基于机器学习整合气象、互联网和监测数据的流感预测模型构建与评价-现代医学

基于机器学习整合气象、互联网和监测数据的流感预测模型构建与评价

单位：1. 苏州市卫生健康信息中心信息统计科, 江苏苏州 215000;
2. 苏州大学公共卫生学院, 江苏苏州 215123;
3. 苏州市疾病预防控制中心急传科, 江苏苏州 215100

分类号：R183.3

出版年·卷·期（页码）：2024·52·第十一期（1695-1702）

摘要：

目的: 探索气象因素、互联网数据在苏州市流感例预测方面的作用，并基于机器学习方法构建苏州市流感预测模型。方法: 收集苏州市2012年1月1日至2019年12月29日气象资料、流感监测资料以及互联网流感关键词搜索资料，采用交叉相关分析方法检验初筛气象因素、流感关键词与流感病例在前、后4周时间范围内的时滞相互关系。根据时滞相关性分析，对关键词进一步过滤，基于确定的不同类型关键词、流感样病例百分比数据以及流感病原阳性检出率数据，构建流感预测模型，并选用SARIMA、LSTM、Att-LSTM 3种方法进行模型的训练和构建。以均方误差(MSE)、平均绝对误差(MAE)和均方根误差(RMSE)3个指标对各模型进行评价。结果: SARIMA模型的拟合度较低， Att-LSTM模型拟合度较高，其MSE、RMSE、MAE值分别为0.055、0.235、0.184。结论: 基于气象、互联网和监测数据构建的Att-LSTM模型可以有效提高模型预测精度，其结果可为苏州地区实现更加精准的流感防控提供科学依据。

Objective: To Explore the role of meteorological factors and internet data in predicting influenza cases in Suzhou City, and construct influenza prediction models for Suzhou City based on the method of machine learning. Methods: We collected meteorological data, influenza surveillance data, and internet influenza keyword search data in Suzhou from January 1, 2012, to December 29, 2019. Then, we used cross-correlation analysis to test the lagged relationships between the preliminary screened meteorological factors, influenza keywords, and influenza cases within a 4-week time frame. Based on the lagged correlation analysis, researchers further filtered the keywords. Utilizing the determined different types of keywords, influenza-like illness consultation rate and positive rate, we constructed influenza prediction models by using SARIMA, LSTM, and Att-LSTM methods. Finally, we evaluated each model using the Mean Squared Error(MSE), Mean Absolute Error(MAE), and Root Mean Squared Error(RMSE) metrics. Results: The fitting of the SARIMA model was relatively low, whereas the Att-LSTM model showed a high fitting degree, with its MSE, RMSE, and MAE values respectively being 0.055, 0.235 and 0.184. Conclusion: The Att-LSTM model, constructed based on meteorological, internet, and surveillance data, can significantly enhance predictive accuracy. The results will provide a scientific basis for more precise influenza prevention and control efforts in Suzhou.

参考文献：

[1] AZZIZ BAUMGARTNER E,DAO C N,NASREEN S,et al.Seasonality,timing,and climate drivers of influenza activity worldwide[J].J Infect Dis,2012,206(6):838-846.
[2] UYEKI T M,HUI D S,ZAMBON M,et al.Influenza[J].Lancet,2022,400(10353):693-706.
[3] PAULES C,SUBBARAO K.Influenza[J].Lancet,2017,390(10095):697-708.
[4] ZHOU L,YANG H,PAN W,et al.Association between meteorological factors and the epidemics of influenza(sub)types in a subtropical basin of Southwest China[J].Epidemics,2022,41:100650.
[5] LI Z,LIU T,ZHU G,et al.Dengue Baidu search index data can improve the prediction of local dengue epidemic:a case study in Guangzhou,China[J].PLoS Negl Trop Dis,2017,11(3):e0005354.
[6] SYLVESTRE E,JOACHIM C,CÉCILIA-JOSEPH E,et al.Data-driven methods for dengue prediction and surveillance using real-world and big data:a systematic review[J].PLoS Negl Trop Dis,2022,16(1):e0010056.
[7] BEMPONG N E,RUIZ DE CASTAÑEDA R,SCHVTTE S,et al.Precision global health—the case of Ebola:a scoping review[J].J Glob Health,2019,9(1):010404.
[8] BARROS J M,DUGGAN J,REBHOLZ-SCHUHMANN D.The application of internet-based sources for public health surveillance(infoveillance):systematic review[J].J Med Internet Res,2020,22(3):e13680.
[9] LI K,LIU M,FENG Y,et al.Using Baidu search engine to monitor AIDS epidemics inform for targeted intervention of HIV/AIDS in China[J].Sci Rep,2019,9(1):320.
[10] GINSBERG J,MOHEBBI M H,PATEL R S,et al.Detecting influenza epidemics using search engine query data[J].Nature,2009,457(7232):1012-1014.
[11] LU F S,HATTAB M W,CLEMENTE C L,et al.Improved state-level influenza nowcasting in the United States leveraging internet-based data and network approaches[J].Nat Commun,2019,10(1):147.
[12] 薛红新，刘绕星，况立群，等.基于百度指数与机器学习方法的流感样病例预测[J].中国预防医学杂志,2023,24(8):788-794.
[13] 王力.基于气象因素和互联网搜索数据的流感疫情预测研究：以香港为例 [D].汕头:汕头大学,2017.
[14] ZHANG Y,YE C,YU J,et al.The complex associations of climate variability with seasonal influenza A and B virus transmission in subtropical Shanghai,China[J].Sci Total Environ,2020,701:134607.
[15] SERMAN E,THRASTARSON H T,FRANKLIN M,et al.Spatial variation in humidity and the onset of seasonal influenza across the contiguous United States[J].Geo Health,2022,6(2):e2021GH000469.
[16] 魏柯雯，任雅楠，马仲慧，等.2016—2021年北京市房山区流感样病例与病原学监测相关性分析[J].预防医学情报杂志,2023,39(2):7.
[17] 费俊梁，马成，王黎明，等.机器学习法优化髋关节置换术围手术期治疗策略[J].东南大学学报(医学版),2024,43(2):229-236.

服务与反馈：

【文章下载】【发表评论】【查看评论】【加入收藏】

提示：您还未登录，请登录！点此登录