A Unified Framework of Medical Information Annotation and Extraction for Chinese Clinical Text
This work addresses the need for efficient medical information extraction in Chinese clinical settings, though it is incremental as it builds on existing NLP techniques with task-specific adaptations.
The study tackled the problem of extracting structured medical information from Chinese clinical text by developing a unified framework for annotation and modeling of entity recognition, relation extraction, and attribute extraction, resulting in F1 scores of 93.47%, 67.14%, and 90.89% respectively on a new annotated corpus.
Medical information extraction consists of a group of natural language processing (NLP) tasks, which collaboratively convert clinical text to pre-defined structured formats. Current state-of-the-art (SOTA) NLP models are highly integrated with deep learning techniques and thus require massive annotated linguistic data. This study presents an engineering framework of medical entity recognition, relation extraction and attribute extraction, which are unified in annotation, modeling and evaluation. Specifically, the annotation scheme is comprehensive, and compatible between tasks, especially for the medical relations. The resulted annotated corpus includes 1,200 full medical records (or 18,039 broken-down documents), and achieves inter-annotator agreements (IAAs) of 94.53%, 73.73% and 91.98% F 1 scores for the three tasks. Three task-specific neural network models are developed within a shared structure, and enhanced by SOTA NLP techniques, i.e., pre-trained language models. Experimental results show that the system can retrieve medical entities, relations and attributes with F 1 scores of 93.47%, 67.14% and 90.89%, respectively. This study, in addition to our publicly released annotation scheme and code, provides solid and practical engineering experience of developing an integrated medical information extraction system.