Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Knowledge-augmented Graph Neural Networks with Concept-aware Attention for Adverse Drug Event Detection (2301.10451v3)

Published 25 Jan 2023 in cs.CL

Abstract: Adverse drug events (ADEs) are an important aspect of drug safety. Various texts such as biomedical literature, drug reviews, and user posts on social media and medical forums contain a wealth of information about ADEs. Recent studies have applied word embedding and deep learning -based natural language processing to automate ADE detection from text. However, they did not explore incorporating explicit medical knowledge about drugs and adverse reactions or the corresponding feature learning. This paper adopts the heterogenous text graph which describes relationships between documents, words and concepts, augments it with medical knowledge from the Unified Medical Language System, and proposes a concept-aware attention mechanism which learns features differently for the different types of nodes in the graph. We further utilize contextualized embeddings from pretrained LLMs and convolutional graph neural networks for effective feature representation and relational learning. Experiments on four public datasets show that our model achieves performance competitive to the recent advances and the concept-aware attention consistently outperforms other attention mechanisms.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. Ilseyar Alimova and Valery Solovyev. 2018. Interactive attention network for adverse drug reaction classification. In Conference on Artificial Intelligence and Natural Language, pages 185–196. Springer.
  2. TwiMed: Twitter and PubMed comparable corpus of drugs, diseases, symptoms, and their relations. JMIR Public Health and Surveillance, 3(2):e6396.
  3. Olivier Bodenreider. 2004. The Unified Medical Language System (UMLS): Integrating Biomedical Terminology. Nucleic Acids Research, 32:D267–70.
  4. Learning causality patterns for detecting adverse drug reactions from social media. Journal of Medical Internet Research.
  5. Deep learning for pharmacovigilance: recurrent neural network architectures for labeling adverse drug reactions in twitter posts. Journal of the American Medical Informatics Association, 24(4):813–821.
  6. Adverse drug events detection in clinical notes by jointly modeling entities and relations using neural networks. Drug Safety, 42(1):135–146.
  7. Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT.
  8. To err is human: building a safer health system.
  9. Contextualized graph embeddings for adverse drug event detection. In Proceedings of ECML-PKDD.
  10. Detecting and extracting of adverse drug reaction mentioning tweets with multi-head self attention. In Proceedings of the Fourth Social Media Mining for Health (# SMM4H) Workshop and Shared Task, pages 96–98.
  11. Adverse drug reaction classification with deep neural networks. In COLING.
  12. A survey on knowledge graphs: Representation, acquisition and applications. IEEE Transactions on Neural Networks and Learning Systems, 33.
  13. A knowledge graph embedding based approach to predict the adverse drug reactions using a deep neural network. Journal of Biomedical Informatics, page 104122.
  14. Cadec: A corpus of adverse drug event annotations. Journal of Biomedical Informatics, 55:73–81.
  15. BERT based Adverse Drug Effect Tweet Classification. In Proceedings of the Sixth Social Media Mining for Health (# SMM4H) Workshop and Shared Task, pages 88–90.
  16. Diederik P Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR.
  17. Thomas N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations.
  18. Drug-disease graph: predicting adverse drug reaction signals via graph neural network with clinical data. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pages 633–644. Springer.
  19. Adverse drug reactions of spontaneous reports in shanghai pediatric population. PLoS One, 9(2):e89829.
  20. Exploiting adversarial transfer learning for adverse drug reaction detection from texts. Journal of Biomedical Informatics, 106:103431.
  21. Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks. Knowledge-Based Systems, 235:107643.
  22. BertGCN: Transductive Text Classification by Combining GCN and BERT. arXiv preprint arXiv:2105.05727.
  23. A structured self-attentive sentence embedding. In International Conference on Learning Representations.
  24. RoBERTa: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
  25. Yuan Luo. 2017. Recurrent neural networks for classifying relations in clinical notes. Journal of Biomedical Informatics, 72:85–95.
  26. Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive lstm. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32.
  27. Overview of the sixth social media mining for health applications (# SMM4H) shared tasks at NAACL 2021. In Proceedings of the Sixth Social Media Mining for Health (# SMM4H) Workshop and Shared Task, pages 21–32.
  28. Bertweet: A pre-trained language model for english tweets. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 9–14.
  29. Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features. Journal of the American Medical Informatics Association, 22(3):671–681.
  30. R OpenAI. 2023. Gpt-4 technical report. ArXiv, 2303.
  31. A joint learning approach with knowledge injection for zero-shot cross-lingual hate speech detection. Information Processing & Management, 58(4):102544.
  32. IIITN NLP at SMM4H 2021 Tasks: Transformer Models for Classification on Health-Related Imbalanced Twitter Datasets. In Proceedings of the Sixth Social Media Mining for Health (# SMM4H) Workshop and Shared Task, pages 118–122.
  33. Common sense knowledge based personality recognition from text. In Mexican International Conference on Artificial Intelligence, pages 484–496. Springer.
  34. GAR: Graph adversarial representation for adverse drug event detection on Twitter. Applied Soft Computing, 106:107324.
  35. A graph-boosted framework for adverse drug event detection on twitter. In 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 1129–1131. IEEE.
  36. Mda: An intelligent medical data augmentation scheme based on medical knowledge graph for chinese medical tasks. Applied Sciences, 12(20):10655.
  37. Medxn: an open source medication extraction and normalization tool for clinical text. Journal of the American Medical Informatics Association, 21(5):858–865.
  38. Clinical and economic burden of adverse drug reactions. Journal of Pharmacology & Pharmacotherapeutics, 4(Suppl1):S73.
  39. Medical knowledge graph to enhance fraud, waste, and abuse detection on claim data: model development and performance evaluation. JMIR Medical Informatics, 8(7):e17653.
  40. Attention is all you need. In Advances in Neural Information Processing Systems, pages 5998–6008.
  41. Graph attention networks. In International Conference on Learning Representations.
  42. Explainable detection of adverse drug reaction with imbalanced data distribution. PLoS Computational Biology, 18(6):e1010144.
  43. A study of deep learning approaches for medication and adverse drug event extraction from clinical text. Journal of the American Medical Informatics Association, 27(1):13–21.
  44. New approaches to drug safety: a pharmacovigilance tool kit. Nature Reviews Drug Discovery, 8(10):779–782.
  45. Detecting tweets mentioning drug name and adverse drug reaction with hierarchical tweet representation and multi-head self-attention. In Proceedings of the Third Social Media Mining for Health (# SMM4H) Workshop and Shared Task, pages 34–37.
  46. A dual-attention network for joint named entity recognition and sentence classification of adverse drug events. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, pages 3414–3423.
  47. Medex: a medication information extraction system for clinical narratives. Journal of the American Medical Informatics Association, 17(1):19–24.
  48. LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6442–6454.
  49. A mental state knowledge–aware and contrastive network for early stress and depression detection on social media. Information Processing & Management, 59(4):102961.
  50. Graph convolutional networks for text classification. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 7370–7377.
  51. Usama Yaseen and Stefan Langer. 2021. Neural Text Classification and Stacked Heterogeneous Embeddings for Named Entity Recognition in SMM4H 2021. In Proceedings of the Sixth Social Media Mining for Health (# SMM4H) Workshop and Shared Task, pages 83–87.
  52. An end-to-end deep learning architecture for graph classification. In Proceedings of the AAAI conference on artificial intelligence, volume 32.
  53. Adverse drug reaction detection via a multihop self-attention mechanism. BMC Bioinformatics, 20(1):1–11.
  54. Gated iterative capsule network for adverse drug reaction detection from social media. In 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 387–390. IEEE.
  55. Adversarial neural network with sentiment-aware attention for detecting adverse drug reactions. Journal of Biomedical Informatics, 123:103896.
  56. Every document owns its structure: Inductive text classification via graph neural networks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 334–339.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Shaoxiong Ji (39 papers)
  2. Ya Gao (35 papers)
  3. Pekka Marttinen (56 papers)
Citations (3)
View on Semantic Scholar