SDTM: A Novel Topic Model Framework for Syndrome Differentiation in Traditional Chinese Medicine

Abstract

Syndrome differentiation is the most basic diagnostic method in traditional Chinese medicine (TCM). The process of syndrome differentiation is difficult and challenging due to its complexity, diversity, and vagueness. Recently, artificial intelligent methods have been introduced to discover the regularities of syndrome differentiation from TCM medical records, but the existing DM algorithms failed to consider how a syndrome is generated according to TCM theories. In this paper, we propose a novel topic model framework named syndrome differentiation topic model (SDTM) to dynamically characterize the process of syndrome differentiation. The SDTM framework utilizes latent Dirichlet allocation (LDA) to discover the latent semantic relationship between symptoms and syndromes in mass of Chinese medical records. We also use similarity measurement method to make the uninterpretable topics correspond with the labeled syndromes. Finally, Bayesian method is used in the final differentiated syndromes. Experimental results show the superiority of SDTM over existing topic models for the task of syndrome differentiation.

Intelligent Acupuncture: Data-driven Revolution of Traditional Chinese Medicine

“…The use of precision acupuncture prescriptions leveraging AI techniques, backed by extensive clinical data, assists acupuncturists in comprehending the intricate patterns of syndromes and creating consistent diagnostic criteria for TCM. This approach facilitates the preservation, enhancement, and advancement of TCM diagnostic theories [69] . With the help of AI, accurate acupuncture prescriptions can significantly enhance the efficacy of treatment and improve the clinical outcomes of patients [70] .…”

Research on TCM syndrome differentiation based on multi-feature fusion and GCN

“…ZY-BERT provides a good language model for the field of traditional Chinese medicine. Ma et al [31] proposed a syndrome differentiation topic model (SDTM) to dynamically characterize the process of syndrome differentiation. SDTM uses LDA (Latent Dirichlet Allocation) to capture the relationship between symptoms and syndrome types, and combines similarity to measure the relationship between topics and syndrome types.…”

“…ZY-BERT [30]: Based on TCM-SD pre-training language model, the classification results are obtained directly with CLS symbols. SDTM [31]: Method of TCM syndrome differentiation based on topic model. BiLSTM-CNN [32]: Multi-task joint learning syndrome differentiation method based on BiLSTM and CNN.…”

The Blueprint of Traditional Chinese Medicine

“…What are Yin-Yang and the five-element doctrine? Yin Yang (30,31) is rooted in ancient philosophy in China and it summarizes the properties of the opposite aspects or phenomena of the universe. Yin Yang represents two aspects in opposition, and two opposite sides of a single entity.…”