A Survey of Deep Learning for Electronic Health Records
Source abstract
Abstract
Medical data is an important part of modern medicine. However, with the rapid increase in the amount of data, it has become hard to use this data effectively. The development of machine learning, such as feature engineering, enables researchers to capture and extract valuable information from medical data. Many deep learning methods are conducted to handle various subtasks of EHR from the view of information extraction and representation learning. This survey designs a taxonomy to summarize and introduce the existing deep learning-based methods on EHR, which could be divided into four types (Information Extraction, Representation Learning, Medical Prediction and Privacy Protection). Furthermore, we summarize the most recognized EHR datasets, MIMIC, eICU, PCORnet, Open NHS, NCBI-disease and i2b2/n2c2 NLP Research Data Sets, and introduce the labeling scheme of these datasets. Furthermore, we provide an overview of deep learning models in various EHR applications. Finally, we conclude the challenges that EHR tasks face and identify avenues of future deep EHR research.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Healthcare · Topic Modeling · Biomedical Text Mining and Ontologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China
School of Cyber Science and Engineering, Southeast University, Nanjing 211100, China
Department of computer science, Texas Tech University, Lubbock, TX 79409, USA
School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou 215000, China
Funding
National Natural Science Foundation of China · Innovative Team of Jiangsu Province · Science and Technology Development Project of Suzhou
References (100+)
Show source-provided references
1. Deep patient: An unsupervised representation to predict the future of patients from the electronic health records10.1038/srep26094 ↗
2. Jagannatha, A.N., and Yu, H. (2016, January 1–5). Structured prediction models for RNN based sequence labeling in clinical text. Proceedings of the EMNLP 2016: Conference on Empirical Methods in Natural Language Processing, Austin, TX, USA.10.18653/v1/D16-1082 ↗
3. Bidirectional RNN for medical event detection in electronic health records
4. Poongodi, T., Sumathi, D., Suresh, P., and Balusamy, B. (2021). Deep Learning Techniques for Electronic Health Record (EHR) Analysis. Bio-Inspired Neurocomputing, Springer.10.1007/978-981-15-5495-7_5 ↗
5. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
6. Standard electronic health record (EHR) framework for Indian healthcare system10.1007/s10742-020-00238-0 ↗
7. Harrison, J.E., Weber, S., Jakob, R., and Chute, C.G. (2021). ICD-11: An international classification of diseases for the twenty-first century. BMC Med. Inform. Decis. Mak., 21.10.1186/s12911-021-01534-6 ↗
8. Nomenclature for pediatric and congenital cardiac care: Unification of clinical and administrative nomenclature–the 2021 international paediatric and congenital cardiac code (IPCCC) and the eleventh revision of the International classification of diseases (ICD-11)10.1017/S104795112100281X ↗
9. Bowie, M.J. (2021). Understanding Current Procedural Terminology and HCPCS Coding Systems, 2021, Cengage Learning.
10. Benson, T., and Grieve, G. (2021). LOINC. Principles of Health Interoperability, Springer.10.1007/978-3-030-56883-2 ↗
11. Identification of World Health Organisation ship’s medicine chest contents by Anatomical Therapeutic Chemical (ATC) classification codes10.5603/IMH.2017.0007 ↗
12. Recent developments in clinical terminologies—SNOMED CT, LOINC, and RxNorm10.1055/s-0038-1667077 ↗
13. Applications of support vector machine (SVM) learning in cancer genomics
14. Random forest: A classification and regression tool for compound classification and QSAR modeling10.1021/ci034160g ↗
15. Health insurance portability and accountability act of 1996
16. MIMIC-III, a freely accessible critical care database10.1038/sdata.2016.35 ↗
17. Johnson, A., Bulgarelli, L., Pollard, T., Horng, S., Celi, L.A., and Mark, R. (2021, August 23). Mimic-iv. PhysioNet. Available online: https://physionet.org/content/mimiciv/1.0/.
18. The eICU Collaborative Research Database, a freely available multi-center database for critical care research10.1038/sdata.2018.178 ↗
19. Launching PCORnet, a national patient-centered clinical research network10.1136/amiajnl-2014-002747 ↗
20. Automated systems for the de-identification of longitudinal clinical narratives: Overview of 2014 i2b2/UTHealth shared task Track 110.1016/j.jbi.2015.06.007 ↗
21. Deep learning10.1038/nature14539 ↗
22. LeCun, Y., Bengio, Y., and Bottou, L. (2022, November 03). LeNet-5, Convolutional Neural Networks. Available online: http://yann.lecun.com/exdb/lenet.
23. Imagenet classification with deep convolutional neural networks10.1145/3065386 ↗
24. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
25. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
26. Chen, Y. (2015). Convolutional Neural Network for Sentence Classification. [Master’s Thesis, University of Waterloo].
27. Sundermeyer, M., Schlüter, R., and Ney, H. (2012, January 9–13). LSTM neural networks for language modeling. Proceedings of the INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association, Portland, OR, USA.10.21437/Interspeech.2012-65 ↗
28. Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv.
29. A recurrent latent variable model for sequential data
30. Generative adversarial networks10.1145/3422622 ↗
31. Dai, B., Fidler, S., Urtasun, R., and Lin, D. (2017, January 22–29). Towards diverse and natural image descriptions via a conditional gan. Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.323 ↗
32. Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv.
33. Deep generative image models using a laplacian pyramid of adversarial networks
34. Friedrich, M., Köhn, A., Wiedemann, G., and Biemann, C. (2019). Adversarial learning of privacy-preserving text representations for de-identification of medical records. arXiv.10.18653/v1/P19-1584 ↗
35. Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv.
36. Tai, K.S., Socher, R., and Manning, C.D. (2015). Improved semantic representations from tree-structured long short-term memory networks. arXiv.10.3115/v1/P15-1150 ↗
37. Wang, C., Pan, S., Long, G., Zhu, X., and Jiang, J. (2017, January 6–10). Mgae: Marginalized graph autoencoder for graph clustering. Proceedings of the 2017 ACM Conference on Information and Knowledge Management, Singapore.10.1145/3132847.3132967 ↗
38. Graph attention networks
39. Zhu, R., Zhao, K., Yang, H., Lin, W., Zhou, C., Ai, B., Li, Y., and Zhou, J. (2019). Aligraph: A comprehensive graph neural network platform. arXiv.10.14778/3352063.3352127 ↗
40. Liu, M., Luo, Y., Wang, L., Xie, Y., Yuan, H., Gui, S., Yu, H., Xu, Z., Zhang, J., and Liu, Y. (2021). Dig: A turnkey library for diving into graph deep learning research. arXiv.
41. Cen, Y., Hou, Z., Wang, Y., Chen, Q., Luo, Y., Yao, X., Zeng, A., Guo, S., Zhang, P., and Dai, G. (2021). Cogdl: An extensive toolkit for deep learning on graphs. arXiv.
42. Lu, Q., Nguyen, T.H., and Dou, D. (2021, January 11–15). Predicting patient readmission risk from medical text via knowledge graph enhanced multiview graph convolution. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Montreal, QC, Canada.10.1145/3404835.3463062 ↗
43. Natural language processing of symptoms documented in free-text narratives of electronic health records: A systematic review10.1093/jamia/ocy173 ↗
44. Natural language processing of clinical notes on chronic diseases: Systematic review10.2196/12239 ↗
45. Use of Natural Language Processing to Extract Clinical Cancer Phenotypes from Electronic Medical RecordsNatural Language Processing for Cancer Phenotypes from EMRs10.1158/0008-5472.CAN-19-0579 ↗
46. BioBERT: A pre-trained biomedical language representation model for biomedical text mining10.1093/bioinformatics/btz682 ↗
47. Sachan, D.S., Xie, P., Sachan, M., and Xing, E.P. (2018, January 17–18). Effective use of bidirectional language modeling for transfer learning in biomedical named entity recognition. Proceedings of the Machine Learning for Healthcare Conference, Palo Alto, CA, USA.
48. Cross-type biomedical named entity recognition with deep multi-task learning10.1093/bioinformatics/bty869 ↗
49. Zhao, S., Liu, T., Zhao, S., and Wang, F. (February, January 27). A neural multi-task learning framework to jointly model medical named entity recognition and normalization. Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
50. Nie, B., Li, C., and Wang, H. (2021). KA-NER: Knowledge Augmented Named Entity Recognition. CCKS 2021: Knowledge Graph and Semantic Computing: Knowledge Graph Empowers New Infrastructure Construction, Proceedings of the 6th China Conference on Knowledge Graph and Semantic Computing, Guangzhou, China, 4–7 November 2021, Springer.10.1007/978-981-16-6471-7_5 ↗
51. A study of deep learning approaches for medication and adverse drug event extraction from clinical text10.1093/jamia/ocz063 ↗
52. Adverse drug event detection from electronic health records using hierarchical recurrent neural networks with dual-level embedding10.1007/s40264-018-0765-9 ↗
53. Clinical relation extraction toward drug safety surveillance using electronic health record narratives: Classical learning versus deep learning10.2196/publichealth.9361 ↗
54. Relation extraction from clinical narratives using pre-trained language models
55. Sun, X., Dong, K., Ma, L., Sutcliffe, R., He, F., Chen, S., and Feng, J. (2019). Drug-drug interaction extraction via recurrent hybrid convolutional neural networks with an improved focal loss. Entropy, 21.10.3390/e21010037 ↗
56. Uncertainty-gated stochastic sequential model for ehr mortality prediction10.1109/TNNLS.2020.3016670 ↗
57. Che, Z., Kale, D., Li, W., Bahadori, M.T., and Liu, Y. (2015, January 10–13). Deep computational phenotyping. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, Australia.10.1145/2783258.2783365 ↗
58. Scalable and accurate deep learning with electronic health records10.1038/s41746-018-0029-1 ↗
59. Cheng, Y., Wang, F., Zhang, P., and Hu, J. (2016, January 5–7). Risk prediction with electronic health records: A deep learning approach. Proceedings of the 2016 SIAM International Conference on Data Mining, Miami, FL, USA.10.1137/1.9781611974348.49 ↗
60. Learning low-dimensional representations of medical concepts
61. Wang, F., Lee, N., Hu, J., Sun, J., and Ebadollahi, S. (2012, January 12–16). Towards heterogeneous temporal clinical event pattern discovery: A convolutional approach. Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Beijing, China.10.1145/2339530.2339605 ↗
62. Zhou, J., Wang, F., Hu, J., and Ye, J. (2014, January 24–27). From micro to macro: Data driven phenotyping by densification of longitudinal electronic medical records. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.10.1145/2623330.2623711 ↗
63. Liu, C., Wang, F., Hu, J., and Xiong, H. (2015, January 10–13). 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, Sydney, Australia.10.1145/2783258.2783352 ↗
64. Choi, E., Bahadori, M.T., Song, L., Stewart, W.F., and Sun, J. (2017, January 13–17). GRAM: Graph-based attention model for healthcare representation learning. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada.10.1145/3097983.3098126 ↗
65. Ma, F., You, Q., Xiao, H., Chitta, R., Zhou, J., and Gao, J. (2018, January 22–26). Kame: Knowledge-based attention model for diagnosis prediction in healthcare. Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, Italy.10.1145/3269206.3271701 ↗
66. Med-BERT: Pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction10.1038/s41746-021-00455-y ↗
67. Choi, E., Xu, Z., Li, Y., Dusenberry, M., Flores, G., Xue, E., and Dai, A. (2020, January 7–12). Learning the graphical structure of electronic health records with graph convolutional transformer. Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i01.5400 ↗
68. Song, H., Rajan, D., Thiagarajan, J., and Spanias, A. (2018, January 2–3). Attend and diagnose: Clinical time series analysis using attention models. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11635 ↗
69. BEHRT: Transformer for electronic health records10.1038/s41598-020-62922-y ↗
70. Choi, E., Schuetz, A., Stewart, W.F., and Sun, J. (2016). Medical concept representation learning from electronic health records and its application on heart failure prediction. arXiv.
71. Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)10.1016/j.jbi.2015.01.012 ↗
72. Liu, J., Zhang, Z., and Razavian, N. (2018, January 17–18). Deep EHR: Chronic disease prediction using medical notes. Proceedings of the 3rd Machine Learning for Healthcare Conference, Palo Alto, CA, USA.
73. STAN: Spatio-temporal attention network for pandemic prediction using real-world evidence10.1093/jamia/ocaa322 ↗
74. Machine learning and end-to-end deep learning for the detection of chronic heart failure from heart sounds10.1109/ACCESS.2020.2968900 ↗
75. Multimodal temporal-clinical note network for mortality prediction10.1186/s13326-021-00235-3 ↗
76. Peng, X., Long, G., Shen, T., Wang, S., Jiang, J., and Zhang, C. (2020, January 17–20). BiteNet: Bidirectional temporal encoder network to predict medical outcomes. Proceedings of the 2020 IEEE International Conference on Data Mining (ICDM), Sorrento, Italy.10.1109/ICDM50108.2020.00050 ↗
77. De-identification of patient notes with recurrent neural networks10.1093/jamia/ocw156 ↗
78. Yadav, S., Ekbal, A., Saha, S., and Bhattacharyya, P. Deep learning architecture for patient data de-identification in clinical records. Proceedings of the Clinical Natural Language Processing Workshop (ClinicalNLP).
79. De-identification of electronic health record using neural network10.1038/s41598-020-75544-1 ↗
80. Privacy-preserving deep learning for the detection of protected health information in real-world data: Comparative evaluation10.2196/14064 ↗
81. Coavoux, M., Narayan, S., and Cohen, S.B. (2018). Privacy-preserving neural representations of text. arXiv.10.18653/v1/D18-1001 ↗
82. Jordon, J., Yoon, J., and Van Der Schaar, M. (May, January 30). PATE-GAN: Generating synthetic data with differential privacy guarantees. Proceedings of the Sixth International Conference on Learning Representations, Vancouver, BC, Canada.
83. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv.
84. Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P.A. (2008, January 5–9). Extracting and composing robust features with denoising autoencoders. Proceedings of the 25th International Conference on Machine Learning, Helsinki, Finland.10.1145/1390156.1390294 ↗
85. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
86. Doersch, C. (2016). Tutorial on variational autoencoders. arXiv.
87. Salah, R., Vincent, P., and Muller, X. (July, January 28). Contractive auto-encoders: Explicit invariance during feature extraction. Proceedings of the 28th International Conference on International Conference on Machine Learning, Bellevue, WA, USA.
88. NirmalaDevi, M., alias Balamurugan, S.A., and Swathi, U. (2013, January 25–26). An amalgam KNN to predict diabetes mellitus. Proceedings of the 2013 IEEE International Conference on Emerging Trends in Computing, Communication and Nanotechnology (ICECCN), Tirunelveli, India.10.1109/ICE-CCN.2013.6528591 ↗
89. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes10.1016/S0895-4356(96)00002-9 ↗
90. A review of the logistic regression model with emphasis on medical research
91. Liver disease prediction using SVM and Naïve Bayes algorithms
92. Mantzaris, D.H., Anastassopoulos, G.C., and Lymberopoulos, D.K. (2008, January 8–10). Medical disease prediction using artificial neural networks. Proceedings of the 2008 8th IEEE International Conference on BioInformatics and BioEngineering, Athens, Greece.10.1109/BIBE.2008.4696782 ↗
93. Lipton, Z.C., Kale, D.C., Elkan, C., and Wetzel, R. (2015). Learning to diagnose with LSTM recurrent neural networks. arXiv.
94. Wu, L., Fisch, A., Chopra, S., Adams, K., Bordes, A., and Weston, J. Starspace: Embed all the things! In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA, 2–3 February 2018.10.1609/aaai.v32i1.11996 ↗
95. A simple algorithm for identifying negated findings and diseases in discharge summaries10.1006/jbin.2001.1029 ↗
96. Deng, S., Wang, S., Rangwala, H., Wang, L., and Ning, Y. (2019). Graph message passing with cross-location attentions for long-term ILI prediction. arXiv.
97. Kapoor, A., Ben, X., Liu, L., Perozzi, B., Barnes, M., Blais, M., and O’Banion, S. (2020). Examining covid-19 forecasting using spatio-temporal graph neural networks. arXiv.
98. Choi, E., Bahadori, M.T., Sun, J., Kulas, J., Schuetz, A., and Stewart, W. (2016, January 5–10). Retain: An interpretable predictive model for healthcare using reverse time attention mechanism. Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain.
99. Deepr: A convolutional net for medical records10.1109/JBHI.2016.2633963 ↗
100. Ma, F., Chitta, R., Zhou, J., You, Q., Sun, T., and Gao, J. (2017, January 13–17). Dipole: Diagnosis prediction in healthcare via attention-based bidirectional recurrent neural networks. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada.10.1145/3097983.3098088 ↗