ABSTRACT
Adverse drug reaction (ADR) is one of the most important public health problems. Social media has encouraged more patients to share their medication experiences and has become a major source of unreported ADRs in the testing industry. However, since a large number of user posts do not mention any ADRs, it is difficult to accurately detect the presence of ADRs in each user post. An ADR extraction (ADRE) method from social media based on cascade feature extraction and meta-learner (CFEML) is proposed, including text pre-processing, word embedding, feature extraction and feature cascade, and classification by meta-learner. The experimental results show that ADRE based on CFEML can achieve good performance in the classification task of confirming the relationship between the "ADR" pairs in the description of ADRs, and the final model achieves accuracy of 85.52%. The results validate that the proposed method can help evaluators quickly obtain all possible ADRs from social media, and can be used to provide more research means for drug safety evaluation studies.
- Pappa D, Stergioulas L. (2019). Harnessing social media data for pharmacovigilance: a review of current state of the art, challenges and future directions. International Journal of Data Science and Analytics, 8(2):113-135.Google ScholarCross Ref
- Wang F, Ding Y, Lei X, Identifying gene signatures for cancer drug repositioning based on sample clustering. IEEE/ACM Trans Comput Biol Bioinform 2020;1–13. DOI:10.1109/TCBB.2020.3019781.Google ScholarDigital Library
- Yu Z, Huang F, Zhao X, Predicting drug-disease associations through layer attention graph convolutional network. Brief Bioinform 2021: 22(4):1–11.Google Scholar
- Chen J, Yuan Z, Peng J, DASNet: Dual attentive fully convolutional Siamese networks for change detection of high resolution satellite images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14(99): 1194-1205. DOI:10.1109/JSTARS.2020.3037893.Google ScholarCross Ref
- Monteiro NRC, Ribeiro B, Arrais J, Drug-target interaction prediction: end-to-end deep learning approach. IEEE/ACM Trans ComputBiol Bioinform 2020: 1-12. DOI:10.1109/TCBB.2020.2977335.13.Google ScholarCross Ref
- Wang H, Wang J, Dong C, A novel approach for drug-target interactions prediction based on multimodal deep autoencoder. Front Pharmacol 2020;10:1–19.Google Scholar
- Wang F, Lei X, Liao B, Wu F. Problem Solving Protocol Predicting drug–drug interactions by graph convolutional network with multi-kernel. Briefings in Bioinformatics, 2022, 23, 1–11. DOI: 10.1093/bib/bbab511Google ScholarCross Ref
- Bo X, Lin H, Zhao M, Detecting Potential Adverse Drug Reactions from Health-Related Social Networks. Springer International Publishing, 2016: 523–530.Google Scholar
- Liu J, Wang G. (2018). Pharmacovigilance from social media: An improved random subspace method for identifying adverse drug events. International Journal of Medical Informatics, 117(9):33-43.Google ScholarCross Ref
- Mcmaster C, D Liew, Keith C, A Machine-Learning Algorithm to Optimise Automated Adverse Drug Reaction Detection from Clinical Coding. Drug Safety, 2019, 42(6): 721-725.Google ScholarCross Ref
- Shen C, Lin H, Guo K, Detecting adverse drug reactions from social media based on multi-channel convolutional neural networks. Neural Computing and Applications, 2019, 31:4799–4808.Google ScholarDigital Library
- Fan, B., Fan, W., Smith, C., Garner, H. S. (2020). Adverse drug event detection and extraction from open data: a deep learning approach. Information Processing & Management, 57(1). DOI: 102131.1-102131.14.Google Scholar
- Zhang Y, Cui S, Gao H. Adverse drug reaction detection on social media with deep linguistic features. Journal of Biomedical Informatics, 2020, 106:103437.Google ScholarCross Ref
- Pourebrahim B, Keyvanpour M. Adverse Drug Reaction Detection Using Data Mining Techniques: A Review Article. 10th International Conference on Computer and Knowledge Engineering (ICCKE),2020:118-123.Google Scholar
- Rezaei Z, Komleh H, Eslami B, Adverse Drug Reaction Detection in Social Media by Deep Learning Methods. Cell Journal, 2020, 22(3):319-324.Google Scholar
- Wang X, Huang W, Zhang S. Social Media Adverse Drug Reaction Detection Based on Bi-LSTM with Multi-head Attention Mechanism. Intelligent Computing Theories and Application, 2021: 57–65.Google Scholar
- Jiang H, Lin Y, Ren W, Adverse drug reactions and correlations with drug–drug interactions: A retrospective study of reports from 2011 to 2020. Frontiers in Pharmacology, 2022. DOI:10.3389/fphar.2022.923939Google ScholarCross Ref
- Mikolov T, Chen K, Corrado G, Efficient Estimation of Word Representations in Vector Space. Computer Science, 2013. DOI: 10.48550/arXiv.1301.3781Google ScholarCross Ref
- Kumari A, Lobiyal D K. Efficient estimation of Hindi WSD with distributed word representation in vector space. Journal of King Saud University-Computer and Information Sciences, 2021. DOI: 10.1016/j.jksuci.2021.03.008.Google ScholarCross Ref
- Poleksic, A., Xie, L.J.S.R. (2019). "Database of adverse events associated with drugs and drug combinations," Scientific Reports, 9, 1-9.Google Scholar
- Zhang T, Lin H, Xu B, (2020c). "Gated iterative capsule network for adverse drug reaction detection from social media. IEEE International Conference on Bioinformatics and Biomedicine (BIBM): 387-390. DOI: 10.1109/BIBM49941.2020.9313092.Google ScholarCross Ref
- Rakhsha, M., Keyvanpour, M.R., and Shojaedini, S.V. (2021). "Detecting Adverse Drug Reactions from Social Media Based on Multichannel Convolutional Neural Networks Modified by Support Vector Machine", 7th International Conference on Web Research (ICWR): IEEE), 48-52.Google ScholarCross Ref
- Rezaei, Z., Ebrahimpour-Komleh, H., Eslami, B., Chavoshinejad, R., and Totonchi, M. (2020). "Adverse drug reaction detection in social media by deep learning methods," Cell Journal, 22(3), 319-324.Google Scholar
- Cocos, A., Fiks, A.G., and Masino, A.J.J.J.O.T.a.M.I.A. (2017). Deep learning for pharmacovigilance: recurrent neural network architectures for labeling adverse drug reactions in Twitter posts," Journal of the American Medical Informatics Association Jamia,24, 813-821.Google Scholar
- Shen, C., Lin, H., Guo, K., Xu, K., Yang, Z., and Wang, J. (2019). Detecting adverse drug reactions from social media based on multi-channel convolutional neural networks," Neural Computing and Applications, 31(9):4799-4808.Google Scholar
Index Terms
- Adverse Drug Reaction from Social Media by Cascade Feature Extraction and Meta-Learner
Recommendations
An ensemble method for extracting adverse drug events from social media
We propose a relation extraction system to distinguish between adverse drug events (ADEs) and non-ADEs on social media.We develop a feature-based method, investigate the effectiveness of feature selection, and analyze the contributions of different ...
Exploring adverse drug reactions of diabetes medicine using social media analytics and interactive visualizations
Highlights- A social media analytics framework with interactive visualizations is proposed.
AbstractThe aim of this study is to propose an automatic and real-time social media analytics framework with interactive data visualizations to support effective exploration of knowledge about adverse drug reaction (ADR) surveillance. This ...
Social media mining for drug safety signal detection
SHB '12: Proceedings of the 2012 international workshop on Smart health and wellbeingAdverse Drug Reactions (ADRs) represent a serious problem all over the world. They may complicate a patient's medical conditions and increase the morbidity, even mortality. Drug safety currently depends heavily on post-marketing surveillance, because ...
Comments