Research on Classification Model of TCM Syndrome Based on Integration of Knowledge Graph and Graph Convolutional Network (Preprint)

BACKGROUND Traditional Chinese Medicine (TCM), as an ancient medical system distinct from modern medicine, plays a crucial role in maintaining people's health.The accuracy of Traditional Chinese Medicine (TCM) treatment with syndrome differentiation outcomes is closely related to the experience of physicians. However, primary healthcare practitioners often lack experience, and the relatively low accuracy of intelligent TCM syndrome differentiation results is one of the current challenges. Therefore, a key research focus in the field of intelligent TCM lies in how to quickly and accurately differentiate patients while simultaneously enhancing patient satisfaction. OBJECTIVE The classification of traditional Chinese medicine (TCM) syndrome is an integral component of the TCM diagnostic system. Leveraging artificial intelligence (AI) technology to explore TCM syndrome classification models and enhance their performance holds the potential to extend into various other applications within the field of TCM. METHODS This study employs a residual structural graph convolutional neural network to capture deep features among data nodes, while integrating syndrome-related knowledge graphs to assist in consolidating syndrome embedding representations. This enhances the correlation between symptoms and syndrome by proposing the augmentation of status element weights as their bridge, integrating multi-layer information representations. Furthermore, a multilayer perceptron is utilized for syndrome classification. RESULTS The experimental results demonstrate that the proposed KGRGCN model achieves a precision of 75.43%, an accuracy of 74.93%, a recall of 76.91%, and an F1-score of 75.91%. CONCLUSIONS The proposed syndrome classification method outperforms several popular classification methods, including Support Vector Machine, TextCNN, and Random Forest.