LAMGCN:Traditional Chinese Medicine Herb Recommendation via LSTMs with Attention Mechanisms and Graph Convolutional Networks

Herb recommendation plays a crucial role in the therapeutic process of Traditional Chinese Medicine (TCM), which aims at recommending a set of herbs to treat patients with different symptoms. Previous works used many methods to discover regularities in prescriptions but rarely considered the actual therapeutic process in TCM and the information of herbs was ignored. In this work, we propose LAMGCN (Herb Recommendation via LSTMs with Attention Mechanisms and Graph Convolutional Networks), which takes the syndrome induction process and the herb descriptions into account. We utilize attention mechanisms and graph neural networks to capture the correlation between symptoms and herbs. Extensive experiments have been done and the results demonstrate the effectiveness of our proposed method.