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 10years. 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.

Background: In this study, we focus on building a fine-grained entity annotation corpus with the corresponding annotation guideline of traditional Chinese medicine (TCM) clinical records. Our aim is to provide a basis for the fine-grained corpus construction of TCM clinical records in future. Methods: We developed a four-step approach that is suitable for the construction of TCM medical records in our corpus. First, we determined the entity types included in this study through sample annotation. Then, we drafted a fine-grained annotation guideline by summarizing the characteristics of the dataset and referring to some existing guidelines. We iteratively updated the guidelines until the inter-annotator agreement (IAA) exceeded a Cohen’s kappa value of 0.9. Comprehensive annotations were performed while keeping the IAA value above 0.9. Results: We annotated the 10,197 clinical records in five rounds. Four entity categories involving 13 entity types were employed. The final fine-grained annotated entity corpus consists of 1104 entities and 67,799 tokens. The final IAAs are 0.936 on average (for three annotators), indicating that the fine-grained entity recognition corpus is of high quality. Conclusions: These results will provide a foundation for future research on corpus construction and named entity recognition tasks in the TCM clinical domain.

The International Classification of Diseases (ICD) has an important role in building applications for clinical medicine. Extremely large ICD coding label sets and imbalanced label distribution bring the problem of inconsistency between the local batch data distribution and the global training data distribution into the minibatch gradient descent (MBGD)-based training procedure for deep multi-label classification models for automatic ICD coding. The problem further leads to an overfitting issue. In order to improve the performance and generalization ability of the deep learning automatic ICD coding model, we proposed a simple and effective curriculum batching strategy in this paper for improving the MBGD-based training procedure. This strategy generates three batch sets offline through applying three predefined sampling algorithms. These batch sets satisfy a uniform data distribution, a shuffling data distribution and the original training data distribution, respectively, and the learning tasks corresponding to these batch sets range from simple to complex. Experiments show that, after replacing the original shuffling algorithm-based batching strategy with the proposed curriculum batching strategy, the performance of the three investigated deep multi-label classification models for automatic ICD coding all have dramatic improvements. At the same time, the models avoid the overfitting issue and all show better ability to learn the long-tailed label information. The performance is also better than a SOTA label set reconstruction model.