Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review

  title={Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review},
  author={Cao Xiao and E. Choi and Jimeng Sun},
  journal={Journal of the American Medical Informatics Association : JAMIA},
  pages={1419 - 1428}
  • Cao Xiao, E. Choi, Jimeng Sun
  • Published 8 June 2018
  • Computer Science
  • Journal of the American Medical Informatics Association : JAMIA
Objective To conduct a systematic review of deep learning models for electronic health record (EHR) data, and illustrate various deep learning architectures for analyzing different data sources and their target applications. [] Key MethodDesign/method We searched PubMed and Google Scholar for papers on deep learning studies using EHR data published between January 1, 2010, and January 31, 2018.

Figures and Tables from this paper

Machine learning approaches for electronic health records phenotyping: A methodical review
Objective: Accurate and rapid methods for phenotyping are a prerequisite to realizing the potential of electronic health records (EHRs) data for clinical and translational research. This study
Deep Learning for Electronic Health Records Analytics
The purpose of this study was to offer an intuitive explanation for possible use cases of deep learning with EHR and reflect on techniques that can be applied by health informatics professionals by giving technical intuitions and blue prints on how each clinical task can be approached by a deep learning algorithm.
A Predictive Approach Using Deep Feature Learning for Electronic Medical Records: A Comparative Study
A new predictive approach based on feature representation using deep feature learning and word embedding techniques to obtain effective and more robust features from EMRs, and then build prediction models on the top of them.
A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources
This work aims to review the major developments in various applications of GANs for EHRs and provides an overview of the proposed methodologies, and combines perspectives from healthcare applications and machine learning techniques in terms of source datasets and the fidelity and privacy evaluation of the generated synthetic datasets.
DeepNote-GNN: predicting hospital readmission using clinical notes and patient network
A novel hybrid deep learning model that integrates clinical notes information and patient network topological structure to improve 30-day hospital readmission prediction is proposed, and it is demonstrated that DeepNote-GNN achieves superior results compared to the state-of-the-art baselines on the 30- days readmission task.
Use of deep learning to develop continuous-risk models for adverse event prediction from electronic health records.
This protocol can be used by interdisciplinary teams with programming and clinical expertise to build deep-learning prediction models with alternate data sources and prediction tasks to predict various clinical and operational outcomes from structured electronic health record (EHR) data.
Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives
This paper reviews studies that use multimodal data, i.e. a combination of structured and unstructured data, from EHRs as input for conventional ML or DL models to address the targeted tasks.
Representation Learning with Autoencoders for Electronic Health Records: A Comparative Study
A predictive modeling approach based on deep learning based feature representations and word embedding techniques to obtain effective and robust features from EHRs and then build prediction models on top of them.
Recent Advances in Representation Learning for Electronic Health Records: A Systematic Review
A new taxonomy is proposed to categorize the state-of-the-art EHR RL methods into three categories: statistics learning-based RL methods, knowledge RL methods and graph RL methods to help researchers find the most appropriate methods.


Risk Prediction with Electronic Health Records: A Deep Learning Approach
A deep learning approach for phenotyping from patient EHRs by building a fourlayer convolutional neural network model for extracting phenotypes and perform prediction and the proposed model is validated on a real world EHR data warehouse under the specific scenario of predictive modeling of chronic diseases.
Scalable and accurate deep learning with electronic health records
A representation of patients’ entire raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format is proposed, and it is demonstrated that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization.
Distilling Knowledge from Deep Networks with Applications to Healthcare Domain
A novel knowledge-distillation approach called Interpretable Mimic Learning is introduced, to learn interpretable phenotype features for making robust prediction while mimicking the performance of deep learning models.
Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records
This work proposes a general deep learning framework which is able to boost risk prediction performance with limited EHR data and uses a modified generative adversarial network, namely ehrGAN, to augment the training dataset in a semi-supervised learning manner.
Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records
The findings indicate that deep learning applied to EHRs can derive patient representations that offer improved clinical predictions, and could provide a machine learning framework for augmenting clinical decision systems.
GRAM: Graph-based Attention Model for Healthcare Representation Learning
Compared to the basic RNN, GRAM achieved 10% higher accuracy for predicting diseases rarely observed in the training data and 3% improved area under the ROC curve for predicting heart failure using an order of magnitude less training data.
Comparing Rule-Based and Deep Learning Models for Patient Phenotyping
A CNN-based algorithm automatically learns the phrases associated with each patient phenotype that reduces the annotation complexity for clinical domain experts, who are normally required to develop task-specific annotation rules and identify relevant phrases.
Interpretable Deep Models for ICU Outcome Prediction
This paper introduces a simple yet powerful knowledge-distillation approach called interpretable mimic learning, which uses gradient boosting trees to learn interpretable models and at the same time achieves strong prediction performance as deep learning models.
Risk Factor Analysis Based on Deep Learning Models
Experimental results demonstrate that deep learning based methods are able to aggregate features sharing same characteristics, and reduce effects from unimportant and uncorrelated RFs, and give a good prediction performance in disease diagnosis.
Deep Computational Phenotyping
This work proposes two novel modifications to standard neural net training that address challenges and exploit properties that are peculiar, if not exclusive, to medical data, and examines a general framework for using prior knowledge to regularize parameters in the topmost layers.