用疾病子图位置编码提升图Transformer的共病预测能力
Graph Transformer with Disease Subgraph Positional Encoding for Improved Comorbidity Prediction
- 引入子图位置编码捕捉疾病间拓扑关系
- 在真实临床数据上实现28.24%的ROC AUC提升
- 适合医学图神经网络与共病研究者使用
共病指单个患者同时患有多种疾病，对疾病管理和预后有深远影响。理解这些复杂关联至关重要，尤其在共病加重病情的情况下。基于人类相互作用组（HI）和图方法进展，本文提出图Transformer子图位置编码（TSPE）用于共病预测。受生物监督嵌入（BSE）启发，TSPE结合Transformer注意力机制与子图位置编码（SPE），以捕捉节点间交互及疾病关联。实验表明，SPE比Dwivedi等人使用的线性位置编码（LPE）更有效，凸显整合聚类与疾病特异性信息的重要性。在真实临床基准数据集RR0和RR1上，TSPE相比现有最优方法，最多提升28.24%的ROC AUC和4.93%的准确率。该方法可推广至其他复杂图任务。代码已开源：https://github.com/xihan-qin/TSPE-GraphTransformer。
原文摘要 · Abstract (English)
Comorbidity, the co-occurrence of multiple medical conditions in a single patient, profoundly impacts disease management and outcomes. Understanding these complex interconnections is crucial, especially in contexts where comorbidities exacerbate outcomes. Leveraging insights from the human interactome (HI) and advancements in graph-based methodologies, this study introduces Transformer with Subgraph Positional Encoding (TSPE) for disease comorbidity prediction. Inspired by Biologically Supervised Embedding (BSE), TSPE employs Transformer's attention mechanisms and Subgraph Positional Encoding (SPE) to capture interactions between nodes and disease associations. Our proposed SPE proves more effective than LPE, as used in Dwivedi et al.'s Graph Transformer, underscoring the importance of integrating clustering and disease-specific information for improved predictive accuracy. Evaluated on real clinical benchmark datasets (RR0 and RR1), TSPE demonstrates substantial performance enhancements over the state-of-the-art method, achieving up to 28.24% higher ROC AUC and 4.93% higher accuracy. This method shows promise for adaptation to other complex graph-based tasks and applications. The source code is available in the GitHub repository at: https://github.com/xihan-qin/TSPE-GraphTransformer.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。