Long Short-Term Memory Recurrent Neural Network for Stroke Prediction

  • Pattanapong Chantamit-o-pasEmail author
  • Madhu Goyal
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10934)


Electronic Healthcare Records (EHRs) describe the details about a patient’s physical and mental health, diagnosis, lab results, treatments or patient care plan and so forth. Currently, the International Classification of Diseases, 10th Revision or ICD-10 code is used for representing each patient record. The huge amount of information in these records provides insights about the diagnosis and prediction of various diseases. Various data mining techniques are used for the analysis of data deriving from these patient records. Recurrent Neural Network (RNN) is a powerful and widely used technique in machine learning and bioinformatics. This research aims at the investigation of RNN with Long Short-Term Memory (LSTM) hidden units. The empirical research is intended to evaluate the ability of LSTMs to recognize patterns in multi-label classification of cerebrovascular symptoms or stroke. First, we integrated ICD-10 code into health record, as well as other potential risk factors within EHRs into the pattern and model for prediction. Next, we modelled the effectiveness of LSTMs for prediction of stroke based on healthcare records. The results show several strong baselines that include accuracy, recall, and F1 measure score.


Deep learning Cerebrovascular disease Predictive technique LSTM-RNN 



This research was granted the ethics approval by University of Technology Sydney, Australia (The ethics approval number UTS HREC ETH17-1406). Additionally, without support from the Department of Medical Services (affiliated with Ministry of Public Health of Thailand) and Office of Educational Affairs (affiliated with Royal Thai Embassy to Australia), the research would not have been accomplished. With this acknowledgement, we would like to express our sincere appreciation to them.


  1. 1.
    Deo, R.C.: Machine learning in medicine. Circulation 132, 1920 (2015)CrossRefGoogle Scholar
  2. 2.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)CrossRefGoogle Scholar
  3. 3.
    Langhorne, P., Bernhardt, J., Kwakkel, G.: Stroke rehabilitation. Lancet 377, 1693–1702 (2011)CrossRefGoogle Scholar
  4. 4.
    Khosla, A., Cao, Y., Lin, C.C.-Y., Chiu, H.-K., Hu, J., Lee, H.: An integrated machine learning approach to stroke prediction. In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 183–192. ACM, Washington, D.C. (2010)Google Scholar
  5. 5.
    Leira, E.C., Ku-Chou, C., Davis, P.H., Clarke, W.R., Woolson, R.F., Hansen, M.D., Adams Jr., H.P.: Can we predict early recurrence in acute stroke? Cerebrovasc. Dis. 18, 139–144 (2004)CrossRefGoogle Scholar
  6. 6.
    Cooke, C.R., Joo, M.J., Anderson, S.M., Lee, T.A., Udris, E.M., Johnson, E., Au, D.H.: The validity of using ICD-9 codes and pharmacy records to identify patients with chronic obstructive pulmonary disease. BMC Health Serv. Res. 11, 37 (2011)CrossRefGoogle Scholar
  7. 7.
    Ried, L.D.P., Cameon, R.M.S., Jia, H.P., Findley, K., Hinojosa, M.S.P., Wang, X.P., Tueth, M.J.M.D.: Identifying veterans with acute strokes with high-specificity ICD-9 algorithm with VA automated records and Medicare claims data: a more complete picture. J. Rehabil. Res. Dev. 44, 665–673 (2007)CrossRefGoogle Scholar
  8. 8.
    Scheurer, D.B., Hicks, L.S., Cook, E.F., Schnipper, J.L.: Accuracy of ICD-9 coding for Clostridium difficile infections: a retrospective cohort. Epidemiol. Infect. 135, 1010–1013 (2007)CrossRefGoogle Scholar
  9. 9.
    WHO: ICD10: International Statistical Classification of Disease and Related Health Tenth Revision, vol. 2. World Health Organization, Geneva (2004)Google Scholar
  10. 10.
    Gulshan, V., Peng, L., Coram, M., et al.: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316, 2402–2410 (2016)CrossRefGoogle Scholar
  11. 11.
    Stier, N., Vincent, N., Liebeskind, D., Scalzo, F.: Deep learning of tissue fate features in acute ischemic stroke. In: IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2015, pp. 1316–1321 (2015)Google Scholar
  12. 12.
    Liang, Z., Zhang, G., Huang, J.X., Hu, Q.V.: Deep learning for healthcare decision making with EMRs. In: IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 556–559 (2014)Google Scholar
  13. 13.
    Hammerla, N.Y., Fisher, J., Andras, P., Rochester, L., Walker, R., Plötz, T.: PD disease state assessment in naturalistic environments using deep learning. In: Twenty-Ninth AAAI Conference on Artificial Intelligence, pp. 1742–1748 (2015)Google Scholar
  14. 14.
    Ding, X., Zhang, Y., Liu, T., Duan, J.: Deep learning for event-driven stock prediction. In: Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI 2015), pp. 2327–2333 (2015)Google Scholar
  15. 15.
    Ding, X., Zhang, Y., Liu, T., Duan, J.: Using structured events to predict stock price movement: an empirical investigation. In: EMNLP, pp. 1415–1425 (2014)Google Scholar
  16. 16.
    Goldstein, L.B., Adams, R., Becker, K., Furberg, C.D., Gorelick, P.B., Hademenos, G., Hill, M., Howard, G., Howard, V.J., Jacobs, B., Levine, S.R., Mosca, L., Sacco, R.L., Sherman, D.G., Wolf, P.A., del Zoppo, G.J.: Members: primary prevention of ischemic stroke. Circulation 103, 163–182 (2001)CrossRefGoogle Scholar
  17. 17.
    Goldstein, L.B., Adams, R., Alberts, M.J., Appel, L.J., Brass, L.M., Bushnell, C.D., Culebras, A., DeGraba, T.J., Gorelick, P.B., Guyton, J.R., Hart, R.G., Howard, G., Kelly-Hayes, M., Nixon, J.V., Sacco, R.L.: Primary prevention of ischemic stroke: a guideline from the American Heart Association/American Stroke Association Stroke Council: cosponsored by the Atherosclerotic Peripheral Vascular Disease Interdisciplinary Working Group; Cardiovascular Nursing Council; Clinical Cardiology Council; Nutrition, Physical Activity, and Metabolism Council; and the Quality of Care and Outcomes Research Interdisciplinary Working Group: the American Academy of Neurology affirms the value of this guideline. Stroke 37, 1583–1633 (2006)CrossRefGoogle Scholar
  18. 18.
    The American Heart Association: Comparison of 12 risk stratification schemes to predict stroke in patients with nonvalvular atrial fibrillation. Stroke 39, 1901–1910 (2008)Google Scholar
  19. 19.
    Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Neural Comput. 12, 2451–2471 (2000)CrossRefGoogle Scholar
  20. 20.
    Gers, F.A., Schraudolph, N.N., Schmidhuber, J.: Learning precise timing with LSTM recurrent networks. J. Mach. Learn. Res. 3, 115–143 (2002)MathSciNetzbMATHGoogle Scholar
  21. 21.
    Sak, H., Senior, A., Beaufays, F.: Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: Fifteenth Annual Conference of the International Speech Communication Association, Singapore, pp. 338–342 (2014)Google Scholar
  22. 22.
    Greff, K., Srivastava, R.K., Koutník, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28, 2222–2232 (2017)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Centre for Artificial Intelligence, Faculty of Engineering and Information TechnologyUniversity of Technology SydneyUltimoAustralia
  2. 2.Faculty of Information TechnologyKing Mongkut’s Institute of Technology LadkrabangLadkrabang, BangkokThailand

Personalised recommendations