Recently, considering the advancement of information technology in healthcare, electronic medical records (EMRs) have become the repository of patients' treatment processes in hospitals, including the patient'...
详细信息
Recently, considering the advancement of information technology in healthcare, electronic medical records (EMRs) have become the repository of patients' treatment processes in hospitals, including the patient's treatment pattern (standard treatment process), the patient's medical history, the patient's admission diagnosis, etc. In particular, EMRs-based treatment recommendation systems have become critical for optimizing clinical decision-making. EMRs contain complex relationships between patients and treatment patterns. Recent studies have shown that graph neural collaborative filtering can effectively capture the complex relationships in EMRs. However, none of the existing methods take into account the impact of medical content such as the patient's admission diagnosis, and medical history on treatment recommendations. In this work, we propose a graph neural collaborative filtering model with medical content-aware pre-training (CAPRec) for learning initial embeddings with medical content to improve recommendation performance. First the model constructs a patient-treatment pattern interaction graph from EMRs data. Then we attempt to use the medical content for pre-training learning and transfer the learned embeddings to a graph neural collaborative filtering model. Finally, the learned initial embedding can support the downstream task of graphcollaborativefiltering. Extensive experiments on real world datasets have consistently demonstrated the effectiveness of the medical content-aware training framework in improving treatment recommendations.
The problem of sequential recommendation aims at predicting the most likely item that user will interact based on historical interaction sequence. However, the previous methods only consider the proximity correlations...
详细信息
ISBN:
(纸本)9783031442223;9783031442230
The problem of sequential recommendation aims at predicting the most likely item that user will interact based on historical interaction sequence. However, the previous methods only consider the proximity correlations among items and neglect the internal correlations when exploiting auxiliary information, and thus are insufficient to obtain accurate item embedding. Inspired by the success of transformer in NLP, we propose a novel Knowledge graph Transformer for Sequential Recommendation, KGT-SR for brevity. The main idea of KGT-SR is to extract the rich semantic information of items by utilizing knowledge graph and feed the fused position and item information into the transformer to well learn item representation. KGT-SR consists of embedding layer, knowledge extraction layer and prediction layer. Extensive experiments results on three real world recommendation scenarios show that KGT-SR not only outperforms state-of-the-art sequential recommendation methods but also alleviates the problem of data sparsity.
暂无评论