Deep Learning with Heterogeneous Graph Embeddings for Mortality Prediction from Electronic Health Records

  title={Deep Learning with Heterogeneous Graph Embeddings for Mortality Prediction from Electronic Health Records},
  author={Tingyi Wanyan and Hossein Honarvar and Ariful Azad and Ying Ding and Benjamin Scott Glicksberg},
  journal={Data Intelligence},
Computational prediction of in-hospital mortality in the setting of an intensive care unit can help clinical practitioners to guide care and make early decisions for interventions. As clinical data are complex and varied in their structure and components, continued innovation of modelling strategies is required to identify architectures that can best model outcomes. In this work, we trained a Heterogeneous Graph Model (HGM) on electronic health record (EHR) data and used the resulting embedding… 
1 Citations
Postpartum pelvic organ prolapse assessment via adversarial feature complementation in heterogeneous data
  • Mingxuan Luo, Xiaoshan Yang
  • Neural Computing and Applications
  • 2022


HCNN: Heterogeneous Convolutional Neural Networks for Comorbid Risk Prediction with Electronic Health Records
A new predictive learning framework, Heterogeneous Convolutional Neural Network (HCNN), is proposed that represents EHRs as graphs with heterogeneous attributes, and a novel deep learning methodology for risk prediction of multiple comorbid diseases is developed.
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.
MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare
Multilevel Medical Embedding (MiME) is proposed which learns the multilevel embedding of EHR data while jointly performing auxiliary prediction tasks that rely on this inherent EHR structure without the need for external labels.
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.
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.
Graph Convolutional Transformer: Learning the Graphical Structure of Electronic Health Records
This paper argues that the Transformer is a suitable model to learn the hidden EHR structure, and proposes the Graph Convolutional Transformer, which uses data statistics to guide the structure learning process.
A deep learning model for real-time mortality prediction in critically ill children
A deep model-based, data-driven early warning score tool that can predict mortality in critically ill children and may be useful for the timely identification of deteriorating patients is developed and validated.
Machine learning for real-time prediction of complications in critical care: a retrospective study.
Improvements in prediction for all three investigated clinical outcomes have the potential to improve critical care and are encouraging for prospective deployment in critical care settings to direct the staff's attention towards patients who are most at risk.
Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis
This review surveys the current research on applying deep learning to clinical tasks based on EHR data, where a variety of deep learning techniques and frameworks are being applied to several types of clinical applications including information extraction, representation learning, outcome prediction, phenotyping, and deidentification.
Phe2vec: Automated Disease Phenotyping based on Unsupervised Embeddings from Electronic Health Records
Phe2vec aims to optimize clinical informatics research by augmenting current frameworks to characterize patients by condition and derive reliable disease cohorts by providing a solution to improve time-consuming phenotyping pipelines.