Advances in decision modeling using R. Collaborating in an open source space
Department Research Seminars
Wednesday, 12 February 2020, 4pm to 5pm
Big Data Institute, LG 0 Seminar Room, University of Oxford Old Road Campus, Oxford, OX3 7LF
Hosted by HERC
This seminar will be delivered remotely by Eline Krijkamp (Netherlands Institute of Health Sciences) and Petros Pechlivanoglou (University of Toronto) from the DARTH group
Abstract: High-impact journals increasingly encourage that (some of) the data and the code used in clinical and policy research should be archived and made publicly available alongside a publication. Similarly, efforts are under way for making decision models, which form the basis of economic evaluations and cost-effectiveness analysis, publically available, more transparent, reproducible, and adaptable to new applications. R is an open-source programming environment that can facilitate model transparency, reproducibility, and shareability, through a number of innovative ways (Markdown, Shiny etc.). However, realizing this potential can be challenging given the lack of expertise and standardized use in the field of health decision analysis, and the famous “steep learning curve” of R. Over the past years, a number of groups around the globe have worked, in parallel, on the development of materials to conduct decision modelling in R, analyse the results of decision models, improve and harmonize the link between input parameters and decision models as well as standardize the use of R in decision analysis. During this seminar we will talk about the use of R in the field of health decision making, its advantages and disadvantages. We will talk about existing and future trends in the work of these groups and highlight some examples. Finally, we will briefly illustrate the use of R for decision analysis through the recently developed darthpack R package.
Biography: DARTH (Decision Analysis in R for Technologies in Health) is a multi-institutional, multi-university collaborative effort comprised of researchers who have a passion for transparent and open-source solutions to decision analysis in health. The aim of this collaboration is to expand knowledge in decision analysis using R and develop educational material that empowers people to construct R-based decision models. Eline holds a Master’s in Epidemiology from the Netherlands Institute of Health Sciences and a Master’s in Health Economics from Erasmus University Rotterdam. She is currently a PhD student in epidemiology at the Netherlands Institue of Health Sciences. Petros is a Scientist at the Hospital for Sick Children’s Research Institute and an Assistant Professor at the University of Toronto’s Institute of Health Policy, Management and Evaluation. After studying economics in his native Greece, he received both a Master’s in econometrics and a PhD in health econometrics from the University of Groningen. His research interests include: the use of health decision analysis in economic evaluation; bridging evidence synthesis, administrative data and decision analysis; and the application and extension of predictive models in health economics.