October 19, 2022
Back to all short courses
Metamodeling for Simulation-Based Optimization of Strategies in Healthcare (Virtual)
LEVEL: Intermediate
TRACK: Methodological & Statistical Research
LENGTH: 4 Hours | Course runs 1 day
Register Here
15:00PM-19:00PM Central European Summer Time (CEST)
13:00PM-17:00PM Coordinated Universal Time (UTC)
09:00AM-13:00PM Eastern Daylight Time (EDT)
Click for time zone conversion
DESCRIPTION
It can be computationally challenging to perform analyses that require many simulation model evaluations. For example, studies applying optimization algorithms to optimize healthcare strategies, in terms of health or economic outcomes, may require tens of thousands to millions of model runs. Despite advancements in computational power, the computational burden of such analyses quickly makes them infeasible to perform within acceptable time frames. Consequently, strategy evaluations are performed given that strategy optimization is deemed problematic. By substituting original simulation models by metamodels, the computational burden of optimization algorithms can be substantially reduced. Metamodels can be seen as functions that approximate the outcomes of original simulation models almost instantaneously. Metamodels are frequently applied in many fields of research and recent research has demonstrated their value within health economics. To introduce modelers to the potential and application of metamodeling methods, this course will cover the basics of using metamodels to negate runtime issues with simulation models. A single case study will be used throughout several hands-on exercises, in which metamodels will be developed to enable otherwise infeasible optimization of a screening strategy using a computationally demanding health economic simulation model. During the course R is used for all exercises, and several ready-to-use scripts are provided. Therefore, participants will be equipped with all the knowledge and tools required to develop metamodels for their own projects. Participants who wish to gain hands-on experience are required to bring their laptops with RStudio installed. Further information and prereading materials will be provided closer to the course date.
Koen Degeling, MSc, PhD
Research Scientist, Health Economic Modelling & Advanced Analytics
Lumen Value & Access, A Healthcare Consultancy Group company
Amsterdam, Netherlands
Hendrik Koffijberg, MSc, PhD
Associate Professor, Health Technology Assessment
University of Twente
Enschede, Netherlands
Basic Schedule:
Class Time: 4 hours