Display options
Cite
Zhang W, Peissig P, Kuang Z, et al. Adverse Drug Reaction Discovery from Electronic Health Records with Deep Neural Networks. Proc ACM Conf Health Inference Learn (2020). 2020;2020:30-39doi: 10.1145/3368555.3384459.
Zhang, W., Peissig, P., Kuang, Z., & Page, D. (2020). Adverse Drug Reaction Discovery from Electronic Health Records with Deep Neural Networks. Proceedings of the ACM Conference on Health, Inference, and Learning, 202030-39. https://doi.org/10.1145/3368555.3384459
Zhang, Wei, et al. "Adverse Drug Reaction Discovery from Electronic Health Records with Deep Neural Networks." Proceedings of the ACM Conference on Health, Inference, and Learning vol. 2020 (2020): 30-39. doi: https://doi.org/10.1145/3368555.3384459
Zhang W, Peissig P, Kuang Z, Page D. Adverse Drug Reaction Discovery from Electronic Health Records with Deep Neural Networks. Proc ACM Conf Health Inference Learn (2020). 2020 Apr;2020:30-39. doi: 10.1145/3368555.3384459. PMID: 33283213; PMCID: PMC7718770.
Copy Download .nbib Format: NLM
Share it on

Proc ACM Conf Health Inference Learn (2020). 2020 Apr;2020:30-39. doi: 10.1145/3368555.3384459.

Adverse Drug Reaction Discovery from Electronic Health Records with Deep Neural Networks.

Proceedings of the ACM Conference on Health, Inference, and Learning

Wei Zhang, Peggy Peissig, Zhaobin Kuang, David Page

Affiliations

  1. Computer Sciences Department, University of Wisconsin-Madison.
  2. Biomedical Informatics Research Center, Marshfield Clinic Research Institute.
  3. Computer Science Department, Stanford University.
  4. Department of Biostatistics and Bioinformatics, Duke University.

PMID: 33283213 PMCID: PMC7718770 DOI: 10.1145/3368555.3384459

Abstract

Adverse drug reactions (ADRs) are detrimental and unexpected clinical incidents caused by drug intake. The increasing availability of massive quantities of longitudinal event data such as electronic health records (EHRs) has redefined ADR discovery as a big data analytics problem, where data-hungry deep neural networks are especially suitable because of the abundance of the data. To this end, we introduce neural self-controlled case series (NSCCS), a deep learning framework for ADR discovery from EHRs. NSCCS rigorously follows a self-controlled case series design to adjust implicitly and efficiently for individual heterogeneity. In this way, NSCCS is robust to time-invariant confounding issues and thus more capable of identifying associations that reflect the underlying mechanism between various types of drugs and adverse conditions. We apply NSCCS to a large-scale, real-world EHR dataset and empirically demonstrate its superior performance with comprehensive experiments on a benchmark ADR discovery task.

Keywords: Adverse Drug Reaction Discovery; Deep Neural Networks; Electronic Health Records; Self-Controlled Case Series

References

  1. J Am Med Inform Assoc. 2010 Nov-Dec;17(6):652-62 - PubMed
  2. Proc Mach Learn Res. 2018 Jul;80:1714-1723 - PubMed
  3. Sci Transl Med. 2012 Mar 14;4(125):125ra31 - PubMed
  4. Pharmacoepidemiol Drug Saf. 2012 Jan;21 Suppl 1:9-11 - PubMed
  5. Clin Pharmacol Ther. 2012 Jun;91(6):1010-21 - PubMed
  6. Drug Saf. 2013 Oct;36 Suppl 1:S83-93 - PubMed
  7. Ann Intern Med. 2010 Nov 2;153(9):600-6 - PubMed
  8. Am J Epidemiol. 2013 Nov 1;178(9):1496-504 - PubMed
  9. IEEE Trans Neural Netw Learn Syst. 2019 Oct;30(10):3124-3136 - PubMed
  10. Expert Opin Drug Saf. 2012 Jan;11(1):83-94 - PubMed
  11. Stud Health Technol Inform. 2015;216:574-8 - PubMed
  12. IJCAI (U S). 2016 Jul;2016:2521-2528 - PubMed
  13. Methods Mol Biol. 2019;1903:255-267 - PubMed
  14. Biometrics. 2013 Dec;69(4):893-902 - PubMed
  15. Drug Saf. 2013 Oct;36 Suppl 1:S107-21 - PubMed
  16. Drug Saf. 2013 Oct;36 Suppl 1:S73-82 - PubMed
  17. KDD. 2017 Aug;2017:1537-1546 - PubMed
  18. Drug Saf. 2013 Oct;36 Suppl 1:S143-58 - PubMed
  19. Biometrics. 1988 Sep;44(3):837-45 - PubMed
  20. Proc Int Conf Mach Learn. 2020 Jul;119:11235-11245 - PubMed

Publication Types

Grant support