About: STAN: Spatio-Temporal Attention Network for Pandemic Prediction Using Real World Evidence

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

About: STAN: Spatio-Temporal Attention Network for Pandemic Prediction Using Real World Evidence 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
has title	STAN: Spatio-Temporal Attention Network for Pandemic Prediction Using Real World Evidence
Creator	Qian, Cheng Glass, Lucas Romberg, Justin Sun, Jimeng Xiao, Cao Gao, Junyi Sharma, Rakshith Spaeder, Jeffrey
Source	ArXiv
abstract	Objective: The COVID-19 pandemic has created many challenges that need immediate attention. Various epidemiological and deep learning models have been developed to predict the COVID-19 outbreak, but all have limitations that affect the accuracy and robustness of the predictions. Our method aims at addressing these limitations and making earlier and more accurate pandemic outbreak predictions by (1) using patients' EHR data from different counties and states that encode local disease status and medical resource utilization condition; (2) considering demographic similarity and geographical proximity between locations; and (3) integrating pandemic transmission dynamics into deep learning models. Materials and Methods: We proposed a spatio-temporal attention network (STAN) for pandemic prediction. It uses an attention-based graph convolutional network to capture geographical and temporal trends and predict the number of cases for a fixed number of days into the future. We also designed a physical law-based loss term for enhancing long-term prediction. STAN was tested using both massive real-world patient data and open source COVID-19 statistics provided by Johns Hopkins university across all U.S. counties. Results: STAN outperforms epidemiological modeling methods such as SIR and SEIR and deep learning models on both long-term and short-term predictions, achieving up to 87% lower mean squared error compared to the best baseline prediction model. Conclusions: By using information from real-world patient data and geographical data, STAN can better capture the disease status and medical resource utilization information and thus provides more accurate pandemic modeling. With pandemic transmission law based regularization, STAN also achieves good long-term prediction performance.
has issue date	2020-07-23(xsd:dateTime)
has license	arxiv
sha1sum (hex)	a7db59411ec407b5dbd4d2b69ccd432c2d0a1b64
resource representing a document's title	STAN: Spatio-Temporal Attention Network for Pandemic Prediction Using Real World Evidence
resource representing a document's body	covid:a7db59411ec407b5dbd4d2b69ccd432c2d0a1b64#body_text
is schema:about of	named entity 'pandemic' named entity 'demographic' named entity 'models' named entity 'created' named entity 'pandemic' named entity 'Network' named entity 'NEED' named entity '282' named entity '283' named entity 'limitations' named entity 'data' named entity 'encode' named entity 'locations' named entity 'making' named entity 'COVID-19' named entity 'EHR' named entity 'SEIR' named entity 'COVID-19 pandemic' named entity 'time series prediction' named entity 'GRU' named entity 'public health' named entity '2, 3' named entity 'COVID-19' named entity 'long-term prediction' named entity 'ICD-10' named entity 'COVID-19' named entity 'LSTM' named entity 'COVID-19' named entity 'SEIR' named entity 'JHU' named entity 'loss function' named entity '1.1' named entity 'correlation coefficient' named entity 'COVID-19' named entity 'physical law' named entity 'Database' named entity 'SEIR' named entity 'SEIR' named entity 'COVID-19' named entity 'MSE' named entity 'long-term prediction' named entity 'Intel Xeon' named entity 'Octa-Core' named entity 'physical law' named entity 'evaluation sets' named entity 'SEIR' named entity '8 days' named entity 'convolutional network' named entity 'GRU' named entity 'graph embedding' named entity 'Temporal Attention' named entity 'simple graph' named entity 'multi-layer perceptron' named entity 'physical law' named entity 'differential equation' named entity 'disease outbreaks' named entity 'disease transmission' named entity 'GRU' named entity 'long-term prediction' named entity 'adjacency matrix' named entity 'diagnosis and procedure codes' named entity 'SEIR' named entity 'sliding window' named entity 'neural network' named entity 'May 17' named entity 'IQVIA' named entity 'DNN' named entity 'COVID-19' named entity 'convolutional network' named entity 'attributed graph' named entity '2, 3' named entity 'LSTM' named entity 'graph embedding' named entity 'Epidemiological models' named entity 'MAE' named entity 'disease transmission' named entity 'SEIR' named entity 'Long Short Term Memory' named entity 'overfitting' named entity 'loss function'

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 © 2009-2024 OpenLink Software