Clinicians are increasingly looking towards machine learning to gain insights
about patient evolutions. We propose a novel approach named Multi-Modal UMLS
Graph Learning (MMUGL) for learning meaningful representations of medical
concepts using graph neural networks over knowledge graphs based on the unified
medical language system. These representations are aggregated to represent
entire patient visits and then fed into a sequence model to perform predictions
at the granularity of multiple hospital visits of a patient. We improve
performance by incorporating prior medical knowledge and considering multiple
modalities. We compare our method to existing architectures proposed to learn
representations at different granularities on the MIMIC-III dataset and show
that our approach outperforms these methods. The results demonstrate the
significance of multi-modal medical concept representations based on prior
medical knowledge.

机器学习在医生对病人的发展趋势获得洞察力方面受到越来越多的关注。我们提出了一种名为多模态 UMLS 图神经网络学习（MMUGL）的新方法，用于使用基于统一医学语言系统的知识图上的图神经网络学习医学概念的有意义的表示。这些表示被聚合表示整个病人就诊情况，然后输入到序列模型中以在病人的多次医院就诊的粒度上进行预测。我们通过整合先前的医学知识并考虑多种模态来提高性能。我们将我们的方法与用于不同粒度上学习表示的现有架构在 MIMIC-III 数据集上进行比较，并展示出我们的方法优于这些方法。结果表明了基于先前的医学知识的多模态医学概念表示的重要性。