Advertisement

Adverse Drug Reaction Mentions Extraction from Drug Labels: An Experimental Study

  • Ed-drissiya El-allalyEmail author
  • Mourad Sarrouti
  • Noureddine En-Nahnahi
  • Said Ouatik El Alaoui
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 914)

Abstract

Adverse Drug Reactions (ADRs), unintended and sometimes dangerous effects that a drug may have, are a serious health problem and a leading cause of death. Therefore, it is of vital importance to identify ADRs properly and in a timely manner from drug labels. In this paper, we explore both machine learning and deep learning approaches in extracting adverse reaction mentions and modifier terms such as negation, severity, and drug class from drug labels. We investigated Conditional Random Fields (CRF) as a machine learning method, and both Recurrent Neural Network (RNN) and Bidirectional Recurrent Neural Network (Bi-RNN) as deep learning methods. These methods are widely used in biomedical named entity recognition. Experimental evaluations performed on the publicly available datasets SPL-ADR-200db, provided by the TAC 2017 ADRs challenge, show that Bi-RNN achieves good performances compared with RNN and CRF. Bi-RNN outperforms RNN and CRF by an average of 4% and 4.7% in terms of F1-score, respectively.

Keywords

Adverse Drug Reaction Recurrent Neural Network Bidirectional Recurrent Neural Network Conditional Random Fields Biomedical Named Entity Recognition Natural Language Processing 

Notes

Acknowledgment

The authors would like to thank the TAC 2017 ADRs challenge [6] organizers who provided the datasets used in this study for evaluating ADR mentions extraction methods.

References

  1. 1.
    Ji, Y., Ying, H., Dews, P., Mansour, A., Tran, J., Miller, R.E., Massanari, R.M.: A potential causal association mining algorithm for screening adverse drug reactions in postmarketing surveillance. IEEE Trans. Inf. Technol. Biomed. 15(3), 428–437 (2011).  https://doi.org/10.1109/titb.2011.2131669CrossRefGoogle Scholar
  2. 2.
    Segura-Bedmar, I., Martínez, P.: Pharmacovigilance through the development of text mining and natural language processing techniques. J. Biomed. Inform. 58, 288–291 (2015).  https://doi.org/10.1016/j.jbi.2015.11.001CrossRefGoogle Scholar
  3. 3.
    Harpaz, R., Callahan, A., Tamang, S., Low, Y., Odgers, D., Finlayson, S., Jung, K., LePendu, P., Shah, N.H.: Text mining for adverse drug events: the promise, challenges, and state of the art. Drug Saf. 37(10), 777–790 (2014).  https://doi.org/10.1007/s40264-014-0218-zCrossRefGoogle Scholar
  4. 4.
    Russo, E., Palleria, C., Leporini, C., Chimirri, S., Marrazzo, G., Sacchetta, S., Bruno, L., Lista, R., Staltari, O., Scuteri, A., Scicchitano, F.: Limitations and obstacles of the spontaneous adverse drugs reactions reporting: two “challenging” case reports. J. Pharmacol. Pharmacother. 4(5), 66 (2013).  https://doi.org/10.4103/0976-500x.120955CrossRefGoogle Scholar
  5. 5.
    Fung, K.W., Jao, C.S., Demner-Fushman, D.: Extracting drug indication information from structured product labels using natural language processing. J. Am. Med. Inform. Assoc. 20(3), 482–488 (2013).  https://doi.org/10.1136/amiajnl-2012-001291CrossRefGoogle Scholar
  6. 6.
    Roberts K., Demner-Fushman D., Tonning J.M.: Overview of the TAC 2017 Adverse Reaction Extraction from Drug Labels Track Background: Adverse Drug Reactions (2017). https://bionlp.nlm.nih.gov/tac2017adversereactions/
  7. 7.
    Rios A., Kavuluru R.: Convolutional neural networks for biomedical text classification. In: Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics - BCB 2015. ACM Press (2015).  https://doi.org/10.1145/2808719.2808746
  8. 8.
    Wang, Y., Wu, S., Li, D., Mehrabi, S., Liu, H.: A part-of-speech term weighting scheme for biomedical information retrieval. J. Biomed. Inform. 63, 379–389 (2016).  https://doi.org/10.1016/j.jbi.2016.08.026CrossRefGoogle Scholar
  9. 9.
    Hu, Z., Zhang, Z., Yang, H., Chen, Q., Zuo, D.: A deep learning approach for predicting the quality of online health expert question-answering services. J. Biomed. Inform. 71, 241–253 (2017).  https://doi.org/10.1016/j.jbi.2017.06.012CrossRefGoogle Scholar
  10. 10.
    Sarrouti, M., Alaoui, S.O.E.: A passage retrieval method based on probabilistic information retrieval model and UMLS concepts in biomedical question answering. J. Biomed. Inform. 68, 96–103 (2017).  https://doi.org/10.1016/j.jbi.2017.03.001CrossRefGoogle Scholar
  11. 11.
    Sarrouti, M., Alaoui, S.O.E.: A machine learning-based method for question type classification in biomedical question answering. Methods Inf. Med. 56(03), 209–216 (2017).  https://doi.org/10.3414/me16-01-0116CrossRefGoogle Scholar
  12. 12.
    Sarrouti, M., Lachkar, A.: A new and efficient method based on syntactic dependency relations features for ad hoc clinical question classification. Int. J. Bioinform. Res. Appl. 13(2), 161 (2017).  https://doi.org/10.1504/ijbra.2017.083150CrossRefGoogle Scholar
  13. 13.
    Sarrouti, M., Alaoui, S.O.E.: A yes/no answer generator based on sentiment-word scores in biomedical question answering. Int. J. Healthc. Inf. Syst. Inform. 12(3), 62–74 (2017).  https://doi.org/10.4018/ijhisi.2017070104CrossRefGoogle Scholar
  14. 14.
    Sarrouti M., El Alaoui S.O.: A biomedical question answering system in BioASQ 2017. In: BioNLP 2017, Association for Computational Linguistics (2017).  https://doi.org/10.18653/v1/w17-2337
  15. 15.
    Sarrouti M., El Alaoui S.O.: A generic document retrieval framework based on UMLS similarity for biomedical question answering system. In: Intelligent Decision Technologies 2016, pp. 207–216. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-39627-9_18CrossRefGoogle Scholar
  16. 16.
    Demner-Fushman, D., Shooshan, S.E., Rodriguez, L., Aronson, A.R., Lang, F., Rogers, W., Roberts, K., Tonning, J.: A dataset of 200 structured product labels annotated for adverse drug reactions. Sci. Data 5, 180001 (2018).  https://doi.org/10.1038/sdata.2018.1CrossRefGoogle Scholar
  17. 17.
    Almas, T., Archana, B.: A survey on biomedical named entity extraction. Asian J. Eng. Technol. Innov. 4, 25–28 (2016)Google Scholar
  18. 18.
    Rindflesch T.C., Tanabe L., Weinstein J.N., Hunter L.: EDGAR: extraction of drugs, genes and relations from the biomedical literature. In: Biocomputing 2000, World scientific (1999).  https://doi.org/10.1142/9789814447331_0049
  19. 19.
    Song, M., Yu, H., Han, W.-S.: Developing a hybrid dictionary-based bio-entity recognition technique. BMC Med. Inform. Decis. Mak. 15(S1) (2015).  https://doi.org/10.1186/1472-6947-15-s1-s9
  20. 20.
    Tuason O., Chen, L., Liu, H., Blake, J., Friedman, C.: Biological nomenclatures: a source of lexical knowledge and ambiguity. In: Biocomputing 2004, World scientific (2003).  https://doi.org/10.1142/9789812704856_0023
  21. 21.
    Zeng, Q.T., Goryachev, S., Weiss, S., Sordo, M., Murphy, S.N., Lazarus, R.: Extracting principal diagnosis, co-morbidity and smoking status for asthma research: evaluation of a natural language processing system. BMC Med. Inform. Decis. Mak. 6(1) (2006).  https://doi.org/10.1186/1472-6947-6-30
  22. 22.
    Hanisch, D., Fundel, K., Mevissen, H.T., Zimmer, R., Fluck, J.: ProMiner: rule-based protein and gene entity recognition. BMC Bioinform. 6(Suppl 1), S14 (2005)CrossRefGoogle Scholar
  23. 23.
    Zhao, S.: Named entity recognition in biomedical texts using an HMM model. In: Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications - JNLPBA 2004. Association for Computational Linguistics (2004).  https://doi.org/10.3115/1567594.1567613
  24. 24.
    Zhang, J., Shen, D., Zhou, G., Su, J., Tan, C.-L.: Enhancing HMM-based biomedical named entity recognition by studying special phenomena. J. Biomed. Inform. 37(6), 411–422 (2004).  https://doi.org/10.1016/j.jbi.2004.08.005CrossRefGoogle Scholar
  25. 25.
    Settles, B.: Biomedical named entity recognition using conditional random fields and rich feature sets. In: Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications - JNLPBA 2004. Association for Computational Linguistics (2004).  https://doi.org/10.3115/1567594.1567618
  26. 26.
    Wang, H., Zhao, T., Li, S., Yu, H.: A conditional random fields approach to biomedical named entity recognition. J. Electron. (China) 24(6), 838–844 (2007).  https://doi.org/10.1007/s11767-006-0255-6CrossRefGoogle Scholar
  27. 27.
    Takeuchi, K., Collier, N.: Bio-medical entity extraction using support vector machines. In: Proceedings of the ACL 2003 workshop on Natural language processing in biomedicine. Association for Computational Linguistics (2003).  https://doi.org/10.3115/1118958.1118966
  28. 28.
    Kazama, J., Makino, T., Ohta, Y., Tsujii, J.: Tuning support vector machines for biomedical named entity recognition. In: Proceedings of the ACL 2002 workshop on Natural language processing in the biomedical domain. Association for Computational Linguistics (2002).  https://doi.org/10.3115/1118149.1118150
  29. 29.
    Li, D., Kipper-Schuler, K., Savova, G.: Conditional random fields and support vector machines for disorder named entity recognition in clinical texts. In: Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing - BioNLP 2008. Association for Computational Linguistics (2008).  https://doi.org/10.3115/1572306.1572326
  30. 30.
    Elman, J.L.: Finding structure in time. Cogn. Sci. 14(2), 179–211 (1990).  https://doi.org/10.1207/s15516709cog1402_1CrossRefGoogle Scholar
  31. 31.
    Yao, L., Liu, H., Liu, Y., Li, X., Anwar, M.W.: Biomedical named entity recognition based on deep neutral network. Int. J. Hybrid Inf. Technol. 8(8), 279–288 (2015).  https://doi.org/10.14257/ijhit.2015.8.8.29CrossRefGoogle Scholar
  32. 32.
    Unanue, I.J., Borzeshi, E.Z., Piccardi, M.: Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition. J. Biomed. Inform. 76, 102–109 (2017).  https://doi.org/10.1016/j.jbi.2017.11.007CrossRefGoogle Scholar
  33. 33.
    Zhang, D., Tan, X.: Relation Classification via Recurrent Neural Network (2015). CoRR abs/1508.01006Google Scholar
  34. 34.
    Luo, Y.: Recurrent neural networks for classifying relations in clinical notes. J. Biomed. Inform. 72, 85–95 (2017).  https://doi.org/10.1016/j.jbi.2017.07.006CrossRefGoogle Scholar
  35. 35.
    Werbos, P.: Backpropagation through time: what it does and how to do it. Proc. IEEE 78(10), 1550–1560 (1990).  https://doi.org/10.1109/5.58337CrossRefGoogle Scholar
  36. 36.
    Song, D., Shuang, L., Jin, L., Huang, D.: Biomedical named entity recognition based on recurrent neural networks with different extended methods. Int. J. Data Min. Bioinform. 16(1), 17 (2016).  https://doi.org/10.1504/ijdmb.2016.079799CrossRefGoogle Scholar
  37. 37.
    Stanovsky, G., Gruhl, D., Mendes, P.: Recognizing mentions of adverse drug reaction in social media using knowledge-infused recurrent models. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (vol. 1, Long Papers). Association for Computational Linguistics (2017).  https://doi.org/10.18653/v1/e17-1014
  38. 38.
    Sahu, S., Anand, A.: Recurrent neural network models for disease name recognition using domain invariant features. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (vol. 1, Long Papers). Association for Computational Linguistics (2016).  https://doi.org/10.18653/v1/p16-1209
  39. 39.
    Lafferty, J.D., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: International Conference on Machine Learning (ICML) (2001)Google Scholar
  40. 40.
    Campos, D., Matos, S., Luis, J.: Biomedical named entity recognition: a survey of machine-learning tools. In: Theory and Applications for Advanced Text Mining, InTech (2012).  https://doi.org/10.5772/51066Google Scholar
  41. 41.
    Tieleman, T., Hinton, G.: Lecture 6.5—RmsProp: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. (2012)Google Scholar
  42. 42.
    Okazaki, N.: Crfsuite: a fast implementation of conditional random fields (crfs) (2007). http://www.chokkan.org/software/crfsuite/
  43. 43.
    Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Improving neural networks by preventing co-adaptation of feature detectors (2012). CoRR abs/1207.0580Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Ed-drissiya El-allaly
    • 1
    Email author
  • Mourad Sarrouti
    • 1
  • Noureddine En-Nahnahi
    • 1
  • Said Ouatik El Alaoui
    • 1
  1. 1.Laboratory of Informatics and Modeling, FSDMSidi Mohammed Ben Abdellah UniversityFezMorocco

Personalised recommendations