Multi-modal Graph Learning over UMLS Knowledge Graphs
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 38 of its 72 references that are in the map. First posted on arXiv 10 Jul 2023.
Builds on
38 of 72 references.
References · 38
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
- 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
- 2019Publicly Available Clinical BERT Embeddingscited by 995
26 more
- 2019ERNIE: Enhanced Language Representation with Informative Entitiescited by 525
- 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
- 2020Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease predictioncited by 368
- 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
- 2016RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanismcited by 344
- 2019Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasetscited by 298
- 2017Multitask learning and benchmarking with clinical time series datacited by 287
- 2019Analyzing the Structure of Attention in a Transformer Language Modelcited by 241
- 2020Self-Alignment Pretraining for Biomedical Entity Representationscited by 233
- 2022Deep Bidirectional Language-Knowledge Graph Pretrainingcited by 156
- 2016GRAM: Graph-based Attention Model for Healthcare Representation Learningcited by 152
- 2019Pre-training of Graph Augmented Transformers for Medication Recommendationcited by 124
- 2019Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformercited by 88
- 2020CoLAKE: Contextualized Language and Knowledge Embeddingcited by 86
- 2018MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcarecited by 72
- 2021Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generationcited by 47
- 2019Using Clinical Notes with Time Series Data for ICU Managementcited by 38
- 2021HiRID-ICU-Benchmark -- A Comprehensive Machine Learning Benchmark on High-resolution ICU Datacited by 38
- 2018Clinical Concept Embeddings Learned from Massive Sources of Multimodal Medical Datacited by 33
- 2021Collaborative Graph Learning with Auxiliary Text for Temporal Event Prediction in Healthcarecited by 30
- 2021Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphscited by 20
- 2023BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysiscited by 18
- 2021Self-Supervised Graph Learning with Hyperbolic Embedding for Temporal Health Event Predictioncited by 15
- 2022Graph-Text Multi-Modal Pre-training for Medical Representation Learningcited by 10
- 2022On the Importance of Clinical Notes in Multi-modal Learning for EHR Datacited by 10
- 2019MedGCN: Medication recommendation and lab test imputation via graph convolutional networkscited by 9
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.