多源数据预测重庆市肝炎发病趋势的时滞输入神经网络研究

姚田华; 陈锡程; 伍亚舟

doi:10.16016/j.2097-0927.202309137

您当前的位置：

首页 >

文章列表页 >

多源数据预测重庆市肝炎发病趋势的时滞输入神经网络研究

公共卫生与预防医学 | 更新时间：2026-01-09

- 多源数据预测重庆市肝炎发病趋势的时滞输入神经网络研究
- Prediction for hepatitis trends in Chongqing based on multisource data: a study of delayed input neural network
- 陆军军医大学学报 2024年46卷第12期页码：1447-1456
- 作者机构：
  
  400038 重庆，陆军军医大学(第三军医大学)军事预防医学系军队卫生统计学教研室
- 作者简介：
  
  [ 伍亚舟，E-mail: asiawu@tmmu.edu.cn WU Yazhou, E-mail: asiawu@tmmu.edu.cn
- 基金信息：
  
  国家自然科学基金项目(82173621);国家自然科学基金项目(81872716);青年科学基金项目(82304249)
- DOI：10.16016/j.2097-0927.202309137
  中图分类号： R195.1;R512.6
- 收稿：2023-09-24，
  
  修回：2023-11-30，
  
  纸质出版：2024-06-30
- 稿件说明：
移动端阅览
姚田华, 陈锡程, 伍亚舟. 多源数据预测重庆市肝炎发病趋势的时滞输入神经网络研究[J]. 陆军军医大学学报, 2024,46(12):1447-1456.

Tianhua YAO, Xicheng CHEN, Yazhou WU. Prediction for hepatitis trends in Chongqing based on multisource data: a study of delayed input neural network[J]. Journal of Army Medical University, 2024, 46(12): 1447-1456.
姚田华, 陈锡程, 伍亚舟. 多源数据预测重庆市肝炎发病趋势的时滞输入神经网络研究[J]. 陆军军医大学学报, 2024,46(12):1447-1456. DOI： 10.16016/j.2097-0927.202309137.

Tianhua YAO, Xicheng CHEN, Yazhou WU. Prediction for hepatitis trends in Chongqing based on multisource data: a study of delayed input neural network[J]. Journal of Army Medical University, 2024, 46(12): 1447-1456. DOI： 10.16016/j.2097-0927.202309137.

摘要

目的

利用多源互联网数据构建时序分析融合工具，继而精准预测重庆市肝炎的发病趋势。

方法

利用卫生疾控中心数据库获取肝炎发病率数据，大气污染物数据来源于中国环境监测总站官网，气候数据来源于国家气象星系中心，网络指数数据来源于百度搜索引擎，时间范围均为2013年11月至2023年5月。基于现有的时序分析方法，利用多源数据对分解模型的残差部分进行校正。基于非自回归(non-autoregressive，NAR)和长短期记忆递归神经网络(long short term memory，LSTM)的各自优势，构建了时滞输入神经网络(delayed input neural network，DINN)。之后，还在其基础上加入了星雀优化算法(nutcracker optimizer algorithm，NOA)和联合四分位-Huber损失函数(joint quantile Huber loss，JQHL)等优化模块，继而构建了DINN+。

结果

相较于常见的单输入模型及同步多输入模型，DINN可取得最为优异的预测效果。在加入超参数和损失函数优化后，DINN+的预测性能进一步提升，其测试集MSE为0.1709、MAE为0.4612、RMSE为0.5821、MAPE为0.0626、R

为0.8840。

结论

基于多样方法和多元数据融合的思想，在既往的时序分析方法基础上，本文提出了一个准确性和泛化能力良好的DINN+优化模型。该模型丰富和补充了利用多源数据校准传染病时序预测分析的方法学研究内容，可作为未来传染病公共卫生层面影响因素分析及趋势预测的全新基准。

Abstract

Objective

To construct a time series analysis fusion tool using multisource internet data and then accurately predict the incidence trend of hepatitis in Chongqing.

Methods

The incidence rate of hepatitis were obtained from the database of the Centre for Health and Disease Control. Air pollutant data were obtained from the official website of the China Environmental Monitoring Station

climate data were obtained from the National Meteorological Galaxy Center

and network index data were obtained through Baidu search engine. The time duration was from November 2013 to May 2023. Based on existing time series analysis methods

multisource data were used to correct the residual part of the decomposition model. A delayed input neural network (DINN) was constructed based on the respective advantages of non autoregressive (NAR) and long short-term memory (LSTM) recurrent neural networks. Afterwards

optimization modules such as the Nutcracker Optimization Algorithm (NOA) and Joint Quantile Huber Loss (JQHL) were added to the foundation

and then DINN+ was constructed.

Results

Compared to common single-input models and synchronous multi-input models

DINN achieved the best prediction performance. After adding hyperparameters and loss function optimization

the predictive performance of DINN+ was further improved

with a mean-square error (MSE) of 0.17

0 9

a mean absolute error (MAE) of 0.461 2

a root-mean-square error (RMSE) of 0.582 1

a mean absolute percentage error (MAPE) of 0.062 6

and a R-square (R

) of 0.884 0 in a testing set.

Conclusion

Based on the ideas of diverse methods and multidimensional data fusion

we propose a DINN+ optimization model with good accuracy and generalization ability on the basis of previous time series analysis. This model enriches and supplements the methodological research content of using multisource data to calibrate infectious disease time series prediction analysis and can serve as a new benchmark for future analysis of influencing factors and trend prediction of infectious disease public health.

关键词

Keywords

references

YI D, CHEN X, WANG H, et al . COVID-19 epidemic and public health interventions in Shanghai, China: Statistical analysis of transmission, correlation and conversion[J ] . Front Public Health, 2023, 10: 1076248. DOI: 10.3389/fpubh.2022.1076248.

XU B, LI J, WANG M. Epidemiological and time series analysis on the incidence and death of AIDS and HIV in China[J]. BMC Public Health, 2020, 20(1): 1906. DOI: 10.1186/s12889-020-09977-8.

MAHMOUDI M R, BAROUMAND S. Modeling the stochastic mechanism of sensor using a hybrid method based on seasonal autoregressive integrated moving average time series and generalized estimating equations[J]. ISA trans, 2022, 125: 300-305. DOI: 10.1016/j.isatra.2021.07.013.

EIKENBERRY S E, MARMARELIS V Z. A nonlinear autoregressive Volterra model of the Hodgkin-Huxley equations[J]. J Comput Neurosci, 2013, 34(1): 163-183. DOI: 10.1007/s10827-012-0412-x.

LIU X, LIU C, HUANG R, et al . Long short-term memory recurrent neural network for pharmacokinetic-pharmacodynamic modeling[J ] . Int J Clin Pharmacol Ther, 2021, 59(02): 138-146. DOI: 10.5414/CP203800.

DI NUNNO F, RACE M, GRANATA F. A nonlinear autoregressive exogenous (NARX) model to predict nitrate concentration in rivers[J]. Environ Sci Pollut Res Int, 2022, 29(27): 40623-40642. DOI: 10.1007/s11356-021-18221-8.

WANG Y, XU C, WANG Z, et al . Time series modeling of pertussis incidence in China from 2004 to 2018 with a novel wavelet based SARIMA-NAR hybrid model[J ] . PLoS One, 2018, 13(12): e0208404. DOI: 10.1371/journal.pone.0208404.

IMAI C, ARMSTRONG B, CHALABI Z, et al . Time series regression model for infectious disease and weather[J ] . Environ Res, 2015, 142: 319-327. DOI: 10.1016/j.envres.2015.06.040.

MESSACAR K, PARKER S K, TODD J K, et al . Implementation of rapid molecular infectious disease diagnostics: the role of diagnostic and antimicrobial stewardship[J ] . J Clin Microbiol, 2017, 55(3): 715-723. DOI: 10.1128/JCM.02264-16.

REICH N G, LAUER S A, SAKREJDA K, et al . Challenges in real-time prediction of infectious disease: A case study of dengue in Thailand[J ] . PLoS Negl Trop Dis, 2016, 10(6): e0004761. DOI: 10.1371/journal.pntd.0004761.

YADAV S K, AKHTER Y. Statistical modeling for the prediction of infectious disease dissemination with special reference to COVID-19 Spread[J]. Front Public Health, 2021, 9: 645405. DOI: 10.3389/fpubh.2021.645405.

ROMERO-ALVAREZ D, PARIKH N, OSTHUS D, et al . Google health trends performance reflecting dengue incidence for the Brazilian states[J ] . BMC Infect Dis, 2020, 20(1): 252. DOI: 10.1186/s12879-020-04957-0.

GAO C, ZHANG R, CHEN X, et al . Integrating Internet multisource big data to predict the occurrence and development of COVID-19 cryptic transmission[J ] . NPJ Digit Med, 2022, 5(1): 161. DOI: 10.1038/s41746-022-00704-8.

ZHANG R, GAO C, CHEN X, et al . Genetic algorithm optimised Hadamard product method for inconsistency judgement matrix adjustment in AHP and automatic analysis system development[J ] . Expert Syst Appl, 2023, 211: 118689. DOI: 10.1016/j.eswa.2022.118689.

MARTÍNEZ-ÁLVAREZ F, ASENCIO-CORTÉS G, TORRES J F, et al . Coronavirus optimization algorithm: A bioinspired metaheuristic based on the COVID-19 propagation model[J ] . Big Data, 2020, 8(4): 308-322. DOI: 10.1089/big.2020.0051.

ABDEL-BASSET M, MOHAMED R, JAMEEL M, et al . Nutcracker optimizer: A novel nature-inspired metaheuristic algorithm for global optimization and engineering design problems[J ] . Knowl Based Syst, 2023, 262: 110248. DOI: 10.1016/j.knosys.2022.110248.

SPELLER J, STAERK C, MAYR A. Robust statistical boosting with quantile-based adaptive loss functions[J]. The Int J Biost, 2023, 19(1): 111-129. DOI: 10.1515/ijb-2021-0127.

SUMI A, LUO T, ZHOU D, et al . Time-series analysis of hepatitis A, B, C and E infections in a large Chinese city: application to prediction analysis[J ] . Epidemiol Infect, 2013, 141(5): 905-915. DOI: 10.1017/S095026881200146X.

SLOAN C, CHANDRASEKHAR R, MITCHEL E, et al . Socioeconomic disparities and influenza hospitalizations, Tennessee, USA[J ] . Emerg Infec Dis, 2015, 21(9): 1602-1610. DOI: 10.3201/eid2109.141861.

LUBBA C H, SETHI S S, KNAUTE P, et al . catch22: CAnonical Time-series CHaracteristics: Selected through highly comparative time-series analysis[J ] . Data Min Knowledge Discovery, 2019, 33(6): 1821-1852. DOI: 10.1007/s10618-019-00647-x.

WU L, ZHOU B, LIU D, et al . LASSO regression-based diagnosis of acute ST-segment elevation myocardial infarction (STEMI) on electrocardiogram (ECG)[J ] . J Clin Med, 2022, 11(18): 5408. DOI: 10.3390/jcm11185408.

HAZARIKA B B, GUPTA D. Random vector functional link with ε-insensitive Huber loss function for biomedical data classification[J]. Comput Methods Programs Biomed, 2022, 215: 106622. DOI: 10.1016/j.cmpb.2022.106622.

LOPEZ-MARTIN M, SANCHEZ-ESGUEVILLAS A, HERNANDEZ-CALLEJO L, et al . Additive ensemble neural network with constrained weighted quantile loss for probabilistic electric-load forecasting[J ] . Sensors, 2021, 21(9): 2979. DOI: 10.3390/s21092979.

YE W, CHEN X, LI P, et al . OEDL: an optimized ensemble deep learning method for the prediction of acute ischemic stroke prognoses using union features[J ] . Front Neurol, 2023, 14: 1158555. DOI: 10.3389/fneur.2023.1158555.

WANG K W, DENG C, LI J P, et al . Hybrid methodology for tuberc ulosis incidence time-series forecasting based on ARIMA and a NAR neural network[J ] . Epidemiol Infect, 2017, 145(6): 1118-1129. DOI: 10.1017/S0950268816003216.

LISMAN J. Glutamatergic synapses are structurally and biochemically complex because of multiple plasticity processes: long-term potentiation, long-term depression, short-term potentiation and scaling[J]. Philos Trans R Soc Lond B Biol Sci, 2017, 372(1715): 20160260. DOI: 10.1098/rstb.2016.0260.

BAI Y, ZENG B, LI C, et al . An ensemble long short-term memory neural network for hourly PM2.5 concentration forecasting[J ] . Chemosphere, 2019, 222: 286-294. DOI: 10.1016/j.chemosphere.2019.01.121.

ABDEL-BASSET M, MOHAMED R, AZEEM S A A, et al . Kepler optimization algorithm: A new metaheuristic algorithm inspired by Kepler's laws of planetary motion[J ] . Knowl Based Syst, 2023, 268: 110454. DOI: 10.1016/j.knosys.2023.110454.

ABDEL-BASSET M, MOHAMED R, JAMEEL M, et al . Spider wasp optimizer: a novel meta-heuristic optimization algorithm[J ] . Artif Intell Rev, 2023, 56(10): 11675-11738. DOI: 10.1007/s10462-023-10446-y.

KIRBAŞ I, SOZEN A, TUNCER A D, et al . Comparative analysis and forecasting of COVID-19 cases in various European countri es with ARIMA, NARNNand LSTM approaches[J ] . Chaos Solitons Fractals, 2020, 138: 110015. DOI: 10.1016/j.chaos.2020.110015.

CARREON-ORTIZ H, VALDEZ F, MELIN P, et al . Architecture optimization of a non-linear autoregressive neural networks for Mackey-glass time series prediction using discrete mycorrhiza optimization algorithm[J ] . Micromachines, 2023, 14(1): 149. DOI: 10.3390/mi14010149.

YU L, ZHOU L, TAN L, et al . Application of a new hybrid model with seasonal auto-regressive integrated moving average (ARIMA) and nonlinear auto-regressive neural network (NARNN) in forecasting incidence cases of HFMD in Shenzhen, China[J ] . PloS One, 2014, 9(6): e98241. DOI: 10.1371/journal.pone.0098241.

MIAO R, ZHANG B. Analysis on time-series data from movie using MF-DCCA method and recurrent neural network model under the internet of things[J]. Comput Intell Neurosci, 2022, 2022: 7400833. DOI: 10.1155/2022/7400833.

HATAMI N, CHO T H, MECHTOUFF L, et al . CNN-LSTM Based multimodal MRI and clinical data fusion for predicting functional outcome in stroke patients[C/OL ] //2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Glasgow: IEEE, 2022: 3430-3434[2022-10-05 ] . https://ieeexplore.ieee.org/document/9871735/. DOI: 10.1109/EMBC48229.2022.9871735.

CHEN S, ZOU Y, LIU P X. IBA-U-Net: Attentive BConvLSTM U-Net with Redesigned Inception for medical image segmentation[J]. Comput Biol Med, 2021, 135: 104551. DOI: 10.1016/j.compbiomed.2021.104551.

Global Burden of Disease 2021 Health Financing Collaborator Network. Global investments in pandemic preparedness and COVID-19: development assistance and domestic spending on health between 1990 and 2026[J]. Lancet Glob Health, 2023, 11(3): e385-e413. DOI: 10.1016/S2214-109X(23)00007-4.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据