Foodborne Disease Risk Prediction Using Multigraph Structural Long Short-term Memory Networks: Algorithm Design and Validation Study

BackgroundFoodborne disease is a common threat to human health worldwide, leading to millions of deaths every year. Thus, the accurate prediction foodborne disease risk is very urgent and of great importance for public health management. ObjectiveWe aimed to desig...

Full description

Bibliographic Details
Main Authors: Yi Du, Hanxue Wang, Wenjuan Cui, Hengshu Zhu, Yunchang Guo, Fayaz Ali Dharejo, Yuanchun Zhou
Format: Article
Language:English
Published: JMIR Publications 2021-08-01
Series:JMIR Medical Informatics
Online Access:https://medinform.jmir.org/2021/8/e29433
_version_ 1797735666075828224
author Yi Du
Hanxue Wang
Wenjuan Cui
Hengshu Zhu
Yunchang Guo
Fayaz Ali Dharejo
Yuanchun Zhou
author_facet Yi Du
Hanxue Wang
Wenjuan Cui
Hengshu Zhu
Yunchang Guo
Fayaz Ali Dharejo
Yuanchun Zhou
author_sort Yi Du
collection DOAJ
description BackgroundFoodborne disease is a common threat to human health worldwide, leading to millions of deaths every year. Thus, the accurate prediction foodborne disease risk is very urgent and of great importance for public health management. ObjectiveWe aimed to design a spatial–temporal risk prediction model suitable for predicting foodborne disease risks in various regions, to provide guidance for the prevention and control of foodborne diseases. MethodsWe designed a novel end-to-end framework to predict foodborne disease risk by using a multigraph structural long short-term memory neural network, which can utilize an encoder–decoder to achieve multistep prediction. In particular, to capture multiple spatial correlations, we divided regions by administrative area and constructed adjacent graphs with metrics that included region proximity, historical data similarity, regional function similarity, and exposure food similarity. We also integrated an attention mechanism in both spatial and temporal dimensions, as well as external factors, to refine prediction accuracy. We validated our model with a long-term real-world foodborne disease data set, comprising data from 2015 to 2019 from multiple provinces in China. ResultsOur model can achieve F1 scores of 0.822, 0.679, 0.709, and 0.720 for single-month forecasts for the provinces of Beijing, Zhejiang, Shanxi and Hebei, respectively, and the highest F1 score was 20% higher than the best results of the other models. The experimental results clearly demonstrated that our approach can outperform other state-of-the-art models, with a margin. ConclusionsThe spatial–temporal risk prediction model can take into account the spatial–temporal characteristics of foodborne disease data and accurately determine future disease spatial–temporal risks, thereby providing support for the prevention and risk assessment of foodborne disease.
first_indexed 2024-03-12T13:02:18Z
format Article
id doaj.art-5853cad85649476ca0ca741a9f52a819
institution Directory Open Access Journal
issn 2291-9694
language English
last_indexed 2024-03-12T13:02:18Z
publishDate 2021-08-01
publisher JMIR Publications
record_format Article
series JMIR Medical Informatics
spelling doaj.art-5853cad85649476ca0ca741a9f52a8192023-08-28T19:25:53ZengJMIR PublicationsJMIR Medical Informatics2291-96942021-08-0198e2943310.2196/29433Foodborne Disease Risk Prediction Using Multigraph Structural Long Short-term Memory Networks: Algorithm Design and Validation StudyYi Duhttps://orcid.org/0000-0003-3121-8937Hanxue Wanghttps://orcid.org/0000-0001-5067-7851Wenjuan Cuihttps://orcid.org/0000-0002-1858-8194Hengshu Zhuhttps://orcid.org/0000-0003-4570-643XYunchang Guohttps://orcid.org/0000-0001-5519-2570Fayaz Ali Dharejohttps://orcid.org/0000-0001-7685-3913Yuanchun Zhouhttps://orcid.org/0000-0003-2144-1131 BackgroundFoodborne disease is a common threat to human health worldwide, leading to millions of deaths every year. Thus, the accurate prediction foodborne disease risk is very urgent and of great importance for public health management. ObjectiveWe aimed to design a spatial–temporal risk prediction model suitable for predicting foodborne disease risks in various regions, to provide guidance for the prevention and control of foodborne diseases. MethodsWe designed a novel end-to-end framework to predict foodborne disease risk by using a multigraph structural long short-term memory neural network, which can utilize an encoder–decoder to achieve multistep prediction. In particular, to capture multiple spatial correlations, we divided regions by administrative area and constructed adjacent graphs with metrics that included region proximity, historical data similarity, regional function similarity, and exposure food similarity. We also integrated an attention mechanism in both spatial and temporal dimensions, as well as external factors, to refine prediction accuracy. We validated our model with a long-term real-world foodborne disease data set, comprising data from 2015 to 2019 from multiple provinces in China. ResultsOur model can achieve F1 scores of 0.822, 0.679, 0.709, and 0.720 for single-month forecasts for the provinces of Beijing, Zhejiang, Shanxi and Hebei, respectively, and the highest F1 score was 20% higher than the best results of the other models. The experimental results clearly demonstrated that our approach can outperform other state-of-the-art models, with a margin. ConclusionsThe spatial–temporal risk prediction model can take into account the spatial–temporal characteristics of foodborne disease data and accurately determine future disease spatial–temporal risks, thereby providing support for the prevention and risk assessment of foodborne disease.https://medinform.jmir.org/2021/8/e29433
spellingShingle Yi Du
Hanxue Wang
Wenjuan Cui
Hengshu Zhu
Yunchang Guo
Fayaz Ali Dharejo
Yuanchun Zhou
Foodborne Disease Risk Prediction Using Multigraph Structural Long Short-term Memory Networks: Algorithm Design and Validation Study
JMIR Medical Informatics
title Foodborne Disease Risk Prediction Using Multigraph Structural Long Short-term Memory Networks: Algorithm Design and Validation Study
title_full Foodborne Disease Risk Prediction Using Multigraph Structural Long Short-term Memory Networks: Algorithm Design and Validation Study
title_fullStr Foodborne Disease Risk Prediction Using Multigraph Structural Long Short-term Memory Networks: Algorithm Design and Validation Study
title_full_unstemmed Foodborne Disease Risk Prediction Using Multigraph Structural Long Short-term Memory Networks: Algorithm Design and Validation Study
title_short Foodborne Disease Risk Prediction Using Multigraph Structural Long Short-term Memory Networks: Algorithm Design and Validation Study
title_sort foodborne disease risk prediction using multigraph structural long short term memory networks algorithm design and validation study
url https://medinform.jmir.org/2021/8/e29433
work_keys_str_mv AT yidu foodbornediseaseriskpredictionusingmultigraphstructurallongshorttermmemorynetworksalgorithmdesignandvalidationstudy
AT hanxuewang foodbornediseaseriskpredictionusingmultigraphstructurallongshorttermmemorynetworksalgorithmdesignandvalidationstudy
AT wenjuancui foodbornediseaseriskpredictionusingmultigraphstructurallongshorttermmemorynetworksalgorithmdesignandvalidationstudy
AT hengshuzhu foodbornediseaseriskpredictionusingmultigraphstructurallongshorttermmemorynetworksalgorithmdesignandvalidationstudy
AT yunchangguo foodbornediseaseriskpredictionusingmultigraphstructurallongshorttermmemorynetworksalgorithmdesignandvalidationstudy
AT fayazalidharejo foodbornediseaseriskpredictionusingmultigraphstructurallongshorttermmemorynetworksalgorithmdesignandvalidationstudy
AT yuanchunzhou foodbornediseaseriskpredictionusingmultigraphstructurallongshorttermmemorynetworksalgorithmdesignandvalidationstudy