Missing data imputation in the electronic health record using deeply learned autoencoders

Pacific Symposium on Biocomputing

Volumn 0, Issue 212679, 2017, Pages 207-218

  Beaulieu Jones, Brett K ^a   Moore, Jason H ^b  

^a UNIVERSITY OF PENNSYLVANIA   (United States)

^b UNIVERSITY OF PENNSYLVANIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EHEALTH; LEARNING SYSTEMS; RECORDS MANAGEMENT;

CLINICAL TRIAL; DISEASE PROGRESSION; ELECTRONIC HEALTH RECORD; ELECTRONIC HEALTH RECORD (EHRS); MISSING DATA IMPUTATIONS; MISSING NOT AT RANDOM; MULTIPLE IMPUTATION; VITAL SOURCES;

NEURODEGENERATIVE DISEASES;

AMYOTROPHIC LATERAL SCLEROSIS; ARTIFICIAL NEURAL NETWORK; BIOLOGY; CLINICAL TRIAL (TOPIC); DISEASE COURSE; ELECTRONIC HEALTH RECORD; FACTUAL DATABASE; HUMAN; PATHOPHYSIOLOGY; STATISTICAL BIAS; STATISTICS AND NUMERICAL DATA;

AMYOTROPHIC LATERAL SCLEROSIS; BIAS (EPIDEMIOLOGY); CLINICAL TRIALS AS TOPIC; COMPUTATIONAL BIOLOGY; DATABASES, FACTUAL; DISEASE PROGRESSION; ELECTRONIC HEALTH RECORDS; HUMANS; NEURAL NETWORKS (COMPUTER);

EID: 85021860204     PISSN: 23356928     EISSN: 23356936     Source Type: Journal    
DOI: 10.1142/9789813207813_0021     Document Type: Conference Paper

References (38)

1. Sterne JJC, White IRI, Carlin JJB, et al. Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls. BMJ. 2009;338(July):b2393. doi:10.1136/bmj.b2393.
2. Wells BJ, Chagin KM, Nowacki AS, Kattan MW. Strategies for handling missing data in electronic health record derived data. EGEMS (Washington, DC). 2013;1(3):1035. doi:10.13063/2327-9214.1035.
3. McClatchey KD. Clinical Laboratory Medicine. Lippincott Williams & Wilkins; 2002.
4. Little R, Rubin D. Statistical Analysis with Missing Data. John Wiley & Sons; 2014.
5. Marlin B. Missing data problems in machine learning. 2008. http://www-devel.cs.ubc.ca/~bmarlin/research/phd_thesis/marlin-phd-thesis.pdf. Accessed August 7, 2016.
6. Gelman A, Hill J. Data Analysis Using Regression and Multilevel/hierarchical Models.; 2006. https://books.google.com/books?hl=en&lr=&id=c9xLKzZWoZ4C&oi=fnd&pg=PR17&dq=data+analysis+usi ng+regression+and+multilevel/hierarchical+models&ots=baT3R3Mnng&sig=KpLzVOFtUseaK8_IhUfPLM2 Y7fU. Accessed August 10, 2016.
7. Troyanskaya O, Cantor M, Sherlock G, et al. Missing value estimation methods for DNA microarrays. Bioinformatics. 2001;17(6):520-525. doi:10.1093/bioinformatics/17.6.520.
8. Bengio Y. Learning Deep Architectures for AI. Found Trends® Mach Learn. 2009;2(1):1-127. doi:10.1561/2200000006.
9. Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol P-A. Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion. J Mach Learn Res. 2010;11(3):3371-3408. doi:10.1111/1467-8535.00290.
10. Vincent P, Larochelle H, Bengio Y, Manzagol P-A. Extracting and composing robust features with denoising autoencoders. Proc 25th Int Conf Mach Learn-ICML ’08. 2008:1096-1103. doi:10.1145/1390156.1390294.
11. Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. J Mach Learn Res. 2014;15:1929-1958. doi:10.1214/12-AOS1000.
12. Beaulieu-Jones BK, Greene CS. Semi-Supervised Learning of the Electronic Health Record with Denoising Autoencoders for Phenotype Stratification. bioRxiv. February 2016:39800. doi:10.1101/039800.
13. Miotto R, Li L, Kidd BA, et al. Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records. Sci Rep. 2016;6:26094. doi:10.1038/srep26094.
14. Küffner R, Zach N, Norel R, et al. Crowdsourced analysis of clinical trial data to predict amyotrophic lateral sclerosis progression. Nat Biotechnol. 2015;33(1):51-57. doi:10.1038/nbt.3051.
15. Kollewe K, Mauss U, Krampfl K, Petri S, Dengler R, Mohammadi B. ALSFRS-R score and its ratio: A useful predictor for ALS-progression. J Neurol Sci. 2008;275(1-2):69-73. doi:10.1016/j.jns.2008.07.016.
16. Beghi E, Mennini T, Bendotti C, et al. The heterogeneity of amyotrophic lateral sclerosis: a possible explanation of treatment failure. Curr Med Chem. 2007;14(30):3185-3200. http://www.ncbi.nlm.nih.gov/pubmed/18220753. Accessed August 7, 2016.
17. Sabatelli M, Conte A, Zollino M. Clinical and genetic heterogeneity of amyotrophic lateral sclerosis. Clin Genet. 2013;83(5):408-416. doi:10.1111/cge.12117.
18. Ravits JM, La Spada AR. ALS motor phenotype heterogeneity, focality, and spread: deconstructing motor neuron degeneration. Neurology. 2009;73(10):805-811. doi:10.1212/WNL.0b013e3181b6bbbd.
19. Cedarbaum JM, Stambler N. Performance of the amyotrophic lateral sclerosis functional rating scale (ALSFRS) in multicenter clinical trials. In: Journal of the Neurological Sciences. Vol 152.; 1997. doi:10.1016/S0022-510X(97)00237-2.
20. Cedarbaum JM, Stambler N, Malta E, et al. The ALSFRS-R: A revised ALS functional rating scale that incorporates assessments of respiratory function. J Neurol Sci. 1999;169(1-2):13-21. doi:10.1016/S0022-510X(99)00210-5.
21. Rubinsteyn A, Feldman S. fancyimpute: Version 0.0.9. March 2016. doi:10.5281/zenodo.47151.
22. Chollet F. Keras. GitHub Repos. 2015.
23. Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: Machine Learning in Python. … Mach Learn …. 2012;12:2825-2830. http://dl.acm.org/citation.cfm?id=2078195\nhttp://arxiv.org/abs/1201.0490.
24. Bastien F, Lamblin P, Pascanu R, et al. Theano: new features and speed improvements. arXiv Prepr arXiv…. 2012:1-10. http://arxiv.org/abs/1211.5590.
25. Bergstra J, Breuleux O, Bastien F, et al. Theano: a CPU and GPU math compiler in Python. In: 9th Python in Science Conference.; 2010:1-7. http://www-etud.iro.umontreal.ca/~wardefar/publications/theano_scipy2010.pdf.
26. Socher R, Pennington J, Huang E, Ng A. Semi-supervised recursive autoencoders for predicting sentiment distributions. Proc. 2011. http://dl.acm.org/citation.cfm?id=2145450
27. Hinton G, Salakhutdinov R. Reducing the dimensionality of data with neural networks. Science (80-). 2006. http://science.sciencemag.org/content/313/5786/504.short. Accessed August 8, 2016.
28. Mazumder R, Hastie T, Edu H, Tibshirani R, Edu T. Spectral Regularization Algorithms for Learning Large Incomplete Matrices. J Mach Learn Res. 2010;11:2287-2322.
29. Buuren S van. Flexible Imputation of Missing Data.; 2012. doi:10.1201/b11826.
30. Royston P. Multiple imputation of missing values: update of ice. Stata J. 2005. https://www.researchgate.net/profile/James_Cui2/publication/23780230_Buckley-James_method_for_analyzing_censored_data_with_an_application_to_a_cardiovascular_disease_and_an_HI VAIDS_study/links/53d5866d0cf228d363ea0b7a.pdf#page=59. Accessed August 10, 2016.
31. Kim J, Park H. Toward Faster Nonnegative Matrix Factorization: A New Algorithm and Comparisons.
32. Lin C-J. Projected Gradient Methods for Non-negative Matrix Factorization.
33. Hsieh C-J, Olsen PA. Nuclear Norm Minimization via Active Subspace Selection.
34. Breiman L, Cutler A. Random Forests. 2004. URL http//stat-www berkeley edu/users/breiman/RandomForests/cc home htm. 2014.
35. Nelwamondo F V., Mohamed S, Marwala T. Missing Data: A Comparison of Neural Network and Expectation Maximisation Techniques. April 2007. http://arxiv.org/abs/0704.3474. Accessed September 30, 2016.
36. Zoccolella S, Beghi E, Palagano G, et al. Riluzole and amyotrophic lateral sclerosis survival: a population-based study in southern Italy. Eur J Neurol. 2007;14(3):262-268. doi:10.1111/j.1468-1331.2006.01575.x.
37. Traynor BJ, Alexander M, Corr B, Frost E, Hardiman O. An outcome study of riluzole in amyotrophic lateral sclerosis. J Neurol. 2003;250(4):473-479. doi:10.1007/s00415-003-1026-z.
38. Czaplinski A, Yen AA, Appel SH. Forced vital capacity (FVC) as an indicator of survival and disease progression in an ALS clinic population. J Neurol Neurosurg Psychiatry. 2006;77(3):390-392. doi:10.1136/jnnp.2005.072660.