基于环境因素和深度学习,预测中国州常见肠道传染病的发病率
Xianzhi Zheng1,2, Lei Qiao1,3, Hao Hong3
1Changzhou Institute for Advanced Study of Public Health, Key Laboratory of Public Health Safety and Emergency Prevention and Control Technology of Higher Education Institutions in Jiangsu Province, Nanjing Medical University, Changzhou, 213022, China.
BMC public health
|December 20, 2025
概括
一个新的STL-T-L模型通过分析历史数据,天气和空气污染,有效地预测了常州的每日肠道传染病. 这种工具有助于疾病监测和早期预警系统.
科学领域:
- 环境流行病学环境流行病学
- 传染病建模 传染病建模
- 数据科学数据科学数据科学
背景情况:
- 肠道传染病很常见,受到气象条件和空气污染的影响.
- 公共卫生管理需要准确的短期预测模型.
研究的目的:
- 构建和比较用于预测常州每日肠道传染病发病率的模型.
- 评估环境因素对疾病预测的影响.
主要方法:
- 在长州 (2014-2024) 收集手足口病和传染性腹的每日发病率数据.
- 集成的气象数据 (温度,湿度,风速,气压) 和空气污染物的数据 (PM2.5,PM10,SO2,NO2,O3,AQI).
- 开发并比较了长短期内存 (LSTM),变压器和混合STL-变压器模型,提出了一个先进的STL-T-L (使用Loess,变压器和LSTM进行季节性趋势分解) 模型.
- 利用贝叶斯优化进行超参数调整,并使用RMSE,MAE,MAPE和MASE评估模型.
主要成果:
- 在试验组中,STL-T-L混合模型表现出卓越的预测性能.
- 对于STL-T-L的关键绩效指标:RMSE=6.337,MAE=4.524,MAPE=58.482%,MASE=0.638. 在STL-T-L的关键绩效指标中,RMSE=6.337,MAE=4.524,MAPE=58.482%,MASE=0.638. 在STL-T-L的关键绩效指标中,RMSE=6.337,MAE=4.524,MAPE=58.482%,在STL-T-L的关键绩效指标中,MASE=0.638.
- 该模型有效地整合了历史发生率,气象和空气污染数据,以提高预测.
结论:
- STL-T-L模型对于预测常见的肠道传染病是有效的.
- 这个模型可以作为一个有价值的工具,用于监测和早期预警州的肠道传染病.
相关概念视频
01:18Steps in Outbreak Investigation
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
01:24iChip
The cultivation of environmental microorganisms has long been hindered by the inability to replicate complex native conditions in vitro. The isolation chip (iChip) addresses this limitation by facilitating the growth of previously uncultivable microorganisms through in situ incubation. Designed for high-throughput microbial cultivation, the iChip comprises hundreds of microchambers, each capable of housing a single microbial cell. These microchambers are loaded with a mixture of molten agar and...
01:23Investigation of Disease Outbreaks
Multistate foodborne outbreaks pose significant public health risks and require meticulous investigation to identify sources and implement control measures. The Centers for Disease Control and Prevention (CDC) utilizes a dynamic seven-step process for these investigations, integrating data from laboratories, interviews, and environmental assessments to protect public health.Outbreak Detection: The detection of multistate outbreaks typically begins with PulseNet, the CDC's national laboratory...