of the United States, the Chinese medicine modernization project of the Ministry of science and technology of China, and published more than 60 papers. She has won the second prize of scientific and technological progress in Hubei Province and the third prize of teaching achievements in Hubei Province.