Predictive performance of international COVID-19 mortality forecasting models.
Predictive performance of international COVID-19 mortality forecasting models.
复制标题
国际COVID-19死亡率预测模型的预测性能。
DOI：
10.1038/s41467-021-22457-w
复制
发表时间：
2021-05-10
影响因子：
16.6
通讯作者：
Gakidou E
中科院分区：
文献类型：
--
作者：
Friedman J;Liu P;Troeger CE;Carter A;Reiner RC Jr;Barber RM;Collins J;Lim SS;Pigott DM;Vos T;Hay SI;Murray CJL;Gakidou E
COVID-19死亡率的预测和替代情景一直是大流行应对工作的关键投入，决策者需要有关预测绩效的信息。我们筛选了n = 386个公开的COVID-19预测模型，确定了n = 7个全球范围的模型，并提供了公开的日期版本预测。我们通过外推周数、世界区域和估计月份来检查它们对死亡率的预测性能。我们还评估了每日死亡率高峰时间的预测。在全球范围内，10月份发布的模型显示，六周内的绝对百分比误差（MAPE）中位数为7%至13%，尽管人类行为反应和政府干预的建模非常复杂，但这反映出令人惊讶的良好表现。峰值时间的中位绝对误差从一周预测的8天增加到八周预测的29天，并且对于第一个和随后的峰值是相似的。框架和公共代码库（https：//github.com/pyliu47/covidcompare）可用于比较预测并评估预测性能。对COVID-19死亡率的预测一直是一系列政策的关键投入，决策者需要有关其预测性能的信息。在这里，作者收集了一组全球流行病学模型，并评估了它们在时间和空间上的预测性能。
Forecasts and alternative scenarios of COVID-19 mortality have been critical inputs for pandemic response efforts, and decision-makers need information about predictive performance. We screen n = 386 public COVID-19 forecasting models, identifying n = 7 that are global in scope and provide public, date-versioned forecasts. We examine their predictive performance for mortality by weeks of extrapolation, world region, and estimation month. We additionally assess prediction of the timing of peak daily mortality. Globally, models released in October show a median absolute percent error (MAPE) of 7 to 13% at six weeks, reflecting surprisingly good performance despite the complexities of modelling human behavioural responses and government interventions. Median absolute error for peak timing increased from 8 days at one week of forecasting to 29 days at eight weeks and is similar for first and subsequent peaks. The framework and public codebase (https://github.com/pyliu47/covidcompare) can be used to compare predictions and evaluate predictive performance going forward. Forecasts of COVID-19 mortality have been critical inputs into a range of policies, and decision-makers need information about their predictive performance. Here, the authors gather a panel of global epidemiological models and assess their predictive performance across time and space.