A Hybrid Prediction Model Based on Decomposition-Integration for Foodborne Disease Risks.

IF 1.9 2区 农林科学 Q3 FOOD SCIENCE & TECHNOLOGY
Ke Qin, Jingxiang Zhang, Xiaoting Dai, Linhai Wu, Minguo Gao
{"title":"A Hybrid Prediction Model Based on Decomposition-Integration for Foodborne Disease Risks.","authors":"Ke Qin, Jingxiang Zhang, Xiaoting Dai, Linhai Wu, Minguo Gao","doi":"10.1089/fpd.2024.0189","DOIUrl":null,"url":null,"abstract":"<p><p>Foodborne diseases (FBDs) are contagious, explosive, clustered diseases caused by the ingestion of contaminated foods, which represent huge economic and health burdens globally. Reliably predicting the risk trend of FBDs has become a major challenge in the field of public health. This study aimed to design a risk prediction model suitable for predicting FBD risks by using the decomposition-integration technique. A total of 28,646 FBD cases from FBD surveillance data reported by all sentinel hospitals in Wuxi from 2019 to 2023 were included in the study. The obtained FBD risk data were decomposed into multiple intrinsic mode functions (IMFs) using complete ensemble empirical mode decomposition with adaptive noise, which were then reconstructed by calculating the sample entropy. Finally, the time dependence of the reconstructed IMFs was explored using a temporal convolution network-long short-term memory (TCN-LSTM) model to obtain the prediction results of each component, which were then linearly added to obtain the final prediction results. Compared with other models, our proposed prediction model significantly improved the prediction accuracy of FBD risks, with a best average root mean square error of 5.349 and mean absolute error of 3.819, demonstrating at least a 40% improvement in accuracy over standalone LSTM. The FBD risk prediction results obtained by the method proposed in this study can provide data support for food safety management and policy making and enable more accurate early warning of FBDs.</p>","PeriodicalId":12333,"journal":{"name":"Foodborne pathogens and disease","volume":" ","pages":""},"PeriodicalIF":1.9000,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Foodborne pathogens and disease","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1089/fpd.2024.0189","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"FOOD SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Foodborne diseases (FBDs) are contagious, explosive, clustered diseases caused by the ingestion of contaminated foods, which represent huge economic and health burdens globally. Reliably predicting the risk trend of FBDs has become a major challenge in the field of public health. This study aimed to design a risk prediction model suitable for predicting FBD risks by using the decomposition-integration technique. A total of 28,646 FBD cases from FBD surveillance data reported by all sentinel hospitals in Wuxi from 2019 to 2023 were included in the study. The obtained FBD risk data were decomposed into multiple intrinsic mode functions (IMFs) using complete ensemble empirical mode decomposition with adaptive noise, which were then reconstructed by calculating the sample entropy. Finally, the time dependence of the reconstructed IMFs was explored using a temporal convolution network-long short-term memory (TCN-LSTM) model to obtain the prediction results of each component, which were then linearly added to obtain the final prediction results. Compared with other models, our proposed prediction model significantly improved the prediction accuracy of FBD risks, with a best average root mean square error of 5.349 and mean absolute error of 3.819, demonstrating at least a 40% improvement in accuracy over standalone LSTM. The FBD risk prediction results obtained by the method proposed in this study can provide data support for food safety management and policy making and enable more accurate early warning of FBDs.

基于分解-积分的食源性疾病风险混合预测模型
食源性疾病是由摄入受污染食品引起的传染性、爆炸性、聚集性疾病,在全球范围内造成巨大的经济和健康负担。可靠地预测非传染性疾病的风险趋势已成为公共卫生领域的一项重大挑战。本研究旨在利用分解-积分技术设计一个适合于FBD风险预测的风险预测模型。从2019 - 2023年无锡市所有哨点医院报告的FBD监测数据中,共纳入28646例FBD病例。采用带自适应噪声的全系综经验模态分解方法,将得到的FBD风险数据分解为多个本征模态函数(IMFs),通过计算样本熵对其进行重构。最后,利用时序卷积网络-长短期记忆(TCN-LSTM)模型探讨重构后的IMFs的时间依赖性,得到各分量的预测结果,然后对各分量进行线性相加,得到最终的预测结果。与其他模型相比,我们提出的预测模型显著提高了FBD风险的预测精度,最佳平均均方根误差为5.349,平均绝对误差为3.819,与独立LSTM相比,准确率至少提高了40%。本研究方法获得的FBD风险预测结果可为食品安全管理和政策制定提供数据支持,实现FBD更准确的预警。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Foodborne pathogens and disease
Foodborne pathogens and disease 医学-食品科技
CiteScore
5.30
自引率
3.60%
发文量
80
审稿时长
1 months
期刊介绍: Foodborne Pathogens and Disease is one of the most inclusive scientific publications on the many disciplines that contribute to food safety. Spanning an array of issues from "farm-to-fork," the Journal bridges the gap between science and policy to reduce the burden of foodborne illness worldwide. Foodborne Pathogens and Disease coverage includes: Agroterrorism Safety of organically grown and genetically modified foods Emerging pathogens Emergence of drug resistance Methods and technology for rapid and accurate detection Strategies to destroy or control foodborne pathogens Novel strategies for the prevention and control of plant and animal diseases that impact food safety Biosecurity issues and the implications of new regulatory guidelines Impact of changing lifestyles and consumer demands on food safety.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信