An Explainable Approach of Inferring Potential Medication Effects from Social Media Data

  • Keyuan JiangEmail author
  • Tingyu Chen
  • Liyuan Huang
  • Ravish Gupta
  • Ricardo A. Calix
  • Gordon R. Bernard
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11979)


Understanding medication effects is an important activity in pharmacovigilance in which patients are the most important contributor. Social media, where users share their personal experiences of medication effects, have been recommended as an alternative data source of gathering signal information of suspected medication effects. To discover potential medication-effect relations from Twitter data, we devised a method employing analogical reasoning with neural embedding of Twitter text. The process involves learning the neural embedding from unlabeled tweets and performing vector arithmetic, making it obscure to understand how an inferred relation is derived. To make the process understandable and interpretable and to facilitate the decision making on accepting or rejecting any inferred medication-effect relations, we added explanation(s) to each step of the process. An example of inferred relation is provided to demonstrate the effectiveness of our approach in explaining how the result of each step is derived.


Pharmacovigilance Medication effects Social media Analogical reasoning Explainable machine learning 



Authors wish to thank anonymous reviewers for their critiques and constructive comments that helped improve the final manuscript. This work was supported in part by the US National Institutes of Health Grant 1R15LM011999-01.

Ethics Compliance

The protocol of this project was reviewed and approved for compliance with the human subject research regulation by the Institutional Review Board of Purdue University.


  1. 1.
    Pirmohamed, M., et al.: Adverse drug reactions as cause of admission to hospital: prospective analysis of 18 820 patients. BMJ 329(7456), 15–19 (2004)CrossRefGoogle Scholar
  2. 2.
    Lazarou, J., Pomeranz, B.H., Corey, P.N.: Incidence of adverse drug reactions in hospitalized patients: a meta-analysis of prospective studies. JAMA 279(15), 1200–1205 (1998)CrossRefGoogle Scholar
  3. 3.
    Moore, T.J., Cohen, M.R., Furberg, C.D.: Serious adverse drug events reported to the Food and Drug Administration, 1998–2005. Arch. Intern. Med. 167(16), 1752–1759 (2007)CrossRefGoogle Scholar
  4. 4.
    Levinson, D.R., General, I.: Adverse events in hospitals: national incidence among Medicare beneficiaries. Department of Health & Human Services (2010)Google Scholar
  5. 5.
    Härmark, L., et al.: Patient-reported safety information: a renaissance of pharmacovigilance? Drug Saf. 39(10), 883–890 (2016)CrossRefGoogle Scholar
  6. 6.
    Golder, S., Norman, G., Loke, Y.K.: Systematic review on the prevalence, frequency and comparative value of adverse events data in social media. Br. J. Clin. Pharmacol. 80(4), 878–888 (2015)CrossRefGoogle Scholar
  7. 7.
    Mikolov, T., Yih, W.T., Zweig, G.: Linguistic regularities in continuous space word representations. In: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 746–751 (2013)Google Scholar
  8. 8.
    Adice International Limited: The Erice manifesto: for global reform of the safety of medicines in patient care. Drug Saf. 30(3), 187–190 (2007)CrossRefGoogle Scholar
  9. 9.
    De Marneffe, M.C., MacCartney, B., Manning, C.D.: Generating typed dependency parses from phrase structure parses. LREC 6, 449–454 (2006)Google Scholar
  10. 10.
    Rindflesch, T.C., Fiszman, M.: The interaction of domain knowledge and linguistic structure in natural language processing: interpreting hypernymic propositions in biomedical text. J. Biomed. Inform. 36(6), 462–477 (2003)CrossRefGoogle Scholar
  11. 11.
    Google Code Archive, word2vec.
  12. 12.
    Kuhn, M., Letunic, I., Jensen, L.J., Bork, P.: The SIDER database of drugs and side effects. Nucleic Acids Res. 44(D1), D1075–D1079 (2015)CrossRefGoogle Scholar
  13. 13.
    Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: International Conference on Learning Representations (2013)Google Scholar
  14. 14.
    Bodenreider, O.: The unified medical language system (UMLS): integrating biomedical terminology. Nucleic acids research 32(suppl_1), D267–D270 (2004)CrossRefGoogle Scholar
  15. 15.
    Zeng, Q.T., Tse, T.: Exploring and developing consumer health vocabularies. J. Am. Med. Inform. Assoc. 13(1), 24–29 (2006)CrossRefGoogle Scholar
  16. 16.
    Kilicoglu, H., Rosemblat, G., Fiszman, M., Rindflesch, T.C.: Constructing a semantic predication gold standard from the biomedical literature. BMC Bioinform. 12(1), 486 (2011)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Keyuan Jiang
    • 1
    Email author
  • Tingyu Chen
    • 1
  • Liyuan Huang
    • 1
  • Ravish Gupta
    • 2
  • Ricardo A. Calix
    • 1
  • Gordon R. Bernard
    • 3
  1. 1.Purdue University NorthwestHammondUSA
  2. 2.Amazon.comSeattleUSA
  3. 3.Vanderbilt UniversityNashvilleUSA

Personalised recommendations