MHGRL: An Effective Representation Learning Model for Electronic Health Records (MHGRL：一种用于电子健康记录的有效表征学习模型)

会议：LREC–COLING 2024

论文页码: 11272–11282

DOI: -

作者：Feiyan Liu, Liangzhi Li, Xiaoli Wang, Feng Luo, Chang Liu, Jinsong Su, Yiming Qian

英文摘要:

    Electronic health records (EHRs) serve as a digital repository storing comprehensive medical information about patients. Representation learning for EHRs plays a crucial role in healthcare applications. In this paper, we propose a Multimodal Heterogeneous Graph-enhanced Representation Learning, denoted as MHGRL, aimed at learning effective EHR representations. To address the challenge posed by data insufficiency of EHRs, MHGRL utilizes a multimodal heterogeneous graph to model an EHR. Specifically, we construct a heterogeneous graph for each EHR and enrich it by incorporating multimodal information with medical ontology and textual notes. With the integration of pre-trained model, graph neural network, and attention mechanism, MHGRL effectively incorporates both node attributes and structural information across a multimodal heterogeneous graph. Moreover, we employ contrastive learning to ensure the consistency of representations for similar EHRs and improve the model robustness. The experimental results show that MHGRL outperforms all baselines on two real clinical datasets in downstream tasks, including EHR clustering and disease prediction. The code is available at https://github.com/emmali808/MHGRL.

中文摘要:

    电子健康记录 (EHR) 是存储患者全面医疗信息的数字存储库。EHR 的表征学习在医疗保健应用中发挥着至关重要的作用。本文提出了一种多模态异构图增强表征学习 (MHGRL)，旨在学习有效的 EHR 表征。为了应对 EHR 数据不足带来的挑战，MHGRL 利用多模态异构图对 EHR 进行建模。具体而言，我们为每个 EHR 构建一个异构图，并通过将多模态信息与医学本体和文本注释相结合来丰富其内容。通过整合预训练模型、图神经网络和注意力机制，MHGRL 有效地融合了多模态异构图中的节点属性和结构信息。此外，我们采用对比学习来确保相似 EHR 表征的一致性，并提高模型的鲁棒性。实验结果表明，MHGRL 在两个真实临床数据集上，在 EHR 聚类和疾病预测等下游任务中均优于所有基准模型。该代码可在 https://github.com/emmali808/MHGRL. 获取。

MHGRL框架图