Using recurrent neural network models for early detection of heart failure onset

Journal of the American Medical Informatics Association

Volumn 24, Issue 2, 2017, Pages 361-370

  Choi, Edward ^a   Schuetz, Andy ^b   Stewart, Walter F ^b   Sun, Jimeng ^a  

^a GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

^b SUTTER HEALTH   (United States)

Author keywords

Deep learning; Electronic health records; Heart failure prediction; Patient progression model; Recurrent neural network

Indexed keywords

AREA UNDER THE CURVE; ARTICLE; ARTIFICIAL NEURAL NETWORK; CONTROLLED STUDY; EARLY DIAGNOSIS; ELECTRONIC HEALTH RECORD; HEART FAILURE; HUMAN; K NEAREST NEIGHBOR; MAJOR CLINICAL STUDY; PERCEPTRON; SUPPORT VECTOR MACHINE; MACHINE LEARNING; STATISTICAL MODEL;

AREA UNDER CURVE; EARLY DIAGNOSIS; ELECTRONIC HEALTH RECORDS; HEART FAILURE; HUMANS; LOGISTIC MODELS; MACHINE LEARNING; NEURAL NETWORKS (COMPUTER); SUPPORT VECTOR MACHINE;

EID: 85016146323     PISSN: 10675027     EISSN: 1527974X     Source Type: Journal    
DOI: 10.1093/jamia/ocw112     Document Type: Article

References (55)

1. Roger VL, Weston SA, RedfieldMM, et al. Trends in heart failure incidence and survival in a community-based population. JAMA 2004;292(3): 344-350.
2. Murphy SL, Xu J, Kochanek KD. Deaths: final data for 2010. Natl Vital Stat Rep 2010;61(4):1-117.
3. Investigators SOLVD. Effect of enalapril on mortality and the development of heart failure in asymptomatic patients with reduced left ventricular ejection fractions. N Engl J Med 1992;327:685-691.
4. Arnold J, Yusuf S, Young J, et al. Prevention of heart failure in patients in the Heart Outcomes Prevention Evaluation (HOPE) study. Circulation 2003;107(9):1284-1290.
5. Sciarretta S, Palano F, Tocci G, Baldini R, Volpe M. Antihypertensive treatment and development of heart failure in hypertension: a Bayesian network meta-analysis of studies in patients with hypertension and high cardiovascular risk. Arch Int Med 2011;171(5):384-394.
6. Wang C-H, Weisel R, Liu P, Fedak P, Verma S. Glitazones and heart failure critical appraisal for the clinician. Circulation 2003;107(10): 1350-1354.
7. Wang Y, Ng K, Byrd R, et al. Early detection of heart failure with varying prediction windows by structured and unstructured data in electronic health records. In IEEE Engineering in Medicine and Biology Society 2015:2530-2533.
8. Sun J, Hu J, Luo D, et al. Combining knowledge and data driven insights for identifying risk factors using electronic health records. In American Medical Informatics Association 2012;901-910.
9. Wu J, Roy J, StewartW. Prediction modeling using EHR data: challenges, strategies, and a comparison of machine learning approaches. Med Care 2010;48(6):S106-S113.
10. Karpathy A, Li F. Deep visual-semantic alignments for generating image descriptions. Computer Vision and Pattern Recognition (CVPR) 2015:3128-3137. Boston, MA, USA.
11. Cho K, Van Merrienboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Empirical Methods in Natural Language Processing (EMNLP). 2014:1724-1734. Doha, Qatar.
12. Hinton G, Osindero S, Teh Y-W. A fast learning algorithm for deep belief nets. Neural Comput 2006;18(7):1527-1554.
13. Bengio Y. Learning deep architectures for AI. Foundations Trends Machine Learning. 2009;2(1):1-127.
14. Krizhevsky A, Sutskever I, Hinton G. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (NIPS) 2012:1106-1114. Lake Tahoe,Nevada, United States.
15. Vincent P, Larochelle H, Bengio Y, Manzagol P-A. Extracting and composing robust features with denoising autoencoders. In International Conference on Machine learning (ICML) 2008:1096-1103. Helsinki, Finland.
16. Le Q, Ranzato M, Monga R, et al. Building high-level features using large scale unsupervised learning. In International Conference on Machine Learning (ICML) 2012, Edinburgh, Scotland, UK.
17. Lee H, Pham P, Largman Y, Ng A. Unsupervised feature learning for audio classification using convolutional deep belief networks. In Advances in Neural Information Processing Systems (NIPS) 2009;1096-1104. Vancouver, British Columbia, Canada.
18. Hinton G, Deng L, Yu D, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. Signal Process Mag 2012;29(6):82-97.
19. Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. In arXiv preprint arXiv:1301.3781 2013.
20. Mikolov T, Sutskever I, Chen K, Corrado G, Dean J. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems (NIPS) 2013:3111-3119. Lake Tahoe, Nevada, United States.
21. Socher R, Pennington J, Huang E, Ng A, Manning C. Semi-supervised recursive autoencoders for predicting sentiment distributions. In Empirical Methods in Natural Language Processing (EMNLP). 2011:151-161. Edinburgh, UK.
22. Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput 1997;9(8):1735-1780.
23. Grosicki E, El Abed H. ICDAR 2009 handwriting recognition competition. In International Conference on Document Analysis and Recognition 2009:1398-1402. Barcelona, Spain.
24. Sak H, Senior A, Beaufays F. Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In International Speech Communication Association 2014;338-342. Singapore.
25. Zaremba W, Sutskever I, Vinyals O. Recurrent neural network regularization. In arXiv preprint arXiv:1409.2329 2014.
26. Luong M-T, Sutskever I, Le Q, Vinyals O, Zaremba W. Addressing the rare word problem in neural machine translation. In Association for Computational Linguistics (ACL) 2015:11-19. Beijing, China.
27. Jozefowicz R, ZarembaW, Sutskever I. An empirical exploration of recurrent network architectures. In International Conference on Machine Learning (ICML). 2015:2342-2350. Lille, France.
28. Lasko T, Denny J, Levy M. Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and irregular clinical data. PloS One 2013;8(6):e66341.
29. Che Z, Kale D, Li W, Bahadori M, Liu Y. Deep computational phenotyping. In Knowledge Discovery and Data Mining (KDD). 2015:507-516. Sydney, NSW, Australia.
30. Hammerla N, Fisher J, Andras P, Rochester L, Walker R, Plotz T. PD disease state assessment in naturalistic environments using deep learning. In AAAI 2015 1742-1748. Austin, Texas, USA.
31. Lipton Z, Kale D, Elkan C,Wetzell R. Learning to diagnose with LSTM recurrent neural networks. In arXiv preprint arXiv: 1511.03677 2016.
32. Minarro-Gimenez J, Marin-Alonso O, Samwald M. Exploring the application of deep learning techniques on medical text corpora. Stud Health Technol Inform 2013;205:584-588.
33. De Vine L, Zuccon G, Koopman B, Sitbon L, Bruza P. Medical semantic similarity with a neural language model. In International Conference on Information and Knowledge Management (CIKM). 2014;1819-1822. Shanghai, China.
34. Choi Y, Chiu C, Sontag D. Learning low-dimensional representations of medical concepts. In American Medical Informatics Association on Clinical Research Informatics 2016. San Francisco, CA.
35. Choi E, Schuetz A, Stewart W, Sun J. Medical concept representation learning from electronic health records and its application on heart failure prediction. In arXiv preprint arXiv:1602.03686 2016.
36. Tangri N, Stevens L, Griffith J, et al. A predictive model for progression of chronic kidney disease to kidney failure. JAMA 2011;305(15): 1553-1559.
37. Sukkar R, Katz E, Zhang Y, Raunig D, Wyman B. Disease progression modeling using hidden Markov models. In Engineering in Medicine and Biology Society 2012:2845-2848.
38. Zhou J, Liu J, Narayan V, Ye J. Modeling disease progression via multitask learning. NeuroImage 2013;78:233-248.
39. Liu Y-Y, Ishikawa H, Chen M, Wollstein G, Schuman J, Rehg J. Longitudinal modeling of glaucoma progression using 2-dimensional continuous-time hidden Markov model. In Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2013:444-451. Nagoya, Japan.
40. Schulam P, Saria S. A framework for individualizing predictions of disease trajectories by exploiting multi-resolution structure. In Advances in Neural Information Processing Systems (NIPS) 2015:748-756. Montreal, Quebec, Canada.
41. Wang X, Sontag D, Wang F. Unsupervised learning of disease progression models. In Knowledge Discovery and Data Mining (KDD) 2014:85-94. New York, NY, USA.
42. Choi E, Du N, Chen R, Song L, Sun J. Constructing disease network and temporal progression model via context-sensitive Hawkes process. In International Conference on Data Mining (ICDM) 2015:721-726. Atlantic City, NJ, USA.
43. Goldberg Y. A primer on neural network models for natural language processing. In arXiv preprint arXiv:1510.00726 2015.
44. Bishop C. Pattern Recognition and Machine Learning (Information Science and Statistics) New York: Springer-Verlag; 2006.
45. Bergstra J, Breuleux O, Bastien F, et al. Theano: a CPU and GPU Math Expression Compiler. In Python for Scientific Computing Conference 2010.
46. Greenland S, Thomas D. On the need for the rare disease assumption in case-control studies. Am J Epidemiol. 1982;116(3):547-553.
47. Vijayakrishnan R, Steinhubl S, Ng K, et al. Prevalence of heart failure signs and symptoms in a large primary care population identified through the use of text and data mining of the electronic health record. J Cardiac Failure 2014;20(7):459-464.
48. Gurwitz J, Magid D, Smith D, et al. Contemporary prevalence and correlates of incident heart failure with preserved ejection fraction. Am J Med 2013;126(5):393-400.
49. Clinical Classifications Software (CCS) for ICD-9-CM. Agency for Healthcare Research and Quality. https://www.hcup-us.ahrq.gov/tools software/ccs/ccs.jsp. Accessed April 2016.
50. Medi-Span Electronic Drug File (MED-File) v2. Wolters Kluwer Clinical Drug Information. http://www.wolterskluwercdi.com/drug-data/medispan-electronic-drug-file/. Accessed April 2016.
51. Clinical Classifications Software for Services and Procedures. Agency for Healthcare Research and Quality. https://www.hcup-us.ahrq.gov/tools software/ccs_svcsproc/ccssvcproc.jsp. Accessed April 2016.
52. Zeiler M. ADADELTA: An adaptive learning rate method. In arXiv preprint arXiv:1212.5701 2012.
53. Nwankwo T, Yoon SS, Burt V, Gu Q. Hypertension among adults in the United States: National Health and Nutrition Examination Survey, 2011-2012 NCHS Data Brief 2013;113:1-8.
54. CDC. Coronary Artery Disease (CAD) Centers for Disease Control and Prevention. http://www.cdc.gov/heartdisease/coronary_ad.htm. Accessed July 2016.
55. Karpathy A, Johnson J, Li F. Visualizing and understanding recurrent networks. In arXiv preprint arXiv:1506.02078, 2015.