About: A hybrid method of recurrent neural network and graph neural network for next-period prescription prediction

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: A hybrid method of recurrent neural network and graph neural network for next-period prescription prediction Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
title	A hybrid method of recurrent neural network and graph neural network for next-period prescription prediction
Creator	Li, Tao Zhou, Yi Yan, Jun Wang, Xiaolong Chen, · Ding, Haoyang Liu, Sicen Tang, ·
source	PMC
abstract	Electronic health records (EHRs) have been widely used to help physicians to make decisions by predicting medical events such as diseases, prescriptions, outcomes, and so on. How to represent patient longitudinal medical data is the key to making these predictions. Recurrent neural network (RNN) is a popular model for patient longitudinal medical data representation from the view of patient status sequences, but it cannot represent complex interactions among different types of medical information, i.e., temporal medical event graphs, which can be represented by graph neural network (GNN). In this paper, we propose a hybrid method of RNN and GNN, called RGNN, for next-period prescription prediction from two views, where RNN is used to represent patient status sequences, and GNN is used to represent temporal medical event graphs. Experiments conducted on the public MIMIC-III ICU data show that the proposed method is effective for next-period prescription prediction, and RNN and GNN are mutually complementary.
has issue date	2020-06-23(xsd:dateTime)
bibo:doi	10.1007/s13042-020-01155-x
has license	no-cc
sha1sum (hex)	391638967b25a2dd621d92c03a46c2a279dc32a7
schema:url	https://doi.org/10.1007/s13042-020-01155-x
resource representing a document's title	A hybrid method of recurrent neural network and graph neural network for next-period prescription prediction
has PubMed Central identifier	PMC7308113
schema:publication	Int
resource representing a document's body	covid:391638967b25a2dd621d92c03a46c2a279dc32a7#body_text
is schema:about of	named entity 'patient' named entity 'complex' named entity 'temporal' named entity 'network' named entity 'data' named entity 'RNN' named entity 'sequences' named entity 'hybrid' named entity 'data' named entity 'RNN' named entity 'make decisions' named entity 'medical information' named entity 'EHRs' named entity 'RNN' named entity 'graph' named entity 'graph' named entity 'predicting' named entity 'Association Rule' named entity 'logistic regression' named entity 'medical information' named entity 'DDI' named entity 'research topic' named entity 'Sigmod' named entity 'RNN' named entity 'medical information' named entity 'classification problem' named entity 'LSTM' named entity 'LSTM' named entity 'medical history' named entity 'LSTM' named entity 'Sigmod' named entity 'medical information' named entity 'knowledge graph' named entity 'deep learning' named entity 'RNN' named entity 'Convolution Neural Networks' named entity 'identity matrix' named entity 'EHR' named entity 'LSTM' named entity 'medical information' named entity 'non-linear' named entity 'vector' named entity 'element-wise multiplication' named entity 'deep learning' named entity 'LSTM' named entity 'RNN' named entity 'standard deviation' named entity 'decision tree' named entity 'vectors' named entity 'matrices' named entity 'medical information' named entity 'ontology' named entity 'time intervals' named entity 'medical information' named entity 'matrices' named entity 'inter-correlations' named entity 'RNN' named entity 'medical history' named entity 'drug repurposing' named entity 'LSTM' named entity 'RNN' named entity 'Decagon' named entity 'Cox proportional hazards model' named entity 'one-hot' named entity 'electronic health records' named entity 'LSTM' named entity 'Massachusetts Institute of technology' named entity 'vector' named entity 'natural language processing' named entity 'breast cancer' named entity 'ReLU' named entity 'LSTM' named entity 'upper gastrointestinal bleeding' named entity 'ARIMA' named entity 'LSTM' named entity 'EHRs'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2025 OpenLink Software