A Character-level Convolutional Recurrent Interaction Network for joint traditional Chinese medicine clinical named...

The electronic medical record (EMR) of traditional Chinese medicine (TCM) is a crucial document for recording patients' clinical data, structured around four main dimensions: inspection, listening and smelling, inquiry, and palpation. Analyzing these records using natural language processing holds promise for further structuring and modeling TCM medical data. Currently, deep learning-based named entity recognition is considered the prevailing method for processing TCM EMRs. However, these state-of-the-art models fail to consider the four diagnostic dimensions of TCM clinical data and their impact on entity type extraction, as well as to fully understand the semantic features of ancient Chinese representations in TCM. To address these issues, we introduce a joint clinical named recognition and relation extraction method designed to recognize and classify clinical entities - such as location and symptom attributes - along with their associative relationships (four diagnostic dimensions). In this study, we propose a Character-level Convolutional Recurrent Interaction Network (CCRIN), which treats the four diagnostic dimensions as relationships, locations as head entities, and symptom attributes as tail entities. The CCRIN integrates Chinese character embeddings and Chinese inter-character contextual convolutional feature vectors to capture the semantic information of the ancient Chinese language, while combining entity and relation extraction with a self-attention mechanism to generate rich feature representations through multi-task dynamic interaction. This approach enables the efficient extraction of TCM entities and relations related to the four diagnostic dimensions. Empirical studies on the NYT and the TCM-cases datasets demonstrate the superiority of the proposed model.