Privacy-preserving predictive modeling: Harmonization of contextual embeddings from different sources

JMIR Medical Informatics

Volumn 6, Issue 2, 2018, Pages

  Huang, Yingxiang ^a   Lee, Junghye ^a,b,c   Wang, Shuang ^a   Sun, Jimeng ^d   Liu, Hongfang ^e   Jiang, Xiaoqian ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b Ulsan National Institute of Science and Technology   (South Korea)

^c Pohang University of Science and Technology (POSTECH)   (South Korea)

^d Georgia Institute of Technology   (United States)

^e Mayo Clinic College of Medicine   (United States)

Author keywords

Contextual embedding; Interoperability; Patient data privacy; Predictive models

Indexed keywords

EID: 85056933801     PISSN: None     EISSN: 22919694     Source Type: Journal    
DOI: 10.2196/medinform.9455     Document Type: Article

References (37)

1. Mandl KD, Kohane IS. Federalist principles for healthcare data networks. Nat Biotechnol 2015 Apr; 33(4):360-363 [FREE Full text] [doi: 10.1038/nbt.3180] [Medline: 25850061]
2. Kohane IS, Drazen JM, Campion EW. A glimpse of the next 100 years in medicine. N Engl J Med 2012 Dec 27; 367(26):2538-2539. [doi: 10.1056/NEJMe1213371] [Medline: 23268669]
3. Patten IS, Rana S, Shahul S, Rowe GC, Jang C, Liu L, et al. Cardiac angiogenic imbalance leads to peripartum cardiomyopathy. Nature 2012 May 9; 485(7398):333-338 [FREE Full text] [doi: 10.1038/nature11040] [Medline: 22596155]
4. Berndt SI, Gustafsson S, Mägi R, Ganna A, Wheeler E, Feitosa MF, et al. Genome-wide meta-analysis identifies 11 new loci for anthropometric traits and provides insights into genetic architecture. Nat Genet 2013 May; 45(5):501-512 [FREE Full text] [doi: 10.1038/ng.2606] [Medline: 23563607]
5. Office for Civil Rights HHS. Standards for privacy of individually identifiable health information. Final rule. Fed Regist 2002 Aug 14; 67(157):53181-53273. [Medline: 12180470]
6. Douglass MM, Cliffford GD, Reisner A, Long WJ, Moody GB, Mark RG. De-identification algorithm for free-text nursing notes. 2005 Presented at: Computers in Cardiology; September 25-28, 2005; Lyon, France. [doi: 10.1109/CIC.2005.1588104]
7. Johnson AE, Pollard TJ, Shen L, Lehman LW, Feng M, Ghassemi M, et al. MIMIC-III, a freely accessible critical care database. Sci Data 2016 May 24; 3:160035 [FREE Full text] [doi: 10.1038/sdata.2016.35] [Medline: 27219127]
8. Dernoncourt F, Lee JY, Uzuner O, Szolovits P. De-identification of patient notes with recurrent neural networks. J Am Med Inform Assoc 2017 May 1; 24(3):596-606. [doi: 10.1093/jamia/ocw156] [Medline: 28040687]
9. Neamatullah I, Douglass MM, Lehman LW, Reisner A, Villarroel M, Long WJ, et al. Automated de-identification of free-text medical records. BMC Med Inform Decis Mak 2008 Jul 24; 8:32 [FREE Full text] [doi: 10.1186/1472-6947-8-32] [Medline: 18652655]
10. South BR, Mowery D, Suo Y, Leng J, Ferrández Ó, Meystre SM, et al. Evaluating the effects of machine pre-annotation and an interactive annotation interface on manual de-identification of clinical text. J Biomed Inform 2014 Aug; 50:162-172 [FREE Full text] [doi: 10.1016/j.jbi.2014.05.002] [Medline: 24859155]
11. El Emam K, Jonker E, Arbuckle L, Malin B. A systematic review of re-identification attacks on health data. PLoS One 2011; 6(12):e28071 [FREE Full text] [doi: 10.1371/journal.pone.0028071] [Medline: 22164229]
12. Wu Y, Jiang X, Kim J, Ohno-Machado L. Grid Binary LOgistic REgression (GLORE): Building shared models without sharing data. J Am Med Inform Assoc 2012; 19(5):758-764 [FREE Full text] [doi: 10.1136/amiajnl-2012-000862] [Medline: 22511014]
13. Jiang W, Li P, Wang S, Wu Y, Xue M, Ohno-Machado L, et al. WebGLORE: A web service for Grid LOgistic REgression. Bioinformatics 2013 Dec 15; 29(24):3238-3240 [FREE Full text] [doi: 10.1093/bioinformatics/btt559] [Medline: 24072732]
14. Yu H, Jiang X, Vaidya J. Privacy-preserving SVM using nonlinear kernels on horizontally partitioned data. 2006 Presented at: SAC '06 Proceedings of the 2006 ACM symposium on Applied computing; April 23-27, 2006; Dijon, France. [doi: 10.1145/1141277.1141415]
15. Que J, Jiang X, Ohno-Machado L. A collaborative framework for distributed privacy-preserving support vector machine learning. AMIA Annu Symp Proc 2012; 2012:1350-1359 [FREE Full text] [Medline: 23304414]
16. Shaneck M, Kim Y, Kumar V. Privacy preserving nearest neighbor search. 2006 Presented at: Sixth IEEE International Conference on Data Mining - Workshops (ICDMW'06); 18-22 December 2006; Hong Kong, China. [doi: 10.1109/ICDMW.2006.133]
17. Lu C, Wang S, Ji Z, Wu Y, Xiong L, Jiang X, et al. WebDISCO: A web service for distributed cox model learning without patient-level data sharing. J Am Med Inform Assoc 2015 Nov; 22(6):1212-1219 [FREE Full text] [doi: 10.1093/jamia/ocv083] [Medline: 26159465]
18. Kim Y, Sun J, Yu H, Jiang X. Federated tensor factorization for computational phenotyping. KDD 2017 Aug; 2017:887-895 [FREE Full text] [doi: 10.1145/3097983.3098118] [Medline: 29071165]
19. Farhan W, Wang Z, Huang Y, Wang S, Wang F, Jiang X. A predictive model for medical events based on contextual embedding of temporal sequences. JMIR Med Inform 2016 Nov 25; 4(4):e39 [FREE Full text] [doi: 10.2196/medinform.5977] [Medline: 27888170]
20. Choi E, Bahadori MT, Searles E, Coffey C, Thompson M, Bost J, et al. Multi-layer Representation Learning for Medical Concepts. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.: ACM Press; 2016 Presented at: 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16; August 13-17, 2016; San Francisco, California. [doi: 10.1145/2939672.2939823]
21. Wu Y, Jiang M, Lei J, Xu H. Named entity recognition in Chinese clinical text using deep neural network. Stud Health Technol Inform 2015; 216:624-628 [FREE Full text] [Medline: 26262126]
22. Liu Y, Ge T, Mathews KS, Ji H, McGuinness DL. Exploiting Task-Oriented Resources to Learn Word Embeddings for Clinical Abbreviation Expansion. In: Proceedings of the 2015 Workshop on Biomedical Natural Language Processing (BioNLP 2015). USA: Association for Computational Linguistics; 2015 Presented at: 2015 Workshop on Biomedical Natural Language Processing (BioNLP 2015); July 30, 2015; Beijing, China.
23. Nguyen P, Tran T, Wickramasinghe N, Venkatesh S. $mathtt {Deepr}$: A convolutional net for medical records. IEEE J Biomed Health Inform 2017 Dec; 21(1):22-30. [doi: 10.1109/JBHI.2016.2633963] [Medline: 27913366]
24. Arxiv. Exploiting Convolutional Neural Network for Risk Prediction with Medical Feature Embedding URL:https://arxiv. org/pdf/1701.07474.pdf [accessed 2018-04-03] [WebCite Cache ID 6yPoARTc0]
25. Shickel B, Tighe PJ, Bihorac A, Rashidi P. Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis. IEEE J Biomed Health Inform 2017; 1:1. [doi: 10.1109/JBHI.2017.2767063]
26. GitHub. URL:https://github.com/easonfg/harmonization
27. Aronson AR. Effective mapping of biomedical text to the UMLS Metathesaurus: The MetaMap program. Proc AMIA Symp 2001:17-21 [FREE Full text] [Medline: 11825149]
28. Mikolov T, Chen K, Corrado G, Dean J. Efficient Estimation of Word Representations in Vector Space. 2013. URL:http://llcao.net/cu-deeplearning15/presentation/Distributed_Representation_of_Words.pdf[WebCite Cache ID 6z9se0RPa]
29. Pennington J, Socher R, Manning CD. GloVe: Global Vectors for Word Representation. URL:https://nlp.stanford.edu/pubs/glove.pdf[WebCite Cache ID 6yPoc21eg]
30. Choo J, Bohn S, Nakamura GC, White AM, Park H. Heterogeneous Data Fusion via Space Alignment Using Nonmetric Multidimensional Scaling. 2012 Presented at: Proceedings of the 2012 SIAM International Conference on Data Mining; April 26-28, 2012; Anaheim, California. [doi: 10.1137/1.9781611972825.16]
31. Gower JC. Generalized procrustes analysis. Psychometrika 1975 Mar; 40(1):33. [doi: 10.1007/BF02291478]
32. Stubbs A, Uzuner Ö. Annotating longitudinal clinical narratives for de-identification: The 2014 i2b2/UTHealth corpus. J Biomed Inform 2015 Dec; 58 Suppl:S20-S29 [FREE Full text] [doi: 10.1016/j.jbi.2015.07.020] [Medline: 26319540]
33. Stubbs A, Kotfila C, Uzuner Ö. Automated systems for the de-identification of longitudinal clinical narratives: Overview of 2014 i2b2/UTHealth shared task Track 1. J Biomed Inform 2015 Dec; 58 Suppl:S11-S19 [FREE Full text] [doi: 10.1016/j.jbi.2015.06.007] [Medline: 26225918]
34. Stubbs A, Uzuner Ö. Annotating risk factors for heart disease in clinical narratives for diabetic patients. J Biomed Inform 2015 Dec; 58 Suppl:S78-S91 [FREE Full text] [doi: 10.1016/j.jbi.2015.05.009] [Medline: 26004790]
35. Stubbs A, Kotfila C, Xu H, Uzuner Ö. Identifying risk factors for heart disease over time: Overview of 2014 i2b2/UTHealth shared task Track 2. J Biomed Inform 2015 Dec; 58 Suppl:S67-S77 [FREE Full text] [doi: 10.1016/j.jbi.2015.07.001] [Medline: 26210362]
36. Sun W, Rumshisky A, Uzuner O. Annotating temporal information in clinical narratives. J Biomed Inform 2013 Dec; 46 Suppl:S5-12 [FREE Full text] [doi: 10.1016/j.jbi.2013.07.004] [Medline: 23872518]
37. Narayanan A, Chandramohan M, Venkatesan R, Chen L, Liu Y, Jaiswal S. MLG Workshop. 2017. graph2vec: Learning Distributed Representations of Graphs URL:http://www.mlgworkshop.org/2017/paper/MLG2017_paper_21.pdf[WebCite Cache ID 6z9smNJfu]