Advertisement

A Machine Learning Approach to Classification of Case Reports on Adverse Drug Reactions Using Text Mining of Expert Opinions

  • Hyon Hee Kim
  • Ki Yon Rhew
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 474)

Abstract

In this paper, we present a machine-learning approach to classify case reports on adverse drug reactions according to the causal relationship of adverse drug reactions (ADR). For this purpose, the Naïve Bayes classification algorithm is combined with text mining technique, and applied to textual data of expert opinion on ADR case reports in the Korea Adverse Event Reporting System database. The proposed algorithm classifies the case reports into three categories such as possible, probable, and unlikely based on the causal relationship. Our experimental results show that the precision and recall of data belonging to possible is much higher than the other data belonging to probable and unlikely. We believe that our approach can be used not only for signal but also for prediction and prevention of ADRs.

Keywords

Naïve Bayes classifier Classification of case reports Causal relationship of ADRs Combining text mining and machine learning 

Notes

Acknowledgments

This research was supported by a grant (16172MFDS163) from a Ministry of Food and Drug Safety in 2016.

References

  1. 1.
    WHO: Safety of Medicines – a guide to detecting and reporting adverse drug reactions (2002)Google Scholar
  2. 2.
    Lee, J.: Polypharmacy and inappropriate drug prescription in community-dwelling elderly. J. Korean Acad. Family Med. 29(12), 925–931 (2008)Google Scholar
  3. 3.
    Smyth, R., et al.: Adverse drug reactions in children-a systematic review. PLoS ONE 7(3), e24061 (2012)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Korea Institute of Drug Safety and Risk Management. http://www.drugsafe.or.kr/
  5. 5.
    Hauben, M., et al.: Data mining in pharmacovigilance. Drug Saf. 28(10), 835–842 (2005)CrossRefGoogle Scholar
  6. 6.
    DuMouchel, W.: Bayesian data mining in large frequency tables, with an application to the FDA spontaneous reporting system. Am. Stat. 53(3), 177–190 (1999)Google Scholar
  7. 7.
    Fujiwara, M., Kawasaki, Y., Yamada, H.: A pharmacovigilance approach for post-marketing in Japan using the Japanese adverse drug event report database and association analysis. PLoS ONE 11(4), e0154425 (2016)CrossRefGoogle Scholar
  8. 8.
    Lee, Y.: Development of Mining model through reproducibility assessment in adverse drug event surveillance system. J. Korea Soc. Comput. Inf. 14(3), 183–192 (2009)Google Scholar
  9. 9.
    Harpaz, R., et al.: Text mining for adverse drug events: the promise. Challenges State Art Drug Saf. 37, 777–790 (2014)CrossRefGoogle Scholar
  10. 10.
    Uppsala Monitoring Centre. https://www.who-umc.org/
  11. 11.
    Lantz, B.: Machine Learning with R. PACKT Publishing, Birmingham (2013)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Dongduk Women’s UniversitySeoulSouth Korea

Personalised recommendations