Idioma:

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

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

Journal of biomedical informatics, 2015-12, Vol.58 (Suppl), p.S47-S52 [Periódico revisado por pares]

United States: Elsevier Inc

Texto completo disponível

Citações Citado por

Enviar para

Título:
Automatic de-identification of electronic medical records using token-level and character-level conditional random fields
Autor: Liu, Zengjian ; Chen, Yangxin ; Tang, Buzhou ; Wang, Xiaolong ; Chen, Qingcai ; Li, Haodi ; Wang, Jingfeng ; Deng, Qiwen ; Zhu, Suisong
Assuntos: Biology ; China ; Cohort Studies ; Computational linguistics ; Computer Security ; Confidentiality ; Criteria ; Data Interpretation, Statistical ; Data Mining - methods ; De-identification ; Dictionaries ; Electronic health records ; Electronic Health Records - organization & administration ; Electronic medical records ; Electronic records ; Fields (mathematics) ; Hybrid method ; Hybrid systems ; i2b2 ; Language processing ; Machine learning ; Medical records ; Narration ; Natural language interfaces ; Natural Language Processing ; Pattern Recognition, Automated - methods ; Protected health information ; Rankings ; Tracking ; Vocabulary, Controlled
É parte de: Journal of biomedical informatics, 2015-12, Vol.58 (Suppl), p.S47-S52
Notas: ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Contributed equally to this work.
Descrição: [Display omitted] •We proposed a hybrid system to automatically de-identify electronic medical records.•PHIs are identified by token-level and character-level conditional random fields.•The character-level CRFs is used to avoid boundary errors caused by tokenization.•Our system achieves an F-score of 91.24% on 2014 i2b2 corpus, which is top-ranked. 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.
Editor: United States: Elsevier Inc
Idioma: Inglês

Links

View this record in MEDLINE/PubMed

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

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

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

United States: Elsevier Inc

Buscando em bases de dados remotas. Favor aguardar.