Active Learning to Understand Infectious Disease Models and Improve Policy Making
نویسندگان
چکیده
Modeling plays a major role in policy making, especially for infectious disease interventions but such models can be complex and computationally intensive. A more systematic exploration is needed to gain a thorough systems understanding. We present an active learning approach based on machine learning techniques as iterative surrogate modeling and model-guided experimentation to systematically analyze both common and edge manifestations of complex model runs. Symbolic regression is used for nonlinear response surface modeling with automatic feature selection. First, we illustrate our approach using an individual-based model for influenza vaccination. After optimizing the parameter space, we observe an inverse relationship between vaccination coverage and cumulative attack rate reinforced by herd immunity. Second, we demonstrate the use of surrogate modeling techniques on input-response data from a deterministic dynamic model, which was designed to explore the cost-effectiveness of varicella-zoster virus vaccination. We use symbolic regression to handle high dimensionality and correlated inputs and to identify the most influential variables. Provided insight is used to focus research, reduce dimensionality and decrease decision uncertainty. We conclude that active learning is needed to fully understand complex systems behavior. Surrogate models can be readily explored at no computational expense, and can also be used as emulator to improve rapid policy making in various settings.
منابع مشابه
A Call for a Backward Design to Knowledge Translation
Despite several calls to support evidence-informed policy-making, variations in uptake of evidence into policy persist. This editorial brings together and builds on previous Knowledge Translation (KT) frameworks and theories to present a simple, yet, holistic approach for promoting evidence-informed policies. The proposed conceptual framework is characterized by its impact-oriented approach and...
متن کاملThe Spatial Allocation of Hospitals With Negative Pressure Isolation Rooms in Korea: Are We Prepared for New Outbreaks?
Background Allocation of adequate healthcare facilities is one of the most important factors that public health policy-makers consider when preparing for infectious disease outbreaks. Negative pressure isolation rooms (NPIRs) are one of the critical resources for control of infectious respiratory diseases, such as the novel coronavirus disease 2019 (COVID-19) outbreak. However, there is insuffi...
متن کاملExclusion of Ageing in Social Policy Analyzing Development Plans after the Revolution
The living of the elderly has been turned into a problematic issue affected by social, cultural and economic changes, however, this problematic is not registered in policy makings and there is not appropriate social polices associated to the elderly. The subject of the current study is observe social policies in the context of development plans after the Revolution, to discover overt and covert...
متن کاملToward Standardizing a Lexicon of Infectious Disease Modeling Terms
Disease modeling is increasingly being used to evaluate the effect of health intervention strategies, particularly for infectious diseases. However, the utility and application of such models are hampered by the inconsistent use of infectious disease modeling terms between and within disciplines. We sought to standardize the lexicon of infectious disease modeling terms and develop a glossary of...
متن کاملLessons From Zika Policies to Improve Gender Equity
Gender equity is easily supported in theory but harder to pursue in practice. In this article, the case of Zika travel policies is used to illustrate some glaring gaps related to gender, for both men and women, at both international and national levels. Zika travel policies have not considered new evidence on biological or social determinants of health, putting babies at risk of exposure. The a...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره 10 شماره
صفحات -
تاریخ انتشار 2014