Yang Liuyang, Yang Jiao, He Yuan, Zhang Mengjiao, Han Xuan, Hu Xuancheng, Li Wei, Zhang Ting, Yang Weizhong
Yunnan Cancer Hospital, The Third Affiliated Hospital of Kunming Medical University , Kunming, Yunnan, China.
School of Population Medicine and Public Health, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
Prev Med Rep. 2024 May 15;43:102761. doi: 10.1016/j.pmedr.2024.102761. eCollection 2024 Jul.
This study aimed to develop a universally applicable, feedback-informed Self-Excitation Attention Residual Network (SEAR) model. This model dynamically adapts to evolving disease trends and surveillance system changes, accommodating various scenarios. Thereby enhancing the effectiveness of early warning systems.
Surveillance data on influenza-like illness (ILI) was collected from various regions including Northern China, Southern China, Beijing, and Yunnan. The reproduction number (Rt) was estimated to determine the threshold for issuing warnings. The Self-Excitation Attention Residual Network (SEAR) was devised employing deep learning algorithms and was trained, validated, and tested. The SEAR model's efficacy was assessed based on five metrics: accuracy rate, recall rate, F1 score, confusion matrix, and the receiver operating characteristic curve.
With an advance warning set at three days, the SEAR model outperformed five primary models - logistic regression, support vector machine, random forest, Extreme Gradient Boosting, and Long Short-Term Memory model - in all five evaluation metrics. Notably, the model's warning performance declined with an increase in the early warning value and the number of warning days, albeit maintaining a ROC value over 0.7 in all scenarios.
The SEAR model demonstrated robust early warning performance for influenza in diverse Chinese regions with high accuracy and specificity. This novel model, augmenting traditional systems, supports widespread application for respiratory disease outbreak monitoring. Future evaluations could incorporate alternative indicators, with the model continuously updating through data feedback, thus enhancing its universal applicability. Ongoing optimization, using iterative feedback and expert judgment, heralds a transformative approach to surveillance-based early warning strategies.
本研究旨在开发一种普遍适用的、基于反馈的自激励注意力残差网络（SEAR）模型。该模型能够动态适应不断变化的疾病趋势和监测系统变化，适用于各种场景。从而提高预警系统的有效性。
收集了来自中国北方、南方、北京和云南等不同地区的流感样疾病（ILI）监测数据。估计再生数（Rt）以确定发布警告的阈值。采用深度学习算法设计了自激励注意力残差网络（SEAR），并进行了训练、验证和测试。基于准确率、召回率、F1分数、混淆矩阵和受试者工作特征曲线这五个指标评估了SEAR模型的有效性。
将提前预警设置为三天时，SEAR模型在所有五个评估指标上均优于逻辑回归、支持向量机、随机森林、极端梯度提升和长短期记忆模型这五个主要模型。值得注意的是，随着预警值和预警天数的增加，该模型的预警性能有所下降，尽管在所有情况下其ROC值均保持在0.7以上。
SEAR模型在中国不同地区对流感表现出强大的预警性能，具有高准确性和特异性。这种新型模型增强了传统系统，支持在呼吸道疾病爆发监测中的广泛应用。未来的评估可以纳入替代指标，该模型通过数据反馈不断更新，从而提高其普遍适用性。通过迭代反馈和专家判断进行的持续优化预示着基于监测的预警策略的变革性方法。
