Abstract
Personalized predictive medicine necessitates modeling of patient illness and care processes, which inherently have long-term temporal dependencies. Healthcare observations, recorded in electronic medical records, are episodic and irregular in time. We introduce DeepCare, a deep dynamic neural network that reads medical records and predicts future medical outcomes. At the data level, DeepCare models patient health state trajectories with explicit memory of illness. Built on Long Short-Term Memory (LSTM), DeepCare introduces time parameterizations to handle irregular timing by moderating the forgetting and consolidation of illness memory. DeepCare also incorporates medical interventions that change the course of illness and shape future medical risk. Moving up to the health state level, historical and present health states are then aggregated through multiscale temporal pooling, before passing through a neural network that estimates future outcomes. We demonstrate the efficacy of DeepCare for disease progression modeling and readmission prediction in diabetes, a chronic disease with large economic burden. The results show improved modeling and risk prediction accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arandjelović, O.: Discovering hospital admission patterns using models learnt from electronic hospital records. Bioinformatics. btv508 (2015)
Corbin, J.M., Strauss, A.: A nursing model for chronic illness management based upon the trajectory framework. Res. Theory Nurs. Pract. 5(3), 155–174 (1991)
Futoma, J., Morris, J., Lucas, J.: A comparison of models for predicting early hospital readmissions. J. Biomed. Inform. 56, 229–238 (2015)
Granger, B.B., Moser, D., Germino, B., Harrell, J., Ekman, I.: Caring for patients with chronic heart failure: the trajectory model. Eur. J. Cardiovasc. Nurs. 5(3), 222–227 (2006)
Graves, A.: Generating sequences with recurrent neural networks (2013). arXiv preprint arXiv:1308.0850
Graves, A., Liwicki, M., Fernández, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 855–868 (2009)
Henly, S.J., Wyman, J.F., Findorff, M.J.: Health and illness over time: the trajectory perspective in nursing science. Nurs. Res. 60(3 Suppl), S5 (2011)
Henriques, R., Antunes, C., Madeira, S.C.: Generative modeling of repositories of health records for predictive tasks. Data Min. Knowl. Discov. 29(4), 999–1032 (2015)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Jensen, A.B., Moseley, P.L., Oprea, T.I., Ellesøe, S.G., Eriksson, R., Schmock, H., Jensen, P.B., Jensen, L.J., Brunak, S.: Temporal disease trajectories condensed from population-wide registry data covering 6.2 million patients. Nat. Commun. 5, 10 (2014)
Jensen, P.B., Jensen, L.J., Brunak, S.: Mining electronic health records: towards better research applications and clinical care. Nat. Rev. Genet. 13(6), 395–405 (2012)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Liang, Z., Zhang, G., Huang, J.X., Hu, Q.V.: Deep learning for healthcare decision making with EMRs. In: 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 556–559. IEEE (2014)
Liu, C., Wang, F., Hu, J., Xiong, H.: Temporal phenotyping from longitudinal electronic health records: a graph based framework. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 705–714. ACM (2015)
Mathias, J.S., Agrawal, A., Feinglass, J., Cooper, A.J., Baker, D.W., Choudhary, A.: Development of a 5 year life expectancy index in older adults using predictive mining of electronic health record data. J. Am. Med. Inf. Assoc. 20(e1), e118–e124 (2013)
Orphanou, K., Stassopoulou, A., Keravnou, E.: Temporal abstraction and temporal Bayesian networks in clinical domains: a survey. Artif. Intell. Med. 60(3), 133–149 (2014)
Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMS (2015). arXiv preprint arXiv:1502.04681
Sutskever, I., Vinyals, O., Le, Q.V.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)
Tran, T., Phung, D., Luo, W., Harvey, R., Berk, M., Venkatesh, S.: An integrated framework for suicide risk prediction. In: KDD 2013 (2013)
Tran, T., Luo, W., Phung, D., Gupta, S., Rana, S., Kennedy, R.L., Larkins, A., Venkatesh, S.: A framework for feature extraction from hospital medical data with applications in risk prediction. BMC Bioinform. 15(1), 6596 (2014)
Tran, T., Nguyen, T.D., Phung, D., Venkatesh, S.: Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM). J. Biomed. Inform. 54, 96–105 (2015)
Wang, X., Sontag, D., Wang, F.: Unsupervised learning of disease progression models. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 85–94. ACM (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Pham, T., Tran, T., Phung, D., Venkatesh, S. (2016). DeepCare: A Deep Dynamic Memory Model for Predictive Medicine. In: Bailey, J., Khan, L., Washio, T., Dobbie, G., Huang, J., Wang, R. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2016. Lecture Notes in Computer Science(), vol 9652. Springer, Cham. https://doi.org/10.1007/978-3-319-31750-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-31750-2_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-31749-6
Online ISBN: 978-3-319-31750-2
eBook Packages: Computer ScienceComputer Science (R0)