mlsanityData to 14 Oct 2026

Interpretable graph-based models on multimodal biomedical data integration: A technical review and benchmarking

arXiv 2505.01696 ↗First posted 3 May 2025q-bio.GN cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Integrating heterogeneous biomedical data including imaging, omics, and clinical records supports accurate diagnosis and personalised care. Graph-based models fuse such non-Euclidean data by capturing spatial and relational structure, yet clinical uptake requires regulator-ready interpretability. We present the first technical survey of interpretable graph based models for multimodal biomedical data, covering 26 studies published between Jan 2019 and Sep 2024. Most target disease classification, notably cancer and rely on static graphs from simple similarity measures, while graph-native explainers are rare; post-hoc methods adapted from non-graph domains such as gradient saliency, and SHAP predominate. We group existing approaches into four interpretability families, outline trends such as graph-in-graph hierarchies, knowledge-graph edges, and dynamic topology learning, and perform a practical benchmark. Using an Alzheimer disease cohort, we compare Sensitivity Analysis, Gradient Saliency, SHAP and Graph Masking. SHAP and Sensitivity Analysis recover the broadest set of known AD pathways and Gene-Ontology terms, whereas Gradient Saliency and Graph Masking surface complementary metabolic and transport signatures. Permutation tests show all four beat random gene sets, but with distinct trade-offs: SHAP and Graph Masking offer deeper biology at higher compute cost, while Gradient Saliency and Sensitivity Analysis are quicker though coarser. We also provide a step-by-step flowchart covering graph construction, explainer choice and resource budgeting to help researchers balance transparency and performance. This review synthesises the state of interpretable graph learning for multimodal medicine, benchmarks leading techniques, and charts future directions, from advanced XAI tools to under-studied diseases, serving as a concise reference for method developers and translational scientists.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 108 references that are in the map. First posted on arXiv 3 May 2025.

Builds on

42 of 108 references.

References · 42

  1. 2017Graph Attention Networkscited by 8,923
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  7. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  8. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  9. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  10. 2018Sanity Checks for Saliency Mapscited by 1,156
  11. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  12. 2022Galactica: A Large Language Model for Sciencecited by 744
30 more
  1. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  2. 2020A Generalization of Transformer Networks to Graphscited by 661
  3. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  4. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 478
  5. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  6. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  7. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 320
  8. 2022GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Recordscited by 238
  9. 2021Understanding the Capabilities, Limitations, and Societal Impact of Large Language Modelscited by 160
  10. 2023Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learningcited by 133
  11. 2018Towards Sparse Hierarchical Graph Classifierscited by 100
  12. 2023LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunitiescited by 97
  13. 2022Evaluating Explainability for Graph Neural Networkscited by 87
  14. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
  15. 2021VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantizationcited by 39
  16. 2024From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Taskscited by 38
  17. 2023Leveraging Medical Knowledge Graphs Into Large Language Models for Diagnosis Prediction: Design and Application Studycited by 30
  18. 2023A Survey on Spectral Graph Neural Networkscited by 26
  19. 2022Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysiscited by 25
  20. 2023DEGREE: Decomposition Based Explanation For Graph Neural Networkscited by 18
  21. 2022Explainability in Graph Neural Networks: An Experimental Surveycited by 16
  22. 2024KNOWNET: Guided Health Information Seeking from LLMs via Knowledge Graph Integrationcited by 15
  23. 2022Multimodal spatiotemporal graph neural networks for improved prediction of 30-day all-cause hospital readmissioncited by 14
  24. 2024Integrated Brain Connectivity Analysis with fMRI, DTI, and sMRI Powered by Interpretable Graph Neural Networkscited by 12
  25. 2020Explainable Recommender Systems via Resolving Learning Representationscited by 11
  26. 2021IA-GCN: Interpretable Attention based Graph Convolutional Network for Disease predictioncited by 10
  27. 2021Ensemble manifold based regularized multi-modal graph convolutional network for cognitive ability predictioncited by 9
  28. 2021U-GAT: Multimodal Graph Attention Network for COVID-19 Outcome Predictioncited by 4
  29. 2023Multimodal brain age estimation using interpretable adaptive population-graph learningcited by 3
  30. 2020dg2pix: Pixel-Based Visual Analysis of Dynamic Graphscited by 1

Built on by

Not cited yet.