Eliciting Distributions to Populate Decision Analytic Models

Laura Bojke; Karl Claxton; Yolanda Bravo-Vergel; Mark Sculpher; Stephen Palmer; Keith Abrams

doi:10.1111/j.1524-4733.2010.00709.x

Eliciting Distributions to Populate Decision Analytic Models

Laura Bojke, Karl Claxton, Yolanda Bravo-Vergel, Mark Sculpher, Stephen Palmer, Keith Abrams

Research output: Contribution to journal › Article › peer-review

Abstract

Background:

Elicitation can be used to characterize structural uncertainty within a decision analytic model. This allows the value of acquiring further evidence to resolve these uncertainties to be established.

Aim:

This article demonstrated the use of expert elicitation for this purpose and also compared the elicited results with the results from alternative assumptions previously used to characterize the uncertainties.

Materials and Methods:

Distributions for two unknown parameters were elicited. These were used within a model developed to assess the cost-effectiveness of infliximab and etanercept for the treatment of active psoriatic arthritis (PsA), compared with palliative care. The experts' distributions were synthesized using two approaches: linear pooling and random effects meta-analysis. Weighting of experts is also explored.

Results:

The four methods produce broadly similar results, and in each, the choice of optimum strategy is between etanercept and palliative care (incremental cost-effective ratio for etanercept is between 29,021 pound and 39,259 pound per costs and quality adjusted life years). Decision uncertainty, at a 30,000 pound threshold, is high in all of the synthesis models thus generating high values of further research at between 141 pound and 634 pound million. In each model, the greatest value of further research was for the short-term effectiveness of treatment (47- pound 406 pound million).

Discussion:

Although the cost-effectiveness results do not differ substantially between the models using the elicited values and the original scenarios, there are some stark contrasts in terms of the values of further research generated.

Conclusion:

Elicitation offers a feasible method to generate evidence for the missing information but there are a number of key issues for which further research is required.

Original language	English
Pages (from-to)	557-564
Number of pages	8
Journal	Value in Health
Volume	13
Issue number	5
DOIs	https://doi.org/10.1111/j.1524-4733.2010.00709.x
Publication status	Published - Jul 2010

Keywords

cost-effectiveness
decision analysis
elicitation
uncertainty
COST-EFFECTIVENESS
UNCERTAINTY

Access to Document

10.1111/j.1524-4733.2010.00709.x

Cite this

@article{3e64aaf25ff34dadb8448626aa843c84,

title = "Eliciting Distributions to Populate Decision Analytic Models",

abstract = "Background:Elicitation can be used to characterize structural uncertainty within a decision analytic model. This allows the value of acquiring further evidence to resolve these uncertainties to be established.Aim:This article demonstrated the use of expert elicitation for this purpose and also compared the elicited results with the results from alternative assumptions previously used to characterize the uncertainties.Materials and Methods:Distributions for two unknown parameters were elicited. These were used within a model developed to assess the cost-effectiveness of infliximab and etanercept for the treatment of active psoriatic arthritis (PsA), compared with palliative care. The experts' distributions were synthesized using two approaches: linear pooling and random effects meta-analysis. Weighting of experts is also explored.Results:The four methods produce broadly similar results, and in each, the choice of optimum strategy is between etanercept and palliative care (incremental cost-effective ratio for etanercept is between 29,021 pound and 39,259 pound per costs and quality adjusted life years). Decision uncertainty, at a 30,000 pound threshold, is high in all of the synthesis models thus generating high values of further research at between 141 pound and 634 pound million. In each model, the greatest value of further research was for the short-term effectiveness of treatment (47- pound 406 pound million).Discussion:Although the cost-effectiveness results do not differ substantially between the models using the elicited values and the original scenarios, there are some stark contrasts in terms of the values of further research generated.Conclusion:Elicitation offers a feasible method to generate evidence for the missing information but there are a number of key issues for which further research is required.",

keywords = "cost-effectiveness, decision analysis, elicitation, uncertainty, COST-EFFECTIVENESS, UNCERTAINTY",

author = "Laura Bojke and Karl Claxton and Yolanda Bravo-Vergel and Mark Sculpher and Stephen Palmer and Keith Abrams",

year = "2010",

month = jul,

doi = "10.1111/j.1524-4733.2010.00709.x",

language = "English",

volume = "13",

pages = "557--564",

journal = "Value in Health",

issn = "1524-4733",

publisher = "Elsevier",

number = "5",

}

TY - JOUR

T1 - Eliciting Distributions to Populate Decision Analytic Models

AU - Bojke, Laura

AU - Claxton, Karl

AU - Bravo-Vergel, Yolanda

AU - Sculpher, Mark

AU - Palmer, Stephen

AU - Abrams, Keith

PY - 2010/7

Y1 - 2010/7

N2 - Background:Elicitation can be used to characterize structural uncertainty within a decision analytic model. This allows the value of acquiring further evidence to resolve these uncertainties to be established.Aim:This article demonstrated the use of expert elicitation for this purpose and also compared the elicited results with the results from alternative assumptions previously used to characterize the uncertainties.Materials and Methods:Distributions for two unknown parameters were elicited. These were used within a model developed to assess the cost-effectiveness of infliximab and etanercept for the treatment of active psoriatic arthritis (PsA), compared with palliative care. The experts' distributions were synthesized using two approaches: linear pooling and random effects meta-analysis. Weighting of experts is also explored.Results:The four methods produce broadly similar results, and in each, the choice of optimum strategy is between etanercept and palliative care (incremental cost-effective ratio for etanercept is between 29,021 pound and 39,259 pound per costs and quality adjusted life years). Decision uncertainty, at a 30,000 pound threshold, is high in all of the synthesis models thus generating high values of further research at between 141 pound and 634 pound million. In each model, the greatest value of further research was for the short-term effectiveness of treatment (47- pound 406 pound million).Discussion:Although the cost-effectiveness results do not differ substantially between the models using the elicited values and the original scenarios, there are some stark contrasts in terms of the values of further research generated.Conclusion:Elicitation offers a feasible method to generate evidence for the missing information but there are a number of key issues for which further research is required.

AB - Background:Elicitation can be used to characterize structural uncertainty within a decision analytic model. This allows the value of acquiring further evidence to resolve these uncertainties to be established.Aim:This article demonstrated the use of expert elicitation for this purpose and also compared the elicited results with the results from alternative assumptions previously used to characterize the uncertainties.Materials and Methods:Distributions for two unknown parameters were elicited. These were used within a model developed to assess the cost-effectiveness of infliximab and etanercept for the treatment of active psoriatic arthritis (PsA), compared with palliative care. The experts' distributions were synthesized using two approaches: linear pooling and random effects meta-analysis. Weighting of experts is also explored.Results:The four methods produce broadly similar results, and in each, the choice of optimum strategy is between etanercept and palliative care (incremental cost-effective ratio for etanercept is between 29,021 pound and 39,259 pound per costs and quality adjusted life years). Decision uncertainty, at a 30,000 pound threshold, is high in all of the synthesis models thus generating high values of further research at between 141 pound and 634 pound million. In each model, the greatest value of further research was for the short-term effectiveness of treatment (47- pound 406 pound million).Discussion:Although the cost-effectiveness results do not differ substantially between the models using the elicited values and the original scenarios, there are some stark contrasts in terms of the values of further research generated.Conclusion:Elicitation offers a feasible method to generate evidence for the missing information but there are a number of key issues for which further research is required.

KW - cost-effectiveness

KW - decision analysis

KW - elicitation

KW - uncertainty

KW - COST-EFFECTIVENESS

KW - UNCERTAINTY

UR - http://www.scopus.com/inward/record.url?scp=77955462630&partnerID=8YFLogxK

U2 - 10.1111/j.1524-4733.2010.00709.x

DO - 10.1111/j.1524-4733.2010.00709.x

M3 - Article

SN - 1524-4733

VL - 13

SP - 557

EP - 564

JO - Value in Health

JF - Value in Health

IS - 5

ER -

Eliciting Distributions to Populate Decision Analytic Models

Abstract

Keywords

Access to Document

Other files and links

Cite this