Can auxiliary indicators improve COVID-19 forecasting and hotspot prediction?
Can auxiliary indicators improve COVID-19 forecasting and hotspot prediction?
复制标题
DOI：
10.1073/pnas.2111453118
复制
发表时间：
2021-12-21
影响因子：
11.1
通讯作者：
Tibshirani RJ
中科院分区：
文献类型：
--
作者：
McDonald DJ;Bien J;Green A;Hu AJ;DeFries N;Hyun S;Oliveira NL;Sharpnack J;Tang J;Tibshirani R;Ventura V;Wasserman L;Tibshirani RJ
经过验证的预测方法应该是公共卫生应对任何快速蔓延的流行病或大流行病的重要因素。用于预测时间过程的未来扩展的广泛使用的模型是自回归（AR）模型。虽然是基本的，但这种AR模型（经过适当训练）已经可以与COVID-19预测的顶级模型竞争。在本文中，我们展示了五个辅助指标-基于去识别的医疗保险索赔，通过在线调查自我报告的症状以及与COVID相关的Google搜索-进一步提高了AR模型在COVID-19预测中的预测准确性。最大的收益似乎是在静止时期;但谷歌搜索指标似乎也在流行病活动上升期间提供了改善。对来自公共卫生报告的传统数据流（如病例、住院和死亡）的短期预测是大流行期间公共卫生决策的关键输入。自2020年初以来，我们的研究团队与数据合作伙伴合作，收集、策划并公开大量实时COVID-19指标，提供美国大流行活动的多个视图。本文从预测的角度研究了五个此类指标的实用性-来自去识别的医疗保险索赔、在线调查中的自我报告症状以及与COVID相关的Google搜索活动。对于每一个指标，我们都要问，相对于不包括它的同一模型，将其纳入自回归（AR）模型是否会提高预测准确性。这样一个没有外部特征的AR模型，已经可以与当今使用的许多顶级COVID-19预测模型竞争。我们的分析显示，1）包含这五个指标中的每一个都提高了AR模型的整体预测准确性; 2）预测收益通常在COVID病例呈“持平”或“下降”趋势时最为明显; 3）基于谷歌搜索的一个指标似乎在“上升”趋势时特别有用。
Validated forecasting methodology should be a vital element in the public health response to any fast-moving epidemic or pandemic. A widely used model for predicting the future spread of a temporal process is an autoregressive (AR) model. While basic, such an AR model (properly trained) is already competitive with the top models in operational use for COVID-19 forecasting. In this paper, we exhibit five auxiliary indicators—based on deidentified medical insurance claims, self-reported symptoms via online surveys, and COVID-related Google searches—that further improve the predictive accuracy of an AR model in COVID-19 forecasting. The most substantial gains appear to be in quiescent times; but the Google search indicator appears to also offer improvements during upswings in pandemic activity. Short-term forecasts of traditional streams from public health reporting (such as cases, hospitalizations, and deaths) are a key input to public health decision-making during a pandemic. Since early 2020, our research group has worked with data partners to collect, curate, and make publicly available numerous real-time COVID-19 indicators, providing multiple views of pandemic activity in the United States. This paper studies the utility of five such indicators—derived from deidentified medical insurance claims, self-reported symptoms from online surveys, and COVID-related Google search activity—from a forecasting perspective. For each indicator, we ask whether its inclusion in an autoregressive (AR) model leads to improved predictive accuracy relative to the same model excluding it. Such an AR model, without external features, is already competitive with many top COVID-19 forecasting models in use today. Our analysis reveals that 1) inclusion of each of these five indicators improves on the overall predictive accuracy of the AR model; 2) predictive gains are in general most pronounced during times in which COVID cases are trending in “flat” or “down” directions; and 3) one indicator, based on Google searches, seems to be particularly helpful during “up” trends.
登录
查看更多内容
影响因子：
8
作者：
AUERBACH, AJ
通讯作者：
AUERBACH, AJ
影响因子：
3
作者：
Faust, Jon;Wright, Jonathan H.
通讯作者：
Wright, Jonathan H.
DOI：
10.1016/s1574-0706(05)01017-7
发表时间：
2006-01-01
期刊：
HANDBOOK OF ECONOMIC FORECASTING: VOL 1
影响因子：
--
作者：
Croushore, Dean
通讯作者：
Croushore, Dean
影响因子：
--
作者：
Hamilton, JD;PerezQuiros, G
通讯作者：
PerezQuiros, G
影响因子：
8
作者：
HOWREY, EP
通讯作者：
HOWREY, EP