Department of Automation, Tsinghua University, Beijing, People's Republic of China.
Clinical College of Chinese Medicine, Hubei University of Chinese Medicine, Wuhan, Hubei, People's Republic of China.
J Biomed Inform. 2021 Oct;122:103894. doi: 10.1016/j.jbi.2021.103894. Epub 2021 Aug 26.
Influenza is one of the most common infectious diseases worldwide, which causes a considerable economic burden on hospitals and other healthcare costs. Predicting new and urgent trends in epidemiological data is an effective way to prevent influenza outbreaks and protect public health. Traditional autoregressive(AR) methods and new deep learning models like Recurrent Neural Network(RNN) have been actively studied to solve the problem. Most existing studies focus on the short-term prediction of influenza. Recently, Transformer models show superior performance in capturing long-range dependency than RNN models. In this paper, we develop a Transformer-based model, which utilizes the potential of the Transformer to increase the prediction capacity. To fuse information from data of different sources and capture the spatial dependency, we design a sources selection module based on measuring curve similarity. Our model is compared with the widely used AR models and RNN-based models on USA and Japan datasets. Results show that our approach provides approximate performance in short-term forecasting and better performance in long-term forecasting.
流感是全球最常见的传染病之一，给医院和其他医疗保健成本造成了相当大的经济负担。预测流行病学数据中的新的和紧迫的趋势是预防流感爆发和保护公众健康的有效方法。传统的自回归（AR）方法和新的深度学习模型，如递归神经网络（RNN），已经被积极研究来解决这个问题。大多数现有研究都集中在流感的短期预测上。最近，Transformer 模型在捕捉长程依赖关系方面的表现优于 RNN 模型。在本文中，我们开发了一种基于 Transformer 的模型，利用 Transformer 的潜力来提高预测能力。为了融合来自不同数据源的数据信息并捕捉空间依赖性，我们设计了一个基于曲线相似性度量的源选择模块。我们的模型在美国和日本数据集上与广泛使用的 AR 模型和基于 RNN 的模型进行了比较。结果表明，我们的方法在短期预测中提供了近似的性能，在长期预测中提供了更好的性能。
