Modeling Patient Visit Using Electronic Medical Records for Cost Profile Estimation

  • Kangzhi ZhaoEmail author
  • Yong Zhang
  • Zihao Wang
  • Hongzhi Yin
  • Xiaofang Zhou
  • Jin Wang
  • Chunxiao Xing
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10828)


Estimating health care cost of patients provides promising opportunities for better management and treatment to medical providers and patients. Existing clinical approaches only focus on patient’s demographics and historical diagnoses but ignore ample information from clinical records. In this paper, we formulate the problem of patient’s cost profile estimation and use Electronic Medical Records (EMRs) to model patient visit for better estimating future health care cost. The performance of traditional learning based methods suffered from the sparseness and high dimensionality of EMR dataset. To address these challenges, we propose Patient Visit Probabilistic Generative Model (PVPGM) to describe a patient’s historical visits in EMR. With the help of PVPGM, we can not only learn a latent patient condition in a low dimensional space from sparse and missing data but also hierarchically organize the high dimensional EMR features. The model finally estimates the patient’s health care cost through combining the effects learned both from the latent patient condition and the generative process of medical procedure. We evaluate the proposed model on a large collection of real-world EMR dataset with 836,033 medical visits from over 50,000 patients. Experimental results demonstrate the effectiveness of our model.


Electronic medical records Cost profile estimation Health care data mining Probabilistic generative model 



This work was supported by NSFC (91646202), the National High-tech R&D Program of China (SS2015AA020102), NSSFC (15CTQ028), Research/Project 2017YB142 supported by Ministry of Education of The People’s Republic of China, the 1000-Talent program and Tsinghua Fudaoyuan Research Fund.


  1. 1.
    Ash, A.S., Ellis, R.P., Pope, G.C., Ayanian, J.Z., Bates, D.W., Burstin, H., Iezzoni, L.I., MacKay, E., Yu, W.: Using diagnoses to describe populations and predict costs. Health Care Financ. Rev. 21(3), 7 (2000)Google Scholar
  2. 2.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3(Jan), 993–1022 (2003)zbMATHGoogle Scholar
  3. 3.
    Breiman, L., Friedman, J., Stone, C.J., Olshen, R.A.: Classification and Regression Trees. CRC Press, Boca Raton (1984)zbMATHGoogle Scholar
  4. 4.
    Caballero Barajas, K.L., Akella, R.: Dynamically modeling patient’s health state from electronic medical records: a time series approach. In: KDD, pp. 69–78 (2015)Google Scholar
  5. 5.
    Chang, C., Lin, C.: LIBSVM: a library for support vector machines. ACM TIST 2(3), 27:1–27:27 (2011)Google Scholar
  6. 6.
    Feld, S.I., Cobian, A.G., Tevis, S.E., Kennedy, G.D., Craven, M.: Modeling the temporal evolution of postoperative complications. In: AMIA (2016)Google Scholar
  7. 7.
    Fetter, R.B., Shin, Y., Freeman, J.L., Averill, R.F., Thompson, J.D.: Case mix definition by diagnosis-related groups. Med. Care 18(2), i–53 (1980)Google Scholar
  8. 8.
    Fleishman, J.A., Cohen, J.W.: Using information on clinical conditions to predict high-cost patients. Health Serv. Res. 45(2), 532–552 (2010)CrossRefGoogle Scholar
  9. 9.
    Hajian-Tilaki, K.: Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Casp. J. Internal Med. 4(2), 627 (2013)Google Scholar
  10. 10.
    Horn, S.D., Bulkley, G., Sharkey, P.D., Chambers, A.F., Horn, R.A., Schramm, C.J.: Interhospital differences in severity of illness: problems for prospective payment based on diagnosis-related groups (DRGs). N. Engl. J. Med. 313(1), 20–24 (1985)CrossRefGoogle Scholar
  11. 11.
    Jolliffe, I.T.: Principal component analysis and factor analysis. In: Jolliffe, I.T. (ed.) Principal Component Analysis, pp. 115–128. Springer, New York (1986). Scholar
  12. 12.
    Koh, H.C., Tan, G., et al.: Data mining applications in healthcare. J. Healthc. Inf. Manag. 19(2), 65 (2011)Google Scholar
  13. 13.
    Koren, Y., Bell, R.M., Volinsky, C.: Matrix factorization techniques for recommender systems. IEEE Comput. 42(8), 30–37 (2009)CrossRefGoogle Scholar
  14. 14.
    Krishnapuram, B., Carin, L., Figueiredo, M.A.T., Hartemink, A.J.: Sparse multinomial logistic regression: fast algorithms and generalization bounds. IEEE Trans. Pattern Anal. Mach. Intell. 27(6), 957–968 (2005)CrossRefGoogle Scholar
  15. 15.
    Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. In: NIPS, pp. 801–808 (2006)Google Scholar
  16. 16.
    Lee, J.D., Hastie, T.J.: Learning the structure of mixed graphical models. J. Comput. Graph. Stat. 24(1), 230–253 (2015)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Lin, Y.K., Chen, H., Brown, R.A., Li, S.H., Yang, H.J.: Healthcare predictive analytics for risk profiling in chronic care: a Bayesian multitask learning approach. MIS Q. 41(2), 473–495 (2017)CrossRefGoogle Scholar
  18. 18.
    Liu, C., Wang, F., Hu, J., Xiong, H.: Temporal phenotyping from longitudinal electronic health records: a graph based framework. In: KDD, pp. 705–714 (2015)Google Scholar
  19. 19.
    Liu, L., Tang, J., Cheng, Y., Agrawal, A., Liao, W.K., Choudhary, A.: Mining diabetes complication and treatment patterns for clinical decision support. In: CIKM, pp. 279–288 (2013)Google Scholar
  20. 20.
    Moher, D., Jones, A., Cook, D.J., Jadad, A.R., Moher, M., Tugwell, P., Klassen, T.P., et al.: Does quality of reports of randomised trials affect estimates of intervention efficacy reported in meta-analyses? Lancet 352(9128), 609–613 (1998)CrossRefGoogle Scholar
  21. 21.
    Moturu, S.T., Johnson, W.G., Liu, H.: Predicting future high-cost patients: a real-world risk modeling application. In: BIBM, pp. 202–208. IEEE (2007)Google Scholar
  22. 22.
    Pearl, J.: Causality. Cambridge University Press, Cambridge (2009)CrossRefGoogle Scholar
  23. 23.
    Shickel, B., Tighe, P., Bihorac, A., Rashidi, P.: Deep EHR: a survey of recent advances on deep learning techniques for electronic health record (EHR) analysis. arXiv preprint arXiv:1706.03446 (2017)
  24. 24.
    Shivade, C., Raghavan, P., Fosler-Lussier, E., Embi, P.J., Elhadad, N., Johnson, S.B., Lai, A.M.: A review of approaches to identifying patient phenotype cohorts using electronic health records. J. Am. Med. Inform. Assoc. 21(2), 221–230 (2013)CrossRefGoogle Scholar
  25. 25.
    Wang, J., Wang, Z., Zhang, D., Yan, J.: Combining knowledge with deep convolutional neural networks for short text classification. In: IJCAI, pp. 2915–2921 (2017)Google Scholar
  26. 26.
    Wood, A.M., White, I.R., Thompson, S.G.: Are missing outcome data adequately handled? A review of published randomized controlled trials in major medical journals. Clin. Trials 1(4), 368–376 (2004)CrossRefGoogle Scholar
  27. 27.
    Yadav, P., Steinbach, M., Kumar, V., Simon, G.: Mining electronic health records: a survey. arXiv preprint arXiv:1702.03222 (2017)
  28. 28.
    Yang, S., Khot, T., Kersting, K., Natarajan, S.: Learning continuous-time Bayesian networks in relational domains: a non-parametric approach. In: AAAI, pp. 2265–2271 (2016)Google Scholar
  29. 29.
    Yang, Y., Luyten, W., Liu, L., Moens, M.F., Tang, J., Li, J.: Forecasting potential diabetes complications. In: AAAI, pp. 313–319 (2014)Google Scholar
  30. 30.
    Yin, H., Cui, B.: Spatio-Temporal Recommendation in Social Media. Springer Briefs in Computer Science. Springer, Singapore (2016). Scholar
  31. 31.
    Yin, H., Cui, B., Zhou, X., Wang, W., Huang, Z., Sadiq, S.W.: Joint modeling of user check-in behaviors for real-time point-of-interest recommendation. ACM Trans. Inf. Syst. 35(2), 11:1–11:44 (2016)CrossRefGoogle Scholar
  32. 32.
    Yin, H., Hu, Z., Zhou, X., Wang, H., Zheng, K., Hung, N.Q.V., Sadiq, S.W.: Discovering interpretable geo-social communities for user behavior prediction. In: ICDE, pp. 942–953. IEEE Computer Society (2016)Google Scholar
  33. 33.
    Yin, H., Wang, W., Wang, H., Chen, L., Zhou, X.: Spatial-aware hierarchical collaborative deep learning for POI recommendation. IEEE Trans. Knowl. Data Eng. 29(11), 2537–2551 (2017)CrossRefGoogle Scholar
  34. 34.
    Yin, H., Zhou, X., Cui, B., Wang, H., Zheng, K., Hung, N.Q.V.: Adapting to user interest drift for POI recommendation. IEEE Trans. Knowl. Data Eng. 28(10), 2566–2581 (2016)CrossRefGoogle Scholar
  35. 35.
    Yin, H., Zhou, X., Shao, Y., Wang, H., Sadiq, S.W.: Joint modeling of user check-in behaviors for point-of-interest recommendation. In: CIKM, pp. 1631–1640. ACM (2015)Google Scholar
  36. 36.
    Yoshida, R., West, M.: Bayesian learning in sparse graphical factor models via variational mean-field annealing. J. Mach. Learn. Res. 11, 1771–1798 (2010)MathSciNetzbMATHGoogle Scholar
  37. 37.
    Zhang, X., Yu, Y., White, M., Huang, R., Schuurmans, D.: Convex sparse coding, subspace learning, and semi-supervised extensions. In: AAAI (2011)Google Scholar
  38. 38.
    Zhang, Y., Li, X., Wang, J., Zhang, Y., Xing, C., Yuan, X.: An efficient framework for exact set similarity search using tree structure indexes. In: ICDE, pp. 759–770 (2017)Google Scholar
  39. 39.
    Zhong, P., Wang, R.: Learning sparse crfs for feature selection and classification of hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 46(12), 4186–4197 (2008)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Kangzhi Zhao
    • 1
    Email author
  • Yong Zhang
    • 1
  • Zihao Wang
    • 1
  • Hongzhi Yin
    • 2
  • Xiaofang Zhou
    • 2
  • Jin Wang
    • 3
  • Chunxiao Xing
    • 1
  1. 1.RIIT, TNList, Department of Computer Science and Technology, Institute of Internet IndustryTsinghua UniversityBeijingChina
  2. 2.The University of QueenslandBrisbaneAustralia
  3. 3.Computer Science DepartmentUniversity of California, Los AngelesLos AngelesUSA

Personalised recommendations