Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (1): 265-269.DOI: 10.11772/j.issn.1001-9081.2020060936

Special Issue: 第八届中国数据挖掘会议(CCDM 2020)

• China Conference on Data Mining 2020 (CCDM 2020) • Previous Articles     Next Articles

Incidence trend prediction of hand-foot-mouth disease based on long short-term memory neural network

MA Tingting1, JI Tianjiao2, YANG Guanyu1, CHEN Yang1, XU Wenbo2, LIU Hongtu2   

  1. 1. School of Computer Science and Engineering, Southeast University, Nanjing Jiangsu 210096, China;
    2. Key Laboratory of Medical Virology Ministry of Health, National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China
  • Received:2020-05-31 Revised:2020-07-31 Online:2021-01-10 Published:2020-09-02
  • Supported by:
    This work is partially supported by the National Science and Technology Major Project (2018ZX10201-002-003).

基于长短时记忆神经网络的手足口病发病趋势预测

马停停1, 冀天娇2, 杨冠羽1, 陈阳1, 许文波2, 刘宏图2   

  1. 1. 东南大学 计算机科学与工程学院, 南京 210096;
    2. 中国疾病预防控制中心病毒病预防控制所 卫生部医学病毒学和病毒病重点实验室, 北京 102206
  • 通讯作者: 杨冠羽
  • 作者简介:马停停(1994-),女,安徽阜阳人,硕士,主要研究方向:时间序列分析、传染病预测;冀天娇(1986-),女,河北邯郸人,助理研究员,硕士,主要研究方向:肠道病毒的分子流行病学;杨冠羽(1980-),男,江苏南京人,副教授,博士,主要研究方向:深度学习、医疗人工智能;陈阳(1979-),男,江苏南京人,教授,博士,主要研究方向:医学信号图像处理与分析、计算机视觉;许文波(1963-),男,吉林舒兰人,研究员,博士,主要研究方向:肠道病毒和呼吸道病毒的诊断和分子流行病学;刘宏图(1968-),男,北京人,研究员,博士,主要研究方向:肿瘤病毒、肿瘤免疫。
  • 基金资助:
    国家科技重大专项(2018ZX10201-002-003)。

Abstract: In order to solve the problems of the traditional Hand-Foot-Mouth Disease (HFMD) incidence trend prediction algorithm, such as low prediction accuracy, lack of the combination of other influencing factors and short prediction time, a method of long-term prediction using meteorological factors and Long Short-Term Memory (LSTM) network was proposed. First, the sliding window was used to convert the incidence sequence into the input and output of the network. Then, the LSTM network was used for data modeling and prediction, and the iterative prediction was used to obtain the long-term prediction results. Finally, the temperature and humidity variables were added to the network to compare the impact of these variables on the prediction results. Experimental results show that adding meteorological factors can improve the prediction accuracy of the model. The proposed model has the Mean Absolute Error (MAE) on the Jinan dataset of 74.9, and the MAE on the Guangzhou dataset of 427.7. Compared with the commonly used Seasonal Autoregressive Integrated Moving Average (SARIMA) model and Support Vector Regression (SVR) model, the proposed model has the prediction accuracy higher, which proves that the model is an effective experimental method for the prediction of the incidence trend of HFMD.

Key words: Hand-Foot-Mouth Disease (HFMD), time series, correlation analysis, Long Short-Term Memory (LSTM) network, infectious disease prediction

摘要: 针对传统手足口病(HFMD)发病趋势预测算法预测精度不高、未结合其他影响因素、预测时间较短等问题,提出结合气象因素使用长短时记忆(LSTM)网络进行长期预测的方法。首先,将发病序列通过滑动窗口的方式转化为网络的输入和输出;然后采用LSTM网络进行数据建模和预测,并使用迭代预测的方式获得较长期的预测结果;最后在网络中增加温度和湿度变量,比较这些变量对预测结果的影响。实验结果表明,加入气象因素能够提高模型的预测精度,所提模型在济南市数据集上的平均绝对误差(MAE)为74.9,在广州市数据集上的MAE为427.7,相较于常用的季节性差分自回归移动平均(SARIMA)模型和支持向量回归(SVR)模型,该模型的预测准确率更高。可见所提模型是HFMD发病趋势预测的一种有效的实验方法。

关键词: 手足口病, 时间序列, 相关分析, 长短时记忆网络, 传染病预测

CLC Number: