Calculating the Expected Value of Sample Information Using Efficient Nested Monte Carlo: A Tutorial.

@article{Heath2018CalculatingTE,
  title={Calculating the Expected Value of Sample Information Using Efficient Nested Monte Carlo: A Tutorial.},
  author={Anna Heath and Gianluca Baio},
  journal={Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research},
  year={2018},
  volume={21 11},
  pages={
          1299-1304
        }
}
  • Anna Heath, G. Baio
  • Published 7 September 2017
  • Medicine
  • Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research

Tables from this paper

Calculating the Expected Value of Sample Information in Practice: Considerations from 3 Case Studies
TLDR
It is suggested that EVSI can now be efficiently computed with confidence in realistic examples, as all the evaluated methods gave estimates similar to those given by traditional Monte Carlo.
Estimating the Expected Value of Sample Information across Different Sample Sizes Using Moment Matching and Nonlinear Regression
TLDR
A method to reduce the computation time required to calculate the expected value of sample information (EVSI) across different sample sizes is developed, which will allow researchers to realize the potential of using the EVSI to determine an economically optimal trial design for reducing uncertainty in health economic models.
Calculating Expected Value of Sample Information Adjusting for Imperfect Implementation
  • Anna Heath
  • Computer Science
    Medical decision making : an international journal of the Society for Medical Decision Making
  • 2022
TLDR
Two methods, based on nested Monte Carlo sampling and the moment matching EVSI calculation method, are developed to adjust EVSI calculations for imperfect implementation when the speed and level of the implementation of a new treatment depends on the strength of evidence in favor of the treatment.
Computing the Expected Value of Sample Information Efficiently: Practical Guidance and Recommendations for Four Model-Based Methods.
  • Natalia Kunst, E. Wilson, Anna Heath
  • Computer Science
    Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research
  • 2020
Optimal Allocation of Research Funds under a Budget Constraint
TLDR
This work employs a budget-constrained portfolio optimization framework in which the decisions are whether to invest in a study and at what sample size, and shows how to determine the optimal research portfolio and study-specific levels of investment.
Prioritizing Research in an Era of Personalized Medicine: The Potential Value of Unexplained Heterogeneity
  • Anna Heath, P. Pechlivanoglou
  • Psychology
    Medical decision making : an international journal of the Society for Medical Decision Making
  • 2022
TLDR
3 measures that assess the value of personalizing care based on a set of unknown patient characteristics form the basis of a novel framework to prioritize research into novel personalized treatment strategies that have high potential to improve patient outcomes and health system efficiency.
Probabilistic threshold analysis by pairwise stochastic approximation for decision-making under uncertainty
TLDR
This paper forms the probabilistic threshold analysis as a root-finding problem involving the conditional expectations, and proposes a pairwise stochastic approximation algorithm to search for the threshold value below and above which the choice of conditionally optimal decision options changes.
BayCANN: Streamlining Bayesian Calibration With Artificial Neural Network Metamodeling
TLDR
BayCANN only uses a dataset of model inputs and outputs to obtain the calibrated joint parameter distributions, and can be adapted to models of various levels of complexity with minor or no change to its structure.
Universal late pregnancy ultrasound screening to predict adverse outcomes in nulliparous women: a systematic review and cost-effectiveness analysis.
TLDR
The case for offering universal late pregnancy ultrasound to all nulliparous women in the UK is assessed and health economic analysis indicated that universal ultrasound for fetal presentation only may be both clinically and economically justified on the basis of existing evidence.
...
...

References

SHOWING 1-10 OF 45 REFERENCES
Efficient Monte Carlo Estimation of the Expected Value of Sample Information Using Moment Matching
TLDR
This work presents an approximation method for the EVSI that is framed in a Bayesian setting and is based on estimating the distribution of the posterior mean of the incremental net benefit across all possible future samples, known as the Distribution of the preposterior mean.
A Review of Methods for Analysis of the Expected Value of Information
TLDR
A method based on nonparametric regression offers the best method for calculating the EVPPI in terms of accuracy, computational time, and ease of implementation and can now be used practically in health economic evaluations, especially as all the methods are developed in parallel with R functions and a web app to aid practitioners.
Expected Value of Sample Information Calculations in Medical Decision Modeling
  • A. Ades, G. Lu, K. Claxton
  • Mathematics
    Medical decision making : an international journal of the Society for Medical Decision Making
  • 2004
TLDR
Simple Monte Carlo methods are derived that extend the use of EVSI calculations to medical decision applications with multiple sources of uncertainty, with particular attention to the form in which epidemiological data and research findings are structured.
Estimating the Expected Value of Sample Information Using the Probabilistic Sensitivity Analysis Sample
TLDR
A fast nonparametric regression-based method for estimating per-patient EVSI that requires only the probabilistic sensitivity analysis sample, which is applicable with a model of any complexity and with any specification of model parameter distribution.
Estimating the expected value of partial perfect information in health economic evaluations using integrated nested Laplace approximation
TLDR
It is demonstrated that the EVPPI calculated using the method for GP regression is in line with the standard GP regression method and that despite the apparent methodological complexity of this new method, R functions are available in the package BCEA to implement it simply and efficiently.
An Efficient Estimator for the Expected Value of Sample Information
  • N. Menzies
  • Engineering
    Medical decision making : an international journal of the Society for Medical Decision Making
  • 2016
TLDR
A novel approach that allows efficient EVSI computation for a wide range of study designs and is applicable to models of arbitrary complexity is described, removing two major challenges for estimating EVSI—the difficulty of estimating the posterior parameter distribution given hypothetical study data and the need for many model evaluations.
Estimating Expected Value of Sample Information for Incomplete Data Models Using Bayesian Approximation
TLDR
A revision to a form of Bayesian Laplace approximation for EVSI computation to support decisions in incomplete data models and potential wider benefits in many fields requiring Bayesian approximation is described.
Adjusting Estimates of the Expected Value of Information for Implementation
  • L. Andronis, P. Barton
  • Economics
    Medical decision making : an international journal of the Society for Medical Decision Making
  • 2016
TLDR
This article provides a simple framework that accounts for improved, rather than perfect, implementation and offers more realistic estimates of the expected value of research.
Computing Expected Value of Partial Sample Information from Probabilistic Sensitivity Analysis Using Linear Regression Metamodeling
TLDR
This study proposes a novel practical approach for conductingVOI analysis using a combination of probabilistic sensitivity analysis, linear regression metamodeling, and unit normal loss integral function—a parametric approach to VOI analysis.
Calculating Partial Expected Value of Perfect Information via Monte Carlo Sampling Algorithms
TLDR
A wider application of partial EVPI is recommended both for greater understanding of decision uncertainty and for analyzing research priorities, as empirical investigation of the numbers of Monte Carlo samples suggests that fewer samples on the outer level and more on the inner level could be efficient and that relatively small numbers of samples can sometimes be used.
...
...