Automatic de-identification of electronic medical records using token-level and character-level conditional random fields

作者：Liu, Zengjian; Chen, Yangxin; Tang, Buzhou^*; Wang, Xiaolong; Chen, Qingcai; Li, Haodi; Wang, Jingfeng; Deng, Qiwen; Zhu, Suisong

来源：Journal of Biomedical Informatics, 2015, 58: S47-S52.

DOI：10.1016/j.jbi.2015.06.009

• De-identification
• Protected health information
• Electronic medical records i2b2
• Natural language processing
• Hybrid method

De-identification, identifying and removing all protected health information (PHI) present in clinical data including electronic medical records (EMRs), is a critical step in making clinical data publicly available. The 2014 i2b2 (Center of Informatics for Integrating Biology and Bedside) clinical natural language processing (NLP) challenge sets up a track for de-identification (track 1). In this study, we propose a hybrid system based on both machine learning and rule approaches for the de-identification track. In our system, PHI instances are first identified by two (token-level and character-level) conditional random fields (CRFs) and a rule-based classifier, and then are merged by some rules. Experiments conducted on the i2b2 corpus show that our system submitted for the challenge achieves the highest micro F-scores of 94.64%, 91.24% and 91.63% under the "token", "strict" and "relaxed" criteria respectively, which is among top-ranked systems of the 2014 i2b2 challenge. After integrating some refined localization dictionaries, our system is further improved with F-scores of 94.83%, 91.57% and 91.95% under the "token", "strict" and "relaxed" criteria respectively.

• 出版日期2015-12
• 单位哈尔滨工业大学; 深圳市南山区人民医院; 中山大学