1932
0
  1. Home
  2. A-Z Publications
  3. Annual Review of Biomedical Data Science
  4. Volume 7, 2024
  5. Article

Annual Review of Biomedical Data Science

Volume 7, 2024

Graph Artificial Intelligence in Medicine

Abstract

In clinical artificial intelligence (AI), graph representation learning, mainly through graph neural networks and graph transformer architectures, stands out for its capability to capture intricate relationships and structures within clinical datasets. With diverse data—from patient records to imaging—graph AI models process data holistically by viewing modalities and entities within them as nodes interconnected by their relationships. Graph AI facilitates model transfer across clinical tasks, enabling models to generalize across patient populations without additional parameters and with minimal to no retraining. However, the importance of human-centered design and model interpretability in clinical decision-making cannot be overstated. Since graph AI models capture information through localized neural transformations defined on relational datasets, they offer both an opportunity and a challenge in elucidating model rationale. Knowledge graphs can enhance interpretability by aligning model-driven insights with medical knowledge. Emerging graph AI models integrate diverse data modalities through pretraining, facilitate interactive feedback loops, and foster human–AI collaboration, paving the way toward clinically meaningful predictions.

Keyword(s): artificial intelligence, graph neural networks, graph transformers, health care, human-centered AI, knowledge graphs, medicine, multimodal learning, transfer learning
Loading

Article metrics loading...

/content/journals/10.1146/annurev-biodatasci-110723-024625
2024-08-23
2024-10-12
Loading full text...

Full text loading...

/deliver/fulltext/biodatasci/7/1/annurev-biodatasci-110723-024625.html?itemId=/content/journals/10.1146/annurev-biodatasci-110723-024625&mimeType=html&fmt=ahah

Literature Cited

  1. 1.
    Natl. Res. Counc. Comm. Framew. Dev. New Taxon. Dis. 2011.. Toward Precision Medicine: Building a Knowledge Network for Biomedical Research and a New Taxonomy of Disease. Washington, DC:: Natl. Acad.
     [Google Scholar]
  2. 2.
    Collins FS, Varmus H. 2015.. A new initiative on precision medicine. . N. Engl. J. Med. 372::793–95
     [Crossref] [Google Scholar]
  3. 3.
    Safran C, Bloomrosen M, Hammond WE, Labkoff S, Markel-Fox S, et al. 2007.. Toward a national framework for the secondary use of health data: an American Medical Informatics Association white paper. . J. Am. Med. Inf. Assoc. 14::1–9
     [Crossref] [Google Scholar]
  4. 4.
    Nair S, Hsu D, Celi LA. 2016.. Challenges and opportunities in secondary analyses of electronic health record data. . In Secondary Analysis of Electronic Health Records, pp. 17–26. Cham, Switz:.: Springer
     [Google Scholar]
  5. 5.
    Sandhu E, Weinstein S, McKethan A, Jain SH. 2012.. Secondary uses of electronic health record data: benefits and barriers. . Jt. Comm. J. Qual. Patient Saf. 38::34–40
     [Google Scholar]
  6. 6.
    Weiskopf NG, Hripcsak G, Swaminathan S, Weng C. 2013.. Defining and measuring completeness of electronic health records for secondary use. . J. Biomed. Inform. 46::830–36
     [Crossref] [Google Scholar]
  7. 7.
    Jensen PB, Jensen LJ, Brunak S. 2012.. Mining electronic health records: towards better research applications and clinical care. . Nat. Rev. Genet. 13::395–405
     [Crossref] [Google Scholar]
  8. 8.
    Hripcsak G, Albers DJ. 2013.. Next-generation phenotyping of electronic health records. . J. Am. Med. Inform. Assoc. 20::117–21
     [Crossref] [Google Scholar]
  9. 9.
    Bengio Y, Courville A, Vincent P. 2013.. Representation learning: a review and new perspectives. . IEEE Trans. Pattern Anal. Mach. Intell. 35::1798–828
     [Crossref] [Google Scholar]
  10. 10.
    Acosta JN, Falcone GJ, Rajpurkar P, Topol EJ. 2022.. Multimodal biomedical AI. . Nat. Med. 28::1773–84
     [Crossref] [Google Scholar]
  11. 11.
    Himmelstein DS, Baranzini SE. 2015.. Heterogeneous network edge prediction: a data integration approach to prioritize disease-associated genes. . PLOS Comput. Biol. 11::e1004259
     [Crossref] [Google Scholar]
  12. 12.
    Nelson CA, Butte AJ, Baranzini SE. 2019.. Integrating biomedical research and electronic health records to create knowledge-based biologically meaningful machine-readable embeddings. . Nat. Commun. 10::3045
     [Crossref] [Google Scholar]
  13. 13.
    Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, et al. 2017.. Attention is all you need. . Adv. Neural Inf. Proc. Syst. 30::6000–10
     [Google Scholar]
  14. 14.
    Zhang R, Zou Y, Ma J. 2019.. Hyper-SAGNN: a self-attention based graph neural network for hypergraphs. . arXiv:1911.02613 [cs.LG]
  15. 15.
    Wang J, Ma A, Chang Y, Gong J, Jiang Y, et al. 2021.. scGNN is a novel graph neural network framework for single-cell RNA-seq analyses. . Nat. Commun. 12::1882
     [Crossref] [Google Scholar]
  16. 16.
    Li MM, Huang K, Zitnik M. 2022.. Graph representation learning in biomedicine and healthcare. . Nat. Biomed. Eng. 6::1353–69
     [Crossref] [Google Scholar]
  17. 17.
    Cheng TM, Lu YE, Vendruscolo M, Liò P, Blundell TL. 2008.. Prediction by graph theoretic measures of structural effects in proteins arising from non-synonymous single nucleotide polymorphisms. . PLOS Comput. Biol. 4::e1000135
     [Crossref] [Google Scholar]
  18. 18.
    Fout A, Byrd J, Shariat B, Ben-Hur A. 2017.. Protein interface prediction using graph convolutional networks. . Adv. Neural Inf. Proc. Syst. 30::6533–42
     [Google Scholar]
  19. 19.
    Zitnik M, Agrawal M, Leskovec J. 2018.. Modeling polypharmacy side effects with graph convolutional networks. . Bioinformatics 34::i457–66
     [Crossref] [Google Scholar]
  20. 20.
    Jin W, Barzilay R, Jaakkola T. 2020.. Discovering synergistic drug combinations for COVID with biological bottleneck models. . arXiv:2011.04651 [q-bio.BM]
  21. 21.
    Zitnik M, Li MM, Wells A, Glass K, Gysi DM, et al. 2023.. Current and future directions in network biology. . arXiv:2309.08478 [q-bio.MN]
  22. 22.
    Hamilton WL, Ying R, Leskovec J. 2017.. Representation learning on graphs: methods and applications. . arXiv:1709.05584 [cs.SI]
  23. 23.
    Hamilton WL. 2020.. Graph Representation Learning. San Francisco, CA:: Morgan & Claypool
     [Google Scholar]
  24. 24.
    Ju W, Fang Z, Gu Y, Liu Z, Long Q, et al. 2023.. A comprehensive survey on deep graph representation learning. . arXiv:2304.05055 [cs.LG]
  25. 25.
    Sosa DN, Derry A, Guo M, Wei E, Brinton C, Altman RB. 2019.. A literature-based knowledge graph embedding method for identifying drug repurposing opportunities in rare diseases. . In Pacific Symposium on Biocomputing 2020, pp. 463–74. Singapore:: World Sci.
     [Google Scholar]
  26. 26.
    Morselli Gysi D, Do Valle Í, Zitnik M, Ameli A, Gan X, et al. 2021.. Network medicine framework for identifying drug-repurposing opportunities for COVID-19. . PNAS 118::e2025581118
     [Crossref] [Google Scholar]
  27. 27.
    Nguyen T, Le H, Quinn TP, Nguyen T, Le TD, Venkatesh S. 2021.. GraphDTA: predicting drug–target binding affinity with graph neural networks. . Bioinformatics 37::1140–47
     [Crossref] [Google Scholar]
  28. 28.
    Huang K, Chandak P, Wang Q, Havaldar S, Vaid A, et al. 2023.. Zero-shot prediction of therapeutic use with geometric deep learning and clinician centered design. . medRxiv 2023.03.19.23287458. https://doi.org/10.1101/2023.03.19.23287458
  29. 29.
    Hwang D, Jeon M, Kang J. 2020.. A drug-induced liver injury prediction model using transcriptional response data with graph neural network. . In 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), pp. 323–29. Piscataway, NJ:: IEEE
     [Google Scholar]
  30. 30.
    Kim D, Kim S, Risacher SL, Shen L, Ritchie MD, et al. 2013.. A graph-based integration of multimodal brain imaging data for the detection of early mild cognitive impairment (E-MCI). . In Multimodal Brain Image Analysis: 3rd International Workshop (MBIA 2013), Held in Conjunction with MICCAI 2013, Proceedings 3, pp. 159–69. Berlin:: Springer
     [Google Scholar]
  31. 31.
    Tong T, Gray K, Gao Q, Chen L, Rueckert D, et al. 2017.. Multi-modal classification of Alzheimer's disease using nonlinear graph fusion. . Pattern Recognit. 63::171–81
     [Crossref] [Google Scholar]
  32. 32.
    Yang H, Li X, Wu Y, Li S, Lu S, et al. 2019.. Interpretable multimodality embedding of cerebral cortex using attention graph network for identifying bipolar disorder. . In Medical Image Computing and Computer Assisted Intervention—MICCAI 2019: 22nd International Conference, Proceedings, Part III, pp. 799–807. Berlin:: Springer
     [Google Scholar]
  33. 33.
    Li X, Wang Y, Wang D, Yuan W, Peng D, Mei Q. 2019.. Improving rare disease classification using imperfect knowledge graph. . BMC Med. Inform. Decis. Mak. 19::238
     [Crossref] [Google Scholar]
  34. 34.
    Sun Z, Yin H, Chen H, Chen T, Cui L, Yang F. 2020.. Disease prediction via graph neural networks. . IEEE J. Biomed. Health Inform. 25::818–26
     [Crossref] [Google Scholar]
  35. 35.
    Alsentzer E, Finlayson SG, Li MM, Zitnik M. 2020.. Subgraph neural networks. . In Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS 20), pp. 8017–29. New York:: ACM
     [Google Scholar]
  36. 36.
    Alsentzer E, Li MM, Kobren SN, Kohane IS, Zitnik M. 2022.. Deep learning for diagnosing patients with rare genetic diseases. . medRxiv 2022.12.07.22283238. https://doi.org/10.1101/2022.12.07.22283238
  37. 37.
    Wu Z, Trevino AE, Wu E, Swanson K, Kim HJ, et al. 2022.. Graph deep learning for the characterization of tumour microenvironments from spatial protein profiles in tissue specimens. . Nat. Biomed. Eng. 6::1435–48
     [Crossref] [Google Scholar]
  38. 38.
    Lee Y, Park JH, Oh S, Shin K, Sun J, et al. 2022.. Derivation of prognostic contextual histopathological features from whole-slide images of tumours via graph deep learning. . Nat. Biomed. Eng. https://doi.org/10.1038/s41551-022-00923-0
    [Google Scholar]
  39. 39.
    Zhou H, Skolnick J. 2016.. A knowledge-based approach for predicting gene–disease associations. . Bioinformatics 32::2831–38
     [Crossref] [Google Scholar]
  40. 40.
    Wang X, Gong Y, Yi J, Zhang W. 2019.. Predicting gene–disease associations from the heterogeneous network using graph embedding. . In 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 504–11. Piscataway, NJ:: IEEE
     [Google Scholar]
  41. 41.
    Wen J, Zhang X, Rush E, Panickan VA, Li X, et al. 2023.. Multimodal representation learning for predicting molecule–disease relations. . Bioinformatics 39::btad085
     [Crossref] [Google Scholar]
  42. 42.
    Lu H, Uddin S. 2021.. A weighted patient network–based framework for predicting chronic diseases using graph neural networks. . Sci. Rep. 11::22607
     [Crossref] [Google Scholar]
  43. 43.
    Mao C, Yao L, Luo Y. 2022.. MedGCN: medication recommendation and lab test imputation via graph convolutional networks. . J. Biomed. Inform. 127::104000
     [Crossref] [Google Scholar]
  44. 44.
    Murali L, Gopakumar G, Viswanathan DM, Nedungadi P. 2023.. Towards electronic health record–based medical knowledge graph construction, completion, and applications: a literature study. . J. Biomed. Inform. 143::104403
     [Crossref] [Google Scholar]
  45. 45.
    Walke D, Micheel D, Schallert K, Muth T, Broneske D, et al. 2023.. The importance of graph databases and graph learning for clinical applications. . Database 2023::baad045
     [Google Scholar]
  46. 46.
    Aleksander SA, Balhoff J, Carbon S, Cherry JM, Drabkin HJ, et al. 2023.. The Gene Ontology Knowledgebase in 2023. . Genetics 224::iyad031
     [Crossref] [Google Scholar]
  47. 47.
    Chandak P, Huang K, Zitnik M. 2023.. Building a knowledge graph to enable precision medicine. . Sci. Data 10::67
     [Crossref] [Google Scholar]
  48. 48.
    Waikhom L, Patgiri R. 2023.. A survey of graph neural networks in various learning paradigms: methods, applications, and challenges. . Artif. Intell. Rev. 56::6295–364
     [Crossref] [Google Scholar]
  49. 49.
    Perozzi B, Al-Rfou R, Skiena S. 2014.. DeepWalk: online learning of social representations. . In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701–10. New York:: ACM
     [Google Scholar]
  50. 50.
    Grover A, Leskovec J. 2016.. node2vec: scalable feature learning for networks. . In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855–64. New York:: ACM
     [Google Scholar]
  51. 51.
    Trouillon T, Welbl J, Riedel S, Gaussier É, Bouchard G. 2016.. Complex embeddings for simple link prediction. . Proc. Mach. Learn. Res. 48::2071–80
     [Google Scholar]
  52. 52.
    Sun Z, Deng ZH, Nie JY, Tang J. 2019.. RotatE: knowledge graph embedding by relational rotation in complex space. Paper presented at 7th International Conference on Learning Representations (ICLR19), New Orleans, LA:, May 6–9
    [Google Scholar]
  53. 53.
    Hamilton W, Ying Z, Leskovec J. 2017.. Inductive representation learning on large graphs. . Adv. Neural Inf. Proc. Syst. 30::1025–35
     [Google Scholar]
  54. 54.
    Xu K, Hu W, Leskovec J, Jegelka S. 2018.. How powerful are graph neural networks?. arXiv:1810.00826 [cs.LG]
  55. 55.
    Xu K, Li C, Tian Y, Sonobe T, Kawarabayashi K, Jegelka S. 2018.. Representation learning on graphs with jumping knowledge networks. . Proc. Mach. Learn. Res. 80::5453–62
     [Google Scholar]
  56. 56.
    Li G, Müller M, Ghanem B, Koltun V. 2021.. Training graph neural networks with 1000 layers. . Proc. Mach. Learn. Res. 139::6437–49
     [Google Scholar]
  57. 57.
    Veličković P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y. 2018.. Graph attention networks. Paper presented at 6th International Conference on Learning Representations (ICLR18), Vancouver, Can.:, Apr. 30–May 3
    [Google Scholar]
  58. 58.
    Ma L, Lin C, Lim D, Romero-Soriano A, Dokania PK, et al. 2023.. Graph inductive biases in transformers without message passing. . Proc. Mach. Learn. Res. 202::23321–37
     [Google Scholar]
  59. 59.
    Kong K, Chen J, Kirchenbauer J, Ni R, Bruss CB, Goldstein T. 2023.. GOAT: a global transformer on large-scale graphs. . Proc. Mach. Learn. Res. 202::17375–90
     [Google Scholar]
  60. 60.
    Kreuzer D, Beaini D, Hamilton W, Létourneau V, Tossou P. 2021.. Rethinking graph transformers with spectral attention. . Adv. Neural Inf. Proc. Syst. 34::21618–29
     [Google Scholar]
  61. 61.
    Rampášek L, Galkin M, Dwivedi VP, Luu AT, Wolf G, Beaini D. 2022.. Recipe for a general, powerful, scalable graph transformer. . Adv. Neural Inf. Proc. Syst. 35::14501–15
     [Google Scholar]
  62. 62.
    Wu Q, Zhao W, Li Z, Wipf DP, Yan J. 2022.. NodeFormer: a scalable graph structure learning transformer for node classification. . Adv. Neural Inf. Proc. Syst. 35::27387–401
     [Google Scholar]
  63. 63.
    Longa A, Lachi V, Santin G, Bianchini M, Lepri B, et al. 2023.. Graph neural networks for temporal graphs: state of the art, open challenges, and opportunities. . arXiv:2302.01018 [cs]
  64. 64.
    Skianis K, Nikolentzos G, Gallix B, Thiebaut R, Exarchakis G. 2023.. Predicting COVID-19 positivity and hospitalization with multi-scale graph neural networks. . Sci. Rep. 13::5235
     [Crossref] [Google Scholar]
  65. 65.
    Fritz C, Dorigatti E, Rügamer D. 2022.. Combining graph neural networks and spatio-temporal disease models to improve the prediction of weekly COVID-19 cases in Germany. . Sci. Rep. 12::3930
     [Crossref] [Google Scholar]
  66. 66.
    Zhang X, Zeman M, Tsiligkaridis T, Zitnik M. 2022.. Graph-guided network for irregularly sampled multivariate time series. Paper presented at 10th International Conference on Learning Representations (ICLR22), online, Apr. 25
    [Google Scholar]
  67. 67.
    Antelmi A, Cordasco G, Polato M, Scarano V, Spagnuolo C, Yang D. 2023.. A survey on hypergraph representation learning. . ACM Comput. Surv. 56::24.1–38
     [Google Scholar]
  68. 68.
    Pang S, Zhang K, Wang S, Zhang Y, He S, et al. 2021.. HGDD: a drug-disease high-order association information extraction method for drug repurposing via hypergraph. . In International Symposium on Bioinformatics Research and Applications, pp. 424–35. Berlin:: Springer
     [Google Scholar]
  69. 69.
    Sun Z, Yang X, Feng Z, Xu T, Fan X, Tian J. 2022.. EHR2HG: modeling of EHRs data based on hypergraphs for disease prediction. . In 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1730–33. Piscataway, NJ:: IEEE
     [Google Scholar]
  70. 70.
    Xu R, Ali MK, Ho JC, Yang C. 2023.. Hypergraph transformers for EHR-based clinical predictions. . AMIA Summits Transl. Sci. Proc. 2023::582–91
     [Google Scholar]
  71. 71.
    Wu J, He K, Mao R, Li C, Cambria E. 2023.. MEGACare: knowledge-guided multi-view hypergraph predictive framework for healthcare. . Inf. Fusion 100::101939
     [Crossref] [Google Scholar]
  72. 72.
    Wang X, Zhang M. 2022.. GLASS: GNN with labeling tricks for subgraph representation learning. Paper presented at 10th International Conference on Learning Representations (ICLR22), online, Apr. 25
    [Google Scholar]
  73. 73.
    Hartman E, Scott AM, Karlsson C, Mohanty T, Vaara ST, et al. 2023.. Interpreting biologically informed neural networks for enhanced proteomic biomarker discovery and pathway analysis. . Nat. Commun. 14::5359
     [Crossref] [Google Scholar]
  74. 74.
    Elmarakeby HA, Hwang J, Arafeh R, Crowdis J, Gang S, et al. 2021.. Biologically informed deep neural network for prostate cancer discovery. . Nature 598::348–52
     [Crossref] [Google Scholar]
  75. 75.
    Haendel MA, Chute CG, Robinson PN. 2018.. Classification, ontology, and precision medicine. . N. Engl. J. Med. 379::1452–62
     [Crossref] [Google Scholar]
  76. 76.
    Zhang M, King CR, Avidan M, Chen Y. 2020.. Hierarchical attention propagation for healthcare representation learning. . In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 249–56. New York:: ACM
     [Google Scholar]
  77. 77.
    Lu Q, De Silva N, Kafle S, Cao J, Dou D, et al. 2019.. Learning electronic health records through hyperbolic embedding of medical ontologies. . In Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, pp. 338–46. New York:: ACM
     [Google Scholar]
  78. 78.
    Hao J, Lei C, Efthymiou V, Quamar A, Özcan F, et al. 2021.. MEDTO: Medical data to ontology matching using hybrid graph neural networks. . In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 2946–54. New York:: ACM
     [Google Scholar]
  79. 79.
    Peng X, Long G, Wang S, Jiang J, Clarke A, et al. 2021.. MIPO: mutual integration of patient journey and medical ontology for healthcare representation learning. . arXiv:2107.09288 [cs.AI]
  80. 80.
    Yao Z, Liu B, Wang F, Sow D, Li Y. 2023.. Ontology-aware prescription recommendation in treatment pathways using multi-evidence healthcare data. . ACM Trans. Inform. Syst. 41:(4):99
     [Crossref] [Google Scholar]
  81. 81.
    Bang D, Lim S, Lee S, Kim S. 2023.. Biomedical knowledge graph learning for drug repurposing by extending guilt-by-association to multiple layers. . Nat. Commun. 14::3570
     [Crossref] [Google Scholar]
  82. 82.
    Biswal S, Xiao C, Glass LM, Milkovits E, Sun J. 2020.. Doctor2Vec: dynamic doctor representation learning for clinical trial recruitment. . In Proceedings of the 34th AAAI Conference on Artificial Intelligence, pp. 557–64. Washington, DC:: AAAI
     [Google Scholar]
  83. 83.
    Hettige B, Li YF, Wang W, Le S, Buntine W. 2019.. MedGraph: structural and temporal representation learning of electronic medical records. . arXiv:1912.03703 [cs.LG]
  84. 84.
    Fernández-Torras A, Duran-Frigola M, Bertoni M, Locatelli M, Aloy P. 2022.. Integrating and formatting biomedical data as pre-calculated knowledge graph embeddings in the Bioteque. . Nat. Commun. 13::5304
     [Crossref] [Google Scholar]
  85. 85.
    Wang L, Liu Q, Zhang M, Hu Y, Wu S, Wang L. 2023.. Stage-aware hierarchical attentive relational network for diagnosis prediction. . IEEE Trans. Knowl. Data Eng. 1::5555
     [Google Scholar]
  86. 86.
    Gao C, Yin S, Wang H, Wang Z, Du Z, Li X. 2023.. Medical-knowledge-based graph neural network for medication combination prediction. . IEEE Trans. Neural Netw. Learn. Syst. In press. https://doi.org/10.1109/TNNLS.2023.3266490
    [Google Scholar]
  87. 87.
    Pfeifer B, Saranti A, Holzinger A. 2022.. GNN-SubNet: disease subnetwork detection with explainable graph neural networks. . Bioinformatics 38:(Suppl. 2):120–26
     [Crossref] [Google Scholar]
  88. 88.
    Liu Z, Li X, Peng H, He L, Philip SY. 2020.. Heterogeneous similarity graph neural network on electronic health records. . In 2020 IEEE International Conference on Big Data, pp. 1196–205. Piscataway, NJ:: IEEE
     [Google Scholar]
  89. 89.
    Li Y, Yang D, Gong X. 2022.. Patient similarity via medical attributed heterogeneous graph convolutional network. . IAENG Int. J. Comput. Sci. 49::4
     [Google Scholar]
  90. 90.
    Bharadhwaj VS, Ali M, Birkenbihl C, Mubeen S, Lehmann J, et al. 2021.. CLEP: a hybrid data- and knowledge-driven framework for generating patient representations. . Bioinformatics 37::3311–18
     [Crossref] [Google Scholar]
  91. 91.
    Pu L, Singha M, Wu HC, Busch C, Ramanujam J, Brylinski M. 2022.. An integrated network representation of multiple cancer-specific data for graph-based machine learning. . npj Syst. Biol. Appl. 8::14
     [Crossref] [Google Scholar]
  92. 92.
    Tong C, Rocheteau E, Veličković P, Lane N, Liò P. 2021.. Predicting patient outcomes with graph representation learning. . In International Workshop on Health Intelligence (W3PHAI 2021): AI for Disease Surveillance and Pandemic Intelligence, pp. 281–93. Berlin:: Springer
     [Google Scholar]
  93. 93.
    Singhal K, Azizi S, Tu T, Mahdavi SS, Wei J, et al. 2023.. Large language models encode clinical knowledge. . Nature 620::172–80
     [Crossref] [Google Scholar]
  94. 94.
    Singhal K, Tu T, Gottweis J, Sayres R, Wulczyn E, et al. 2023.. Towards expert-level medical question answering with large language models. . arXiv:2305.09617 [cs.CL]
  95. 95.
    Kiyasseh D, Ma R, Haque TF, Miles BJ, Wagner C, et al. 2023.. A vision transformer for decoding surgeon activity from surgical videos. . Nat. Biomed. Eng. 7::780–96
     [Crossref] [Google Scholar]
  96. 96.
    Rasmy L, Xiang Y, Xie Z, Tao C, Zhi D. 2021.. Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction. . npj Digit. Med. 4::86
     [Crossref] [Google Scholar]
  97. 97.
    Jiang LY, Liu XC, Nejatian NP, Nasir-Moin M, Wang D, et al. 2023.. Health system–scale language models are all-purpose prediction engines. . Nature 619::357–62
     [Crossref] [Google Scholar]
  98. 98.
    Huang Z, Bianchi F, Yuksekgonul M, Montine TJ, Zou J. 2023.. A visual–language foundation model for pathology image analysis using medical Twitter. . Nat. Med. 29::2307–16
     [Crossref] [Google Scholar]
  99. 99.
    Jiang P, Xiao C, Fu T, Sun J. 2023.. Bi-level contrastive learning for knowledge-enhanced molecule representations. . arXiv:2306.01631 [cs.LG]
  100. 100.
    Wang Y, Zhang J, Jin J, Wei L. 2023.. MolCAP: molecular chemical reactivity pretraining and prompted-finetuning enhanced molecular representation learning. . arXiv:2306.09187 [q-bio.BM]
  101. 101.
    Shang J, Ma T, Xiao C, Sun J. 2019.. Pre-training of graph augmented transformers for medication recommendation. . In Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp. 5953–59. Vienna:: IJCAI
     [Google Scholar]
  102. 102.
    Pan S, Luo L, Wang Y, Chen C, Wang J, Wu X. 2023.. Unifying large language models and knowledge graphs: a roadmap. . arXiv:2306.08302 [cs.CL]
  103. 103.
    Zhang X, Wu C, Zhang Y, Xie W, Wang Y. 2023.. Knowledge-enhanced visual-language pre-training on chest radiology images. . Nat. Commun. 14::4542
     [Crossref] [Google Scholar]
  104. 104.
    Varshney D, Zafar A, Behera NK, Ekbal A. 2023.. Knowledge grounded medical dialogue generation using augmented graphs. . Sci. Rep. 13::3310
     [Crossref] [Google Scholar]
  105. 105.
    Varshney D, Zafar A, Behera NK, Ekbal A. 2023.. Knowledge graph assisted end-to-end medical dialog generation. . Artif. Intell. Med. 139::102535
     [Crossref] [Google Scholar]
  106. 106.
    Xia F, Li B, Weng Y, He S, Liu K, et al. 2022.. MedConQA: medical conversational question answering system based on knowledge graphs. . In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 148–58. Stroudsburg, PA:: Assoc. Comput. Linguist.
     [Google Scholar]
  107. 107.
    McDermott MBA, Yap B, Szolovits P, Zitnik M. 2023.. Structure-inducing pre-training. . Nat. Mach. Intell. 5::612–21
     [Crossref] [Google Scholar]
  108. 108.
    Hu W, Liu B, Gomes J, Zitnik M, Liang P, et al. 2020.. Strategies for pre-training graph neural networks. Paper presented at 8th International Conference on Learning Representations (ICLR20), online, Apr. 26–May 1
    [Google Scholar]
  109. 109.
    Gao Y, Li R, Caskey J, Dligach D, Miller T, et al. 2023.. Leveraging a medical knowledge graph into large language models for diagnosis prediction. . arXiv:2308.14321 [cs.CL]
  110. 110.
    Acosta JN, Falcone GJ, Rajpurkar P, Topol EJ. 2022.. Multimodal biomedical AI. . Nat. Med. 28::1773–84
     [Crossref] [Google Scholar]
  111. 111.
    Lipkova J, Chen RJ, Chen B, Lu MY, Barbieri M, et al. 2022.. Artificial intelligence for multimodal data integration in oncology. . Cancer Cell 40::1095–110
     [Crossref] [Google Scholar]
  112. 112.
    Kline A, Wang H, Li Y, Dennis S, Hutch M, et al. 2022.. Multimodal machine learning in precision health: a scoping review. . npj Digit. Med. 5::171
     [Crossref] [Google Scholar]
  113. 113.
    Ektefaie Y, Dasoulas G, Noori A, Farhat M, Zitnik M. 2023.. Multimodal learning with graphs. . Nat. Mach. Intell. 5::340–50
     [Crossref] [Google Scholar]
  114. 114.
    Dong X, Wong R, Lyu W, Abell-Hart K, Deng J, et al. 2023.. An integrated LSTM-HeteroRGNN model for interpretable opioid overdose risk prediction. . Artif. Intell. Med. 135::102439
     [Crossref] [Google Scholar]
  115. 115.
    Hou W, Lin C, Yu L, Qin J, Yu R, Wang L. 2023.. Hybrid graph convolutional network with online masked autoencoder for robust multimodal cancer survival prediction. . IEEE Trans. Med. Imaging 42::2462–73
     [Crossref] [Google Scholar]
  116. 116.
    Krix S, DeLong LN, Madan S, Domingo-Fernández D, Ahmad A, et al. 2023.. MultiGML: multimodal graph machine learning for prediction of adverse drug events. . Heliyon 9::e19441
     [Crossref] [Google Scholar]
  117. 117.
    Hu K, Wang Z, Martens KAE, Hagenbuchner M, Bennamoun M, et al. 2023.. Graph fusion network–based multimodal learning for freezing of gait detection. . IEEE Trans. Neural Netw. Learn. Syst. 34::1588–600
     [Crossref] [Google Scholar]
  118. 118.
    Dwivedi C, Nofallah S, Pouryahya M, Iyer J, Leidal K, et al. 2022.. Multi stain graph fusion for multimodal integration in pathology. . In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1834–44. Piscataway, NJ:: IEEE
     [Google Scholar]
  119. 119.
    Zhang X, Wu C, Zhang Y, Xie W, Wang Y. 2023.. Knowledge-enhanced visual-language pre-training on chest radiology images. . Nat. Commun. 14::4542
     [Crossref] [Google Scholar]
  120. 120.
    Dsouza NS, Nebel MB, Crocetti D, Robinson J, Mostofsky S, Venkataraman A. 2021.. M-GCN: a multimodal graph convolutional network to integrate functional and structural connectomics data to predict multidimensional phenotypic characterizations. . Proc. Mach. Learn. Res. 143::119–30
     [Google Scholar]
  121. 121.
    Cai H, Gao Y, Liu M. 2023.. Graph transformer geometric learning of brain networks using multimodal MR images for brain age estimation. . IEEE Trans. Med. Imaging 42::456–66
     [Crossref] [Google Scholar]
  122. 122.
    Tang S, Tariq A, Dunnmon JA, Sharma U, Elugunti P, et al. 2023.. Predicting 30-day all-cause hospital readmission using multimodal spatiotemporal graph neural networks. . IEEE J. Biomed. Health Inform. 27::2071–82
     [Google Scholar]
  123. 123.
    Azher ZL, Vaickus LJ, Salas LA, Christensen BC, Levy JJ. 2022.. Development of biologically interpretable multimodal deep learning model for cancer prognosis prediction. . In Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing, pp. 636–44. New York:: ACM
     [Google Scholar]
  124. 124.
    Gao J, Lyu T, Xiong F, Wang J, Ke W, Li Z. 2022.. Predicting the survival of cancer patients with multimodal graph neural network. . IEEE/ACM Trans. Comput. Biol. Bioinform. 19::699–709
     [Crossref] [Google Scholar]
  125. 125.
    Liu J, Du H, Guo R, Bai HX, Kuang H, Wang J. 2022.. MMGK: multimodality multiview graph representations and knowledge embedding for mild cognitive impairment diagnosis. . IEEE Trans. Comput. Soc. Syst. 11::389–98
     [Crossref] [Google Scholar]
  126. 126.
    Wang T, Shao W, Huang Z, Tang H, Zhang J, et al. 2021.. MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification. . Nat. Commun. 12::3445
     [Crossref] [Google Scholar]
  127. 127.
    Golmaei SN, Luo X. 2021.. DeepNote-GNN: predicting hospital readmission using clinical notes and patient network. . In Proceedings of the 12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, art. 19 . New York:: ACM
     [Google Scholar]
  128. 128.
    Agarwal C, Zitnik M, Lakkaraju H. 2022.. Probing GNN explainers: a rigorous theoretical and empirical analysis of GNN explanation methods. . Proc. Mach. Learn. Res. 151::8969–96
     [Google Scholar]
  129. 129.
    Bienefeld N, Boss JM, Lüthy R, Brodbeck D, Azzati J, et al. 2023.. Solving the explainable AI conundrum by bridging clinicians' needs and developers' goals. . npj Digit. Med. 6::94
     [Crossref] [Google Scholar]
  130. 130.
    Agarwal C, Queen O, Lakkaraju H, Zitnik M. 2023.. Evaluating explainability for graph neural networks. . Sci. Data 10::144
     [Crossref] [Google Scholar]
  131. 131.
    Bhatt U, Xiang A, Sharma S, Weller A, Taly A, et al. 2020.. Explainable machine learning in deployment. . In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (FAT* '20), pp. 648–57. New York:: ACM
     [Google Scholar]
  132. 132.
    Davenport T, Kalakota R. 2019.. The potential for artificial intelligence in healthcare. . Future Healthc. J. 6::94
     [Crossref] [Google Scholar]
  133. 133.
    Yuan H, Yu H, Gui S, Ji S. 2022.. Explainability in graph neural networks: a taxonomic survey. . IEEE Trans. Pattern Anal. Mach. Intell. 45::5782–99
     [Google Scholar]
  134. 134.
    Yang G, Ye Q, Xia J. 2022.. Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: a mini-review, two showcases and beyond. . Inf. Fusion 77::29–52
     [Crossref] [Google Scholar]
  135. 135.
    Henderson R, Clevert DA, Montanari F. 2021.. Improving molecular graph neural network explainability with orthonormalization and induced sparsity. . Proc. Mach. Learn. Res. 139::4203–13
     [Google Scholar]
  136. 136.
    Miao S, Liu M, Li P. 2022.. Interpretable and generalizable graph learning via stochastic attention mechanism. . Proc. Mach. Learn. Res. 162::15524–43
     [Google Scholar]
  137. 137.
    Lundberg SM, Lee SI. 2017.. A unified approach to interpreting model predictions. . Adv. Neural Inf. Proc. Syst. 30::4768–77
     [Google Scholar]
  138. 138.
    Duval A, Malliaros FD. 2021.. GraphSVX: Shapley value explanations for graph neural networks. . In Machine Learning and Knowledge Discovery in Databases, Research Track: European Conference (ECML PKDD 2021), Proceedings, Part II, pp. 302–18. Berlin:: Springer
     [Google Scholar]
  139. 139.
    Pope PE, Kolouri S, Rostami M, Martin CE, Hoffmann H. 2019.. Explainability methods for graph convolutional neural networks. . In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10772–81. Piscataway, NJ:: IEEE
     [Google Scholar]
  140. 140.
    Schlichtkrull MS, De Cao N, Titov I. 2021.. Interpreting graph neural networks for NLP with differentiable edge masking. Paper presented at 9th International Conference on Learning Representations (ICLR21), Vienna:, May 4
    [Google Scholar]
  141. 141.
    Ying Z, Bourgeois D, You J, Zitnik M, Leskovec J. 2019.. GNNExplainer: generating explanations for graph neural networks. . Adv. Neural Inf. Proc. Syst. 32::9244–55
     [Google Scholar]
  142. 142.
    Yuan H, Yu H, Wang J, Li K, Ji S. 2021.. On explainability of graph neural networks via subgraph explorations. . Proc. Mach. Learn. Res. 139::12241–52
     [Google Scholar]
  143. 143.
    Ma J, Guo R, Mishra S, Zhang A, Li J. 2022.. CLEAR: Generative counterfactual explanations on graphs. . Adv. Neural Inf. Proc. Syst. 35::25895–907
     [Google Scholar]
  144. 144.
    Lucic A, Ter Hoeve MA, Tolomei G, De Rijke M, Silvestri F. 2022.. CF-GNNExplainer: counterfactual explanations for graph neural networks. . Proc. Mach. Learn. Res. 151::4499–511
     [Google Scholar]
  145. 145.
    Henry KE, Kornfield R, Sridharan A, Linton RC, Groh C, et al. 2022.. Human–machine teaming is key to AI adoption: clinicians' experiences with a deployed machine learning system. . npj Digit. Med. 5::97
     [Crossref] [Google Scholar]
  146. 146.
    Schwartz JM, George M, Rossetti SC, Dykes PC, Minshall SR, et al. 2022.. Factors influencing clinician trust in predictive clinical decision support systems for in-hospital deterioration: qualitative descriptive study. . JMIR Hum. Factors 9::e33960
     [Crossref] [Google Scholar]
  147. 147.
    Metsch JM, Saranti A, Angerschmid A, Pfeifer B, Klemt V, et al. 2024.. CLARUS: an interactive explainable AI platform for manual counterfactuals in graph neural networks. . J. Biomed. Inform. 150::104600
     [Crossref] [Google Scholar]
  148. 148.
    Wang Q, Huang K, Chandak P, Zitnik M, Gehlenborg N. 2022.. Extending the nested model for user-centric XAI: a design study on GNN-based drug repurposing. . IEEE Trans. Vis. Comput. Graph. 29::1266–76
     [Crossref] [Google Scholar]
  149. 149.
    Ektefaie Y, Dasoulas G, Noori A, Farhat M, Zitnik M. 2023.. Multimodal learning with graphs. . Nat. Mach. Intell. 5::340–50
     [Crossref] [Google Scholar]
  150. 150.
    Zhang C, Chu X, Ma L, Zhu Y, Wang Y, et al. 2022.. M3Care: learning with missing modalities in multimodal healthcare data. . In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 2418–28. New York:: ACM
     [Google Scholar]
  151. 151.
    Groenwold RH. 2020.. Informative missingness in electronic health record systems: the curse of knowing. . Diagn. Progn. Res. 4::8
     [Crossref] [Google Scholar]
  152. 152.
    Bommasani R, Hudson DA, Adeli E, Altman R, Arora S, et al. 2021.. On the opportunities and risks of foundation models. . arXiv:2108.07258 [cs.LG]
/content/journals/10.1146/annurev-biodatasci-110723-024625
Loading
Graph Artificial Intelligence in Medicine
Annual Review of Biomedical Data Science 7, 345 (2024); https://doi.org/10.1146/annurev-biodatasci-110723-024625
/content/journals/10.1146/annurev-biodatasci-110723-024625
/content/journals/10.1146/annurev-biodatasci-110723-024625
Loading

Data & Media loading...

  • Article Type: Review Article

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error