보건의료 빅데이터에서의 자연어처리기법 적용방안 연구: 단어임베딩 방법을 중심으로 = A Study on the Application of Natural Language Processing in Health Care Big Data: Focusing on Word Embedding Methods

다국어 초록 (Multilingual Abstract)

While healthcare data sets include extensive information about patients, many researchers have limitations in analyzing them due to their intrinsic characteristics such as heterogeneity, longitudinal irregularity, and noise. In particular, since the majority of medical history information is recorded in text codes, the use of such information has been limited due to the high dimensionality of explanatory variables. To address this problem, recent studies applied word embedding techniques, originally developed for natural language processing, and derived positive results in terms of dimensional reduction and accuracy of the prediction model. This paper reviews the deep learning-based natural language processing techniques (word embedding) and summarizes research cases that have used those techniques in the health care field. Then we finally propose a research framework for applying deep learning-based natural language process in the analysis of domestic health insurance data.

참고문헌 (Reference)

1 Che Z, "xploiting convolutional neural network for risk prediction with medical feature embedding"

2 Rong X, "Word2vec parameter learning explained"

3 Tabak YP, "Using electronic health record data to develop inpatient mortality predictive model : Acute Laboratory Risk of Mortality Score(ALaRMS)" 21 (21): 455-463, 2014

4 Mani S, "Type 2 diabetes risk forecasting from EMR data using machine learning" 2012 : 606-615, 2012

5 Yang Liu, "Topical word embeddings" Association for the Advancement of Artificial Intelligence 2015

6 Sahlgren M, "The effects of data size and frequency range on distributional semantic models" Association for Computational Linguistics 2016

7 Kiela D, "Specializing word embeddings for similarity or relatedness" Association for Computational Linguistics 2015

8 Giatsoglou M, "Sentiment analysis leveraging emotions and word embeddings" 69 : 214-224, 2017

9 Rajkomar A, "Scalable and accurate deep learning with electronic health records" 1 : 18-, 2018

10 Young T, "Recent trends in deep learning based natural language processing" 13 (13): 55-75, 2018

11 Himes BE, "Prediction of chronic obstructive pulmonary disease(COPD)in asthma patients using electronic medical records" 16 (16): 371-379, 2009

12 Nagata M, "Prediction models for risk of type-2 diabetes using health claims" Association for Computational Linguistics 2018

13 Jin B, "Predicting the risk of heart failure with EHR sequential data modeling" 6 : 9256-9261, 2018

14 Zhang J, "Patient2vec : a personalized interpretable deep representation of the longitudinal electronic health record" 6 : 65333-65346, 2018

15 Goldstein BA, "Opportunities and challenges in developing risk prediction models with electronic health records data : a systematic review" 24 (24): 198-208, 2017

16 Kang H, "National-level use of health care big data and its policy implications" Korea Institute for Health and Social Affairs 2016

17 Choi E, "Multi-layer representation learning for medical concepts"

18 Trask A, "Modeling order in neural word embeddings at scale"

19 De Vine L, "Medical semantic similarity with a neural language model" Association for Computing Machinery 2014

20 Choi E, "Medical concept representation learning from electronic health records and its application on heart failure prediction"

21 Cai X, "Medical concept embedding with time-aware attention"

22 Mikolov T, "Linguistic regularities in continuous space word representations" Association for Computational Linguistics 746-751, 2013

23 Choi Y, "Learning low-dimensional representations of medical concepts" 2016 : 41-50, 2016

24 Bai T, "Joint learning of representations of medical concepts and words from EHR data" IEEE 2017

25 Kennedy EH, "Improved cardiovascular risk prediction using nonparametric regression and electronic health record data" 51 (51): 251-258, 2013

26 Pennington J, "Glove: global vectors for word representation" Association for Computational Linguistics 2014

27 Mikolov T, "Extensions of recurrent neural network language model" IEEE 2011

28 Minarro-Gimenez JA, "Exploring the application of deep learning techniques on medical text corpora" 205 : 584-588, 2014

29 Bojanowski P, "Enriching word vectors with subword information" 5 : 135-146, 2017

30 Mikolov T, "Efficient estimation of word representations in vector space"

31 Choi E, "Doctor AI : predicting clinical events via recurrent neural networks" 56 : 301-318, 2016

32 Harris ZS, "Distributional structure" 10 (10): 146-162, 1954

33 Mikolov T, "Distributed representations of words and phrases and their compositionality"

34 Le QV, "Distributed representations of sentences and documents" International Machine Learning Society 2014

35 Pham T, "DeepCare: a deep dynamic memory model for predictive medicine" Springer 30-41, 2017

36 Miotto R, "Deep patient : an unsupervised representation to predict the future of patients from the electronic health records" 6 : 26094-, 2016

37 Miotto R, "Deep learning for healthcare: review, opportunities and challenges" 19 (19): 1236-1246, 2018

38 Zhang E, "Deep holistic representation learning from EHR" IEEE 2018

39 Huang K, "ClinicalBERT: modeling clinical notes and predicting hospital readmission"

40 Rodriguez P, "Beyond one-hot encoding : lower dimensional target embedding" 75 : 21-31, 2018

41 Amarasingham R, "An automated model to identify heart failure patients at risk for 30-day readmission or death using electronic medical record data" 48 (48): 981-988, 2010

42 Bellman, R., "Adaptive control processes: a guided tour" Princeton University Press 1972

43 Chang E, "A study on the advancement of utilization of medical big data" Health Insurance Review & Assessment service 2016

44 Saltzman JR, "A simple risk score accurately predicts in-hospital mortality, length of stay, and cost in acute upper GI bleeding" 74 (74): 1215-1224, 2011

45 Bengio Y, "A neural probabilistic language model" 3 : 1137-1155, 2003