Skip to main content
SpringerLink
Log in

ImputeRNN: Imputing Missing Values in Electronic Medical Records

  • Conference paper
  • First Online:
Database Systems for Advanced Applications (DASFAA 2021)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 12683))

Included in the following conference series:

  • 2536 Accesses

Abstract

Electronic Medical Records (EMRs), which record visits of patients to the hospital, are the main resources for medical data analysis. However, plenty of missing values in EMRs limit the model capability for various researches in healthcare. Recently, many imputation methods have been proposed to address this challenging problem, but they fail to take medical bias into account. Medical bias is a ubiquitous phenomenon that the missingness of medical data is missing not at random because doctors prone to measure features related to the disease of patients. It reflects the physical conditions of patients, which helps impute missing data with accurate and practical values. In this paper, we propose a novel joint recurrent neural network (RNN) model called ImputeRNN, which considers medical bias for EMR imputation. We model the medical bias by an additional RNN based on a mask (missing or not) matrix, whose hidden vectors are incorporated into the model as contexts by a fusion layer. Extensive experiments on two real-world EMR datasets demonstrate that ImputeRNN outperforms state-of-the-art methods on imputation and downstream prediction tasks.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 139.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://github.com/iskandr/fancyimpute.

References

  1. Agniel, D., Kohane, I.S., Weber, G.M.: Biases in electronic health record data due to processes within the healthcare system: retrospective observational study. Br. Med. J. 361 (2018)

    Google Scholar 

  2. Cao, W., Wang, D., Li, J., Zhou, H., Li, L., Li, Y.: BRITS: bidirectional recurrent imputation for time series. In: Advances in Neural Information Processing Systems, NeurIPS, pp. 6776–6786 (2018)

    Google Scholar 

  3. Che, Z., Purushotham, S., Cho, K., Sontag, D.A., Liu, Y.: Recurrent neural networks for multivariate time series with missing values. Sci. Rep. 8(1), 1–12 (2018)

    Google Scholar 

  4. Che, Z., Purushotham, S., Li, M.G., Jiang, B., Liu, Y.: Hierarchical deep generative models for multi-rate multivariate time series. In: International Conference on Machine Learning, ICML, vol. 80, pp. 783–792 (2018)

    Google Scholar 

  5. Fan, J., Zhang, Y., Udell, M.: Polynomial matrix completion for missing data imputation and transductive learning. In: Association for the Advancement of Artificial Intelligence, AAAI, pp. 3842–3849 (2020)

    Google Scholar 

  6. García-Laencina, P.J., Sancho-Gómez, J., Figueiras-Vidal, A.R., Verleysen, M.: K nearest neighbours with mutual information for simultaneous classification and missing data imputation. Neurocomputing 72(7–9), 1483–1493 (2009)

    Article  Google Scholar 

  7. Haneuse, S., Daniels, M.: A general framework for considering selection bias in EHR-based studies: what data are observed and why? Gener. Evid. Methods Improve Patient Outcomes 4(1), 1203–1203 (2016)

    Google Scholar 

  8. Jerez, J.M., et al.: Missing data imputation using statistical and machine learning methods in a real breast cancer problem. Artif. Intell. Med. 50(2), 105–115 (2010)

    Article  Google Scholar 

  9. Johnson, A.E., et al.: MIMIC-III, a freely accessible critical care database. Sci. Data 3(1), 1–9 (2016)

    Article  Google Scholar 

  10. Khayati, M., Lerner, A., Tymchenko, Z., Cudré-Mauroux, P.: Mind the gap: an experimental evaluation of imputation of missing values techniques in time series. Proc. VLDB Endow. 13(5), 768–782 (2020)

    Article  Google Scholar 

  11. Kiela, D., Grave, E., Joulin, A., Mikolov, T.: Efficient large-scale multi-modal classification. In: Association for the Advancement of Artificial Intelligence, AAAI, pp. 5198–5204 (2018)

    Google Scholar 

  12. Kim, Y., Chi, M.: Temporal belief memory: imputing missing data during RNN training. In: International Joint Conference on Artificial Intelligence, IJCAI, pp. 2326–2332 (2018)

    Google Scholar 

  13. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, ICLR (2015)

    Google Scholar 

  14. Li, S.C., Jiang, B., Marlin, B.M.: MisGAN: learning from incomplete data with generative adversarial networks. In: International Conference on Learning Representations, ICLR (2019)

    Google Scholar 

  15. Luo, J., Ye, M., Xiao, C., Ma, F.: HiTANet: hierarchical time-aware attention networks for risk prediction on electronic health records. In: Special Interest Group on Knowledge Discovery in Data, SIGKDD, pp. 647–656 (2020)

    Google Scholar 

  16. Luo, Y., Cai, X., Zhang, Y., Xu, J., Yuan, X.: Multivariate time series imputation with generative adversarial networks. In: Advances in Neural Information Processing Systems, NeurIPS, pp. 1603–1614 (2018)

    Google Scholar 

  17. Luo, Y., Zhang, Y., Cai, X., Yuan, X.: E\({^2}\)GAN: end-to-end generative adversarial network for multivariate time series imputation. In: International Joint Conference on Artificial Intelligence, IJCAI, pp. 3094–3100 (2019)

    Google Scholar 

  18. MacNamee, B., Cunningham, P., Byrne, S., Corrigan, O.I.: The problem of bias in training data in regression problems in medical decision support. Artif. Intell. Med. 24(1), 51–70 (2002)

    Article  Google Scholar 

  19. Ovalle, J.E.A., Solorio, T., Montes-y-Gómez, M., González, F.A.: Gated multimodal units for information fusion. In: International Conference on Learning Representations, ICLR (2017)

    Google Scholar 

  20. Phelan, M., Bhavsar, N.A., Goldstein, B.A.: Illustrating informed presence bias in electronic health records data: how patient interactions with a health system can impact inference. Gener. Evid. Methods Improve Patient Outcomes 5(1), 22 (2017)

    Article  Google Scholar 

  21. Pivovarov, R., Albers, D.J., Sepulveda, J.L., Elhadad, N.: Identifying and mitigating biases in EHR laboratory tests. Biomed. Inform. 51, 24–34 (2014)

    Article  Google Scholar 

  22. Purushotham, S., Meng, C., Che, Z., Liu, Y.: Benchmarking deep learning models on large healthcare datasets. Biomed. Inform. 83, 112–134 (2018)

    Article  Google Scholar 

  23. Salakhutdinov, R., Mnih, A.: Probabilistic matrix factorization. In: Advances in Neural Information Processing Systems, NeurIPS, pp. 1257–1264 (2007)

    Google Scholar 

  24. Silva, I., Moody, G., Scott, D.J., Celi, L.A., Mark, R.G.: Predicting in-hospital mortality of ICU patients: the PhysioNet/computing in cardiology challenge 2012. Comput. Cardiol. 39, 245–248 (2012)

    Google Scholar 

  25. Smieja, M., Struski, L., Tabor, J., Zielinski, B., Spurek, P.: Processing of missing data by neural networks. In: Advances in Neural Information Processing Systems, NeurIPS, pp. 2724–2734 (2018)

    Google Scholar 

  26. Sportisse, A., Boyer, C., Josse, J.: Estimation and imputation in probabilistic principal component analysis with missing not at random data. In: Advances in Neural Information Processing Systems, NeurIPS (2020)

    Google Scholar 

  27. Sterne, J.A., et al.: Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls. Br. Med. J. 338 (2009)

    Google Scholar 

  28. Tang, X., Yao, H., Sun, Y., Aggarwal, C.C., Mitra, P., Wang, S.: Joint modeling of local and global temporal dynamics for multivariate time series forecasting with missing values. In: Association for the Advancement of Artificial Intelligence, AAAI, pp. 5956–5963 (2020)

    Google Scholar 

  29. Vassy, J., et al.: Yield and bias in defining a cohort study baseline from electronic health record data. Biomed. Inform. 78, 54–59 (2018)

    Article  Google Scholar 

  30. Yadav, P., Steinbach, M.S., Kumar, V., Simon, G.J.: Mining electronic health records (EHRs): a survey. ACM Comput. Surv. 50(6), 85:1–85:40 (2018)

    Google Scholar 

  31. Yoon, J., Jordon, J., van der Schaar, M.: GAIN: missing data imputation using generative adversarial nets. In: International Conference on Machine Learning, ICML, vol. 80, pp. 5675–5684 (2018)

    Google Scholar 

  32. Yoon, J., Zame, W.R., van der Schaar, M.: Estimating missing data in temporal data streams using multi-directional recurrent neural networks. IEEE Trans. Biomed. Eng. 66(5), 1477–1490 (2019)

    Article  Google Scholar 

  33. Zheng, K., Gao, J., Ngiam, K.Y., Ooi, B.C., Yip, J.W.L.: Resolving the bias in electronic medical records. In: Special Interest Group on Knowledge Discovery in Data, SIGKDD, pp. 2171–2180 (2017)

    Google Scholar 

Download references

Acknowledgements

This work is supported by Chinese Scientific and Technical Innovation Project 2030 (No. 2018AAA0102100), NSFC-General Technology Joint Fund for Basic Research (No. U1936206, No. U1836109), National Natural Science Foundation of China (No. 61772289, No. U1903128, and No. 62002178), and Natural Science Foundation of Tianjin, China (No. 20JCQNJC01730).

Author information

Authors and Affiliations

  1. College of Computer Science, Nankai University, Tianjin, 300350, China

    Jiawei Ouyang, Ying Zhang & Xiaojie Yuan

  2. College of Cyber Science, Nankai University, Tianjin, 300350, China

    Yuhao Zhang, Xiangrui Cai & Xiaojie Yuan

  3. Tianjin Key Laboratory of Network and Data Security Technology, Tianjin, 300350, China

    Jiawei Ouyang, Yuhao Zhang, Xiangrui Cai, Ying Zhang & Xiaojie Yuan

Authors
  1. Jiawei Ouyang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuhao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiangrui Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ying Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiaojie Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiangrui Cai .

Editor information

Editors and Affiliations

  1. Aalborg University, Aalborg, Denmark

    Christian S. Jensen

  2. Singapore Management University, Singapore, Singapore

    Ee-Peng Lim

  3. Academia Sinica, Taipei, Taiwan

    De-Nian Yang

  4. The Pennsylvania State University, University Park, PA, USA

    Wang-Chien Lee

  5. National Chiao Tung University, Hsinchu, Taiwan

    Vincent S. Tseng

  6. Athens University of Economics and Business, Athens, Greece

    Vana Kalogeraki

  7. National Cheng Kung University, Tainan City, Taiwan

    Jen-Wei Huang

  8. National Tsing Hua University, Hsinchu, Taiwan

    Chih-Ya Shen

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ouyang, J., Zhang, Y., Cai, X., Zhang, Y., Yuan, X. (2021). ImputeRNN: Imputing Missing Values in Electronic Medical Records. In: Jensen, C.S., et al. Database Systems for Advanced Applications. DASFAA 2021. Lecture Notes in Computer Science(), vol 12683. Springer, Cham. https://doi.org/10.1007/978-3-030-73200-4_28

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-73200-4_28

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-73199-1

  • Online ISBN: 978-3-030-73200-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation