Traditionally, expert epidemiologists devise policies for disease control through a mixture of intuition and brute force. Namely, they use their know-how to narrow down the set of logically conceivable policies to a small family described by a few parameters, following which they conduct a grid search to identify the optimal policy within the set. This scheme is not scalable, in the sense that, when used to optimize over policies which depend on many parameters, it will likely fail to output an optimal disease policy in time for its implementation. In this article, we use techniques from convex optimization theory and machine learning to conduct optimizations over disease policies described by hundreds of parameters. In contrast to past approaches for policy optimization based on control theory, our framework can deal with arbitrary uncertainties on the initial conditions and model parameters controlling the spread of the disease. In addition, our methods allow for optimization over weekly-constant policies, specified by either continuous or discrete government measures (e.g.: lockdown on/off). We illustrate our approach by minimizing the total time required to eradicate COVID-19 within the Susceptible-Exposed-Infected-Recovered (SEIR) model proposed by Kissler \emph{et al.} (March, 2020).
翻译:传统上,专家流行病学学家通过直觉和野蛮力量的混合力量制定疾病控制政策。 也就是说,他们利用他们的专门技能将一套逻辑上可以想象的政策缩小到几个参数描述的小家庭,然后进行网格搜索,以确定集中的最佳政策。 这个计划是无法伸缩的,也就是说,当用来优化依赖许多参数的政策时,它可能无法及时产生最佳的疾病政策来加以执行。 在本条中,我们使用来自锥形优化理论和机器学习的技术来对数百项参数描述的疾病政策进行优化。 与以往基于控制理论的政策优化方法相比,我们的框架可以处理控制疾病蔓延的初始条件和模型参数方面的任意不确定性。 此外,我们的方法允许对每周的一致政策进行优化,通过连续或离散的政府措施加以规定(例如:锁定/关闭) 。 我们通过最大限度地减少在可察觉的探索性扩散范围内消除COVID-19所需的全部时间来说明我们的方法。 (SEERIQ) 2020年3月(SEIR) 提议的模型。