No abstract

Background. The practice of traditional Chinese medicine (TCM) began several thousand years ago, and the knowledge of practitioners is recorded in paper and electronic versions of case notes, manuscripts, and books in multiple languages. Developing a method of information extraction (IE) from these sources to generate a cohesive data set would be a great contribution to the medical field. The goal of this study was to perform a systematic review of the status of IE from TCM sources over the last 10 years. Methods. We conducted a search of four literature databases for articles published from 2010 to 2021 that focused on the use of natural language processing (NLP) methods to extract information from unstructured TCM text data. Two reviewers and one adjudicator contributed to article search, article selection, data extraction, and synthesis processes. Results. We retrieved 1234 records, 49 of which met our inclusion criteria. We used the articles to (i) assess the key tasks of IE in the TCM domain, (ii) summarize the challenges to extracting information from TCM text data, and (iii) identify effective frameworks, models, and key findings of TCM IE through classification. Conclusions. Our analysis showed that IE from TCM text data has improved over the past decade. However, the extraction of TCM text still faces some challenges involving the lack of gold standard corpora, nonstandardized expressions, and multiple types of relations. In the future, IE work should be promoted by extracting more existing entities and relations, constructing gold standard data sets, and exploring IE methods based on a small amount of labeled data. Furthermore, fine-grained and interpretable IE technologies are necessary for further exploration.

Objective In this paper, we focused on building a fine-grained entity annotation corpus with corresponding annotation guideline of Traditional Chinese Medicine ( TCM ) clinical records, and to provide an effective way to build more corpora of TCM clinical records in the future.Methods: Instead of previous research methods, we proposed four steps approach which is suitable for TCM medical records in our corpus construction work. Firstly, determine the entity types included in this study through sample annotation method; secondly, draft our fine-grained annotation guideline by summarizing the characteristics of the dataset and referring to some existing guidelines; thirdly, update the guideline through iterative annotations way until the inter-annotator agreement (IAA) value exceed 0.9, kappa value was used to measure the IAA; fourthly, comprehensive annotations were performed, if IAA value exceeds 0.9 stably . After above four method steps, we succeeded to construct the fine-grained entity recognition corpus of TCM clinical records.Results: There are 4 entity categories involving 13 entity types being determined finally. The finegrained annotated entity corpus consists of 1104 entities and 67799 tokens totally. The final IAAs are 0.93, 0.94, 0.94 respectively (between two of the three annotators), the IAA value show the finegrained entity recognition corpus are of high quality. We constructed a fine-grained annotated guideline and entity recognition corpus of TCM clinical records.Conclusions: The four-step method was of high quality, the corpus constructed in this study was an encouraging example . Based on this approach, more comprehensive corpus about TCM clinical records will be built to support the TCM named entity recognition tasks in future research.