Background: Following the outbreak of the coronavirus epidemic in early 2020, municipalities, regional governments and policymakers worldwide had to plan their Non-Pharmaceutical Interventions (NPIs) amidst a scenario of great uncertainty. At this early stage of an epidemic, where no vaccine or medical treatment is in sight, algorithmic prediction can become a powerful tool to inform local policymaking. However, when we replicated one prominent epidemiological model to inform health authorities in a region in the south of Brazil, we found that this model relied too heavily on manually predetermined covariates and was too reactive to changes in data trends. Methods: Our four proposed variations of the original method allow accessing data of daily reported infections and take into account the under-reporting of cases more explicitly. Two of the proposed versions also attempt to model the delay in test reporting. We simulated weekly forecasting of deaths from the period from 31/05/2020 until 31/01/2021. That workflow allowed us to run a lighter version of the model after the first calibration week. Google Mobility data, weekly updated, were used as covariates to the model at each simulated run. Findings: The changes made the model significantly less reactive and more rapid in adapting to scenarios after a peak in deaths is observed. Assuming that reported cases were under-reported greatly benefited the model in its stability, and modelling retroactively-added data (due to the "hot" nature of the data used) had a negligible impact on performance. Interpretation: Although not as reliable as death statistics, case statistics, when modelled in conjunction with an "overestimate" parameter, provide a good alternative for improving the forecasting of models, especially in long-range predictions and after the peak of an infection wave.
翻译:背景:在2020年初爆发了冠状病毒流行病之后,全球各城市、区域政府和决策者不得不在极不确定的情景下规划其非药物干预(NPIs)计划。在这个流行病的早期阶段,没有疫苗或医疗,算法预测可以成为向当地决策提供信息的有力工具。然而,当我们复制了一个突出的流行病学模型,以告知巴西南部一个区域的卫生当局时,我们发现这一模型过于依赖人工预设的共同变异体,而且对数据趋势的变化反应过大。方法:我们提出的四种原始方法的模型变异使得能够获取每日报告的感染数据,并更明确地考虑到病例报告不足的情况。在这个流行病的早期阶段,没有看到疫苗或医疗治疗的早期,算法预测可以成为一个强有力的工具。当我们复制了一个显著的流行病学模型,在第一个校准周之后,我们得以对模型进行较轻的版本。谷歌流动数据、每周更新的更新后,在每次模拟运行的模型中都用作替代模型的变异数据。结果是:在模型中,在不断更新的模型中,不断更新的数据在不断更新的数据中,在不断更新后,在不断更新数据中,在更新数据中,在更新数据中,在不断更新数据中,在更新数据中,在不断更新数据中,在不断更新中,在更新数据中,在不断更新数据中,在更新数据中,在不断更新数据中,在更新数据中,在更新数据中的数据在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在不断更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在不断更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在更新数据中,在