Predicting Patient Outcomes with Graph Representation Learning (2021-01-11T00:00:00.000000Z)

TL;DR

This work proposes LSTM-GNN for patient outcome prediction tasks: a hybrid model combining Long Short-Term Memory networks (LSTMs) for extracting temporal features and Graph Neural Networks (GNNs) for extracts the patient neighbourhood information.

Abstract

Recent work on predicting patient outcomes in the Intensive Care Unit (ICU) has focused heavily on the physiological time series data, largely ignoring sparse data such as diagnoses and medications. When they are included, they are usually concatenated in the late stages of a model, which may struggle to learn from rarer disease patterns. Instead, we propose a strategy to exploit diagnoses as relational information by connecting similar patients in a graph. To this end, we propose LSTM-GNN for patient outcome prediction tasks: a hybrid model combining Long Short-Term Memory networks (LSTMs) for extracting temporal features and Graph Neural Networks (GNNs) for extracting the patient neighbourhood information. We demonstrate that LSTM-GNNs outperform the LSTM-only baseline on length of stay prediction tasks on the eICU database. More generally, our results indicate that exploiting information from neighbouring patient cases using graph neural networks is a promising research direction, yielding tangible returns in supervised learning performance on Electronic Health Records.

Authors

Petar Velickovic

7 papers

N. Lane

3 papers

Emma Rocheteau

2 papers

TL;DR

Abstract

Authors

References32 items

Temporal pointwise convolutional networks for length of stay prediction in the intensive care unit

Graph-Representation of Patient Data: a Systematic Literature Review

Benchmarking machine learning models on eICU critical care dataset

Graph Convolutional Transformer: Learning the Graphical Structure of Electronic Health Records

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

Learning Representations of Missing Data for Predicting Patient Outcomes

How Powerful are Graph Neural Networks?

dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning

The eICU Collaborative Research Database, a freely available multi-center database for critical care research

Dynamic Graph CNN for Learning on Point Clouds

Scalable and accurate deep learning with electronic health records

Graph Attention Networks

Learning Graph Representations with Embedding Propagation

Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting

Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting

Inductive Representation Learning on Large Graphs

Neural Message Passing for Quantum Chemistry

Multitask learning and benchmarking with clinical time series data

A systematic review on the effect of the organisation of hospital discharge on patient health outcomes

Semi-Supervised Classification with Graph Convolutional Networks

Adam: A Method for Stochastic Optimization

Early warning system scores for clinical deterioration in hospitalized patients: a systematic review.

An eight year audit before and after the introduction of modified early warning score (MEWS) charts, of patients admitted to a tertiary referral intensive care unit after CPR.

How Length of Stay for Congestive Heart Failure Patients Was Reduced Through Six Sigma Methodology and Physician Leadership

Factors influencing length of stay in the intensive care unit.

A new model for learning in graph domains

Long Short-Term Memory

A Coefficient of Agreement for Nominal Scales

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Pytorch lightning

Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review

The Graph Neural Network Model

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names