[论文解读] Artificial Intelligence Forecasting of Covid-19 in China

Zixin Hu, Qiyang Ge+3 more|arXiv (Cornell University)|Feb 17, 2020

COVID-19 epidemiological studies参考文献 7被引用 118

一句话总结

本文提出一种受AI启发的方法，使用改进后的堆叠自编码器来预测 COVID-19 在 China 的轨迹，获得多步预测误差在低个位数，并将省份按照传播基础分组。

ABSTRACT

BACKGROUND An alternative to epidemiological models for transmission dynamics of Covid-19 in China, we propose the artificial intelligence (AI)-inspired methods for real-time forecasting of Covid-19 to estimate the size, lengths and ending time of Covid-19 across China. METHODS We developed a modified stacked auto-encoder for modeling the transmission dynamics of the epidemics. We applied this model to real-time forecasting the confirmed cases of Covid-19 across China. The data were collected from January 11 to February 27, 2020 by WHO. We used the latent variables in the auto-encoder and clustering algorithms to group the provinces/cities for investigating the transmission structure. RESULTS We forecasted curves of cumulative confirmed cases of Covid-19 across China from Jan 20, 2020 to April 20, 2020. Using the multiple-step forecasting, the estimated average errors of 6-step, 7-step, 8-step, 9-step and 10-step forecasting were 1.64%, 2.27%, 2.14%, 2.08%, 0.73%, respectively. We predicted that the time points of the provinces/cities entering the plateau of the forecasted transmission dynamic curves varied, ranging from Jan 21 to April 19, 2020. The 34 provinces/cities were grouped into 9 clusters. CONCLUSIONS The accuracy of the AI-based methods for forecasting the trajectory of Covid-19 was high. We predicted that the epidemics of Covid-19 will be over by the middle of April. If the data are reliable and there are no second transmissions, we can accurately forecast the transmission dynamics of the Covid-19 across the provinces/cities in China. The AI-inspired methods are a powerful tool for helping public health planning and policymaking.

研究动机与目标

• 为在 China 实时 COVID-19 预测提供传统流行病模型的 AI 驱动替代方案。
• 开发一个改进的堆叠自编码器，以基于 2020 年初的数据建模传播动态。
• 利用潜变量表示对省份/城市进行聚类并揭示传播结构。
• 提供累计确诊病例的多步预测，并识别各地区的 plateau（平台期）时机。

提出的方法

• 开发一个改进的堆叠自编码器来建模 COVID-19 传播动力学。
• 将该模型应用于 2020 年 1 月 11 日至 2 月 27 日的中国实时省级数据。
• 利用自编码器的潜变量进行聚类，将省份/城市分组为基于传播的簇。
• 执行多步预测，以预测 2020 年 1 月 20 日至 2020 年 4 月 20 日的累计病例。
• 使用 6-到 10 步预测区间的逐步误差来估计预测准确性。

实验结果

研究问题

• RQ1 AI 启发的模型，特别是改进的堆叠自编码器，是否能够在 China 的省份和城市中准确预测 COVID-19 的轨迹？
• RQ2 潜变量表示如何捕捉区域传播结构并支持对省份/城市的聚类？
• RQ3 在 China 的累计确诊病例上，6–10 步多步预测的预期准确度是多少？
• RQ4 在数据可靠的假设下，省份/城市在预测的传播动态中何时进入平台期？

主要发现

• 基于 AI 的方法在多步时间范围内（6 步至 10 步）的平均预测误差较低，分别报告为 1.64%、2.27%、2.14%、2.08%、和 0.73%。
• 基于潜在表示，将 34 个省份/城市分为 9 个簇。
• 该模型对 2020 年 1 月 20 日至 2020 年 4 月 20 日在 China 的累计确诊病例轨迹进行了预测。
• 在数据可靠且无二次传播的前提下，预测疫情可能在四月中旬结束。
• 潜在变量聚类揭示了省份/城市之间的传播结构，支持有针对性的公共卫生规划。