Predicting healthcare trajectories from medical records: A deep learning approach

Journal of Biomedical Informatics

Volumn 69, Issue , 2017, Pages 218-229

  Pham, Trang ^a   Tran, Truyen ^a   Phung, Dinh ^a   Venkatesh, Svetha ^a  

^a DEAKIN UNIVERSITY   (Australia)

Author keywords

Electronic medical records; Healthcare processes; Irregular timing; Long Short Term Memory; Predictive medicine

Indexed keywords

BRAIN; DEEP LEARNING; DEEP NEURAL NETWORKS; DISEASES; FORECASTING; HEALTH; HEALTH CARE; MEDICAL COMPUTING; MEDICINE; NEURAL NETWORKS;

DISEASE PROGRESSION; DYNAMIC NEURAL NETWORKS; ELECTRONIC MEDICAL RECORD; HEALTHCARE PROCESS; HISTORICAL RECORDS; IRREGULAR TIMING; MEDICAL INTERVENTION; PREDICTION ACCURACY;

LONG SHORT-TERM MEMORY;

ARTICLE; ARTIFICIAL NEURAL NETWORK; DIABETES MELLITUS; ELECTRONIC MEDICAL RECORD; HEALTH STATUS; HUMAN; MATHEMATICAL MODEL; MEASUREMENT ACCURACY; MEASUREMENT PRECISION; MEDICAL HISTORY; MEDICAL RECORD; MENTAL HEALTH; PREDICTION; RISK ASSESSMENT; DISEASE EXACERBATION; ELECTRONIC HEALTH RECORD; HEALTH CARE DELIVERY;

DELIVERY OF HEALTH CARE; DISEASE PROGRESSION; ELECTRONIC HEALTH RECORDS; HEALTH STATUS; HUMANS; NEURAL NETWORKS (COMPUTER);

EID: 85018652748     PISSN: 15320464     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jbi.2017.04.001     Document Type: Article

References (46)

1. [1] Arandjelović, Ognjen, Discovering hospital admission patterns using models learnt from electronic hospital records. Bioinformatics, 2015.
2. [4] Bengio, Yoshua, Simard, Patrice, Frasconi, Paolo, Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Networks 5:2 (1994), 157–166.
3. [5] Zhengping Che, Sanjay Purushotham, Kyunghyun Cho, David Sontag, Yan Liu, Recurrent Neural Networks for Multivariate Time Series with Missing Values, 2016. arXiv preprint Available from: < arXiv:1606.0186>.
4. [6] Cheng, Yu, Wang, Fei, Zhang, Ping, Hu, Jianying, Risk prediction with electronic health records: a deep learning approach. SIAM International Conference on Data Mining, 2016, SIAM.
5. [7] Edward Choi, Mohammad Taha Bahadori, Jimeng Sun, Doctor AI: Predicting Clinical Events via Recurrent Neural Networks, 2015. arXiv preprint Available from: < arXiv:1511.05942>.
6. [8] Edward Choi, Mohammad Taha Bahadori, Jimeng Sun, Joshua Kulas, Andy Schuetz, Walter Stewart, Retain: an interpretable predictive model for healthcare using reverse time attention mechanism, in: Advances in Neural Information Processing Systems, 2016, pp. 3504–3512.
7. [9] Choi, Youngduck, Learning low-dimensional representations of medical concepts. Proc. AMIA Summit Clin. Res. Inform. (CRI), 2016.
8. [10] Corbin, Juliet M., Strauss, Anselm, A nursing model for chronic illness management based upon the trajectory framework. Res. Theory Nurs. Pract. 5:3 (1991), 155–174.
9. [13] Futoma, Joseph, Morris, Jonathan, Lucas, Joseph, A comparison of models for predicting early hospital readmissions. J. Biomed. Inform. 56 (2015), 229–238.
10. [14] Granger, Bradi B., Moser, Debra, Germino, Barbara, Harrell, Joanne, Ekman, Inger, Caring for patients with chronic heart failure: the trajectory model. Eur. J. Cardiovascular Nurs. 5:3 (2006), 222–227.
11. [15] Alex Graves, Generating Sequences with Recurrent Neural Networks, 2013. arXiv preprint Available from: < arXiv:1308.0850>.
12. [16] Alex Graves, Marcus Liwicki, Horst Bunke, Jürgen Schmidhuber, Santiago Fernández, Unconstrained on-line handwriting recognition with recurrent neural networks, in: Advances in Neural Information Processing Systems, 2008, pp. 577–584.
13. [17] Graves, Alex, Liwicki, Marcus, Fernández, Santiago, Bertolami, Roman, Bunke, Horst, Schmidhuber, Jürgen, A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31:5 (2009), 855–868.
14. [18] Graves, Alex, Mohamed, Abdel-rahman, Hinton, Geoffrey, Speech recognition with deep recurrent neural networks. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013, IEEE, 6645–6649.
15. [19] Henly, Susan J., Wyman, Jean F., Findorff, Mary J., Health and illness over time: the trajectory perspective in nursing science. Nursing Res., 60(Suppl. 3), 2011, S5.
16. [21] Hochreiter, Sepp, Schmidhuber, Jürgen, Long short-term memory. Neural Comput. 9:8 (1997), 1735–1780.
17. [22] Hripcsak, George, Albers, David J., Perotte, Adler, Parameterizing time in electronic health record studies. J. Am. Med. Inform. Assoc., 2015, ocu051.
18. [23] Huang, Zhengxing, Dong, Wei, Duan, Huilong, Li, Haomin, Similarity measure between patient traces for clinical pathway analysis: problem, method, and applications. IEEE J. Biomed. Health Inform. 18:1 (2014), 4–14.
19. [24] Jackson, Christopher H., Sharples, Linda D., Thompson, Simon G., Duffy, Stephen W., Couto, Elisabeth, Multistate Markov models for disease progression with classification error. J. Roy. Stat. Soc.: Ser. D (The Statistician) 52:2 (2003), 193–209.
20. [25] Jensen, Anders Boeck, Moseley, Pope L., Oprea, Tudor I., Ellesøe, Sabrina Gade, Eriksson, Robert, Schmock, Henriette, Jensen, Peter Bjødstrup, Jensen, Lars Juhl, Brunak, Søren, Temporal disease trajectories condensed from population-wide registry data covering 6.2 million patients. Nat. Commun., 5, 2014.
21. [26] Jensen, Peter B., Jensen, Lars J., Brunak, Søren, Mining electronic health records: towards better research applications and clinical care. Nat. Rev. Genet. 13:6 (2012), 395–405.
22. [27] LeCun, Yann, Bengio, Yoshua, Hinton, Geoffrey, Deep learning. Nature 521:7553 (2015), 436–444.
23. [28] Liang, Zhaohui, Zhang, Gang, Huang, Jimmy Xiangji, Hu, Qmming Vivian, Deep learning for healthcare decision making with EMRs. 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2016, IEEE, 556–559.
24. [29] Z. Lipton, D. Kale, C. Elkan, R. Wetzel, Learning to diagnose with LSTM recurrent neural networks, in: International Conference on Learning Representations (ICLR 2016), 2016.
25. [30] Liu, Chuanren, Wang, Fei, Hu, Jianying, Xiong, Hui, Temporal phenotyping from longitudinal electronic health records: a graph based framework. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015, ACM, 705–714.
26. [31] Lu, H.M., Zeng, D., Chen, H.C., Prospective infectious disease outbreak detection using Markov switching models. IEEE Trans. Knowl. Data Eng., 2009.
27. [32] Nguyen, Phuoc, Tran, Truyen, Wickramasinghe, Nilmini, Venkatesh, Svetha, Deepr: a convolutional net for medical records. IEEE J. Biomed. Health Inform., 2016.
28. [33] T.D. Nguyen, T. Tran, D. Phung, S. Venkatesh, Learning parts-based representations with nonnegative restricted Boltzmann machine, in: Proc. of 5th Asian Conference on Machine Learning (ACML), Canberra, Australia, Nov 2013.
29. [34] Nguyen, Tu Dinh, Tran, Truyen, Phung, Dinh, Venkatesh, Svetha, Graph-induced restricted Boltzmann machines for document modeling. Inform. Sci. 328 (2016), 60–75.
30. [35] Orphanou, Kalia, Stassopoulou, Athena, Keravnou, Elpida, Temporal abstraction and temporal Bayesian networks in clinical domains: a survey. Artif. Intell. Med. 60:3 (2014), 133–149.
31. [36] Pascanu, Razvan, Mikolov, Tomas, Bengio, Yoshua, On the difficulty of training recurrent neural networks. ICML (3) 28 (2013), 1310–1318.
32. [37] Chris Paxton, Suchi Saria, Alexandru Niculescu-Mizil, Developing predictive models using electronic medical records: challenges and pitfalls, in: AMIA, 2013.
33. [38] Pham, Trang, Tran, Truyen, Phung, Dinh, Venkatesh, Svetha, Deepcare: a deep dynamic memory model for predictive medicine. Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2016, ACM, 30–41.
34. [39] Trang Pham, Truyen Tran, Dinh Phung, Svetha Venkatesh, Faster training of very deep networks via p-norm gates, in: ICPR’16, 2016.
35. [40] Ramati, Michael, Shahar, Yuval, Irregular-time Bayesian Networks. 2010, UAI.
36. [41] Snyderman, Ralph, Williams, R. Sanders, Prospective medicine: the next health care transformation. Acad. Med. 78:11 (2003), 1079–1084.
37. [42] Srivastava, Nitish, Hinton, Geoffrey, Krizhevsky, Alex, Sutskever, Ilya, Salakhutdinov, Ruslan, Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15 (2014), 1929–1958.
38. [43] Steyerberg, Ewout W., Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating. 2009, Springer.
39. [44] Ilya Sutskever, Oriol Vinyals, Quoc V.V. Le, Sequence to sequence learning with neural networks, in: Advances in Neural Information Processing Systems, 2014, pp. 3104–3112.
40. [45] Tran, Truyen, Luo, Wei, Phung, Dinh, Gupta, Sunil, Rana, Santu, Kennedy, Richard L., Larkins, Ann, Venkatesh, Svetha, A framework for feature extraction from hospital medical data with applications in risk prediction. BMC Bioinform., 15(1), 2014, 6596.
41. [46] Tran, Truyen, Nguyen, Tu Dinh, Phung, Dinh, Venkatesh, Svetha, Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM). J. Biomed. Inform. 54 (2015), 96–105.
42. [47] Tran, Truyen, Phung, Dinh, Luo, Wei, Harvey, Richard, Berk, Michael, Venkatesh, Svetha, An integrated framework for suicide risk prediction. Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2013, ACM, 1410–1418.
43. [48] Tran, Truyen, Phung, Dinh, Luo, Wei, Venkatesh, Svetha, Stabilized sparse ordinal regression for medical risk stratification. Knowl. Inform. Syst., 2014, 10.1007/s10115-014-0740-4.
44. [49] Wang, Fei, Lee, Noah, Hu, Jianying, Sun, Jimeng, Ebadollahi, Shahram, Laine, Andrew F., A framework for mining signatures from event sequences and its applications in healthcare data. IEEE Trans. Pattern Anal. Mach. Intell. 35:2 (2013), 272–285.
45. [50] Wang, Xiang, Sontag, David, Wang, Fei, Unsupervised learning of disease progression models. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014, ACM, 85–94.
46. [51] Zhao, Jing, Papapetrou, Panagiotis, Asker, Lars, Boström, Henrik, Learning from heterogeneous temporal data in electronic health records. J. Biomed. Inform. 65 (2017), 105–119.