Using CART to identify thresholds and hierarchies in the determinants of funding decisions

Chris Schilling, Duncan Mortimer, Kim Dalziel

Research output: Contribution to journalArticleResearchpeer-review

Abstract

There is much interest in understanding decision-making processes that determine funding outcomes for health interventions. We use classification and regression trees (CART) to identify cost-effectiveness thresholds and hierarchies in the determinants of funding decisions. The hierarchical structure of CART is suited to analyzing complex conditional and nonlinear relationships. Our analysis uncovered hierarchies where interventions were grouped according to their type and objective. Cost-effectiveness thresholds varied markedly depending on which group the intervention belonged to: lifestyle-type interventions with a prevention objective had an incremental cost-effectiveness threshold of $2356, suggesting that such interventions need to be close to cost saving or dominant to be funded. For lifestyle-type interventions with a treatment objective, the threshold was much higher at $37,024. Lower down the tree, intervention attributes such as the level of patient contribution and the eligibility for government reimbursement influenced the likelihood of funding within groups of similar interventions. Comparison between our CART models and previously published results demonstrated concurrence with standard regression techniques while providing additional insights regarding the role of the funding environment and the structure of decision-maker preferences.
Original languageEnglish
Pages (from-to)173-182
Number of pages10
JournalMedical Decision Making
Volume37
Issue number2
DOIs
Publication statusPublished - Feb 2017

Keywords

  • CART
  • cost-effectiveness
  • funding of health care

Cite this

@article{7e8b709023f7463dbe64bc7673b225cf,
title = "Using CART to identify thresholds and hierarchies in the determinants of funding decisions",
abstract = "There is much interest in understanding decision-making processes that determine funding outcomes for health interventions. We use classification and regression trees (CART) to identify cost-effectiveness thresholds and hierarchies in the determinants of funding decisions. The hierarchical structure of CART is suited to analyzing complex conditional and nonlinear relationships. Our analysis uncovered hierarchies where interventions were grouped according to their type and objective. Cost-effectiveness thresholds varied markedly depending on which group the intervention belonged to: lifestyle-type interventions with a prevention objective had an incremental cost-effectiveness threshold of $2356, suggesting that such interventions need to be close to cost saving or dominant to be funded. For lifestyle-type interventions with a treatment objective, the threshold was much higher at $37,024. Lower down the tree, intervention attributes such as the level of patient contribution and the eligibility for government reimbursement influenced the likelihood of funding within groups of similar interventions. Comparison between our CART models and previously published results demonstrated concurrence with standard regression techniques while providing additional insights regarding the role of the funding environment and the structure of decision-maker preferences.",
keywords = "CART, cost-effectiveness, funding of health care",
author = "Chris Schilling and Duncan Mortimer and Kim Dalziel",
year = "2017",
month = "2",
doi = "10.1177/0272989X16638846",
language = "English",
volume = "37",
pages = "173--182",
journal = "Medical Decision Making",
issn = "0272-989X",
publisher = "SAGE Publications Ltd",
number = "2",

}

Using CART to identify thresholds and hierarchies in the determinants of funding decisions. / Schilling, Chris; Mortimer, Duncan; Dalziel, Kim.

In: Medical Decision Making, Vol. 37, No. 2, 02.2017, p. 173-182.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Using CART to identify thresholds and hierarchies in the determinants of funding decisions

AU - Schilling, Chris

AU - Mortimer, Duncan

AU - Dalziel, Kim

PY - 2017/2

Y1 - 2017/2

N2 - There is much interest in understanding decision-making processes that determine funding outcomes for health interventions. We use classification and regression trees (CART) to identify cost-effectiveness thresholds and hierarchies in the determinants of funding decisions. The hierarchical structure of CART is suited to analyzing complex conditional and nonlinear relationships. Our analysis uncovered hierarchies where interventions were grouped according to their type and objective. Cost-effectiveness thresholds varied markedly depending on which group the intervention belonged to: lifestyle-type interventions with a prevention objective had an incremental cost-effectiveness threshold of $2356, suggesting that such interventions need to be close to cost saving or dominant to be funded. For lifestyle-type interventions with a treatment objective, the threshold was much higher at $37,024. Lower down the tree, intervention attributes such as the level of patient contribution and the eligibility for government reimbursement influenced the likelihood of funding within groups of similar interventions. Comparison between our CART models and previously published results demonstrated concurrence with standard regression techniques while providing additional insights regarding the role of the funding environment and the structure of decision-maker preferences.

AB - There is much interest in understanding decision-making processes that determine funding outcomes for health interventions. We use classification and regression trees (CART) to identify cost-effectiveness thresholds and hierarchies in the determinants of funding decisions. The hierarchical structure of CART is suited to analyzing complex conditional and nonlinear relationships. Our analysis uncovered hierarchies where interventions were grouped according to their type and objective. Cost-effectiveness thresholds varied markedly depending on which group the intervention belonged to: lifestyle-type interventions with a prevention objective had an incremental cost-effectiveness threshold of $2356, suggesting that such interventions need to be close to cost saving or dominant to be funded. For lifestyle-type interventions with a treatment objective, the threshold was much higher at $37,024. Lower down the tree, intervention attributes such as the level of patient contribution and the eligibility for government reimbursement influenced the likelihood of funding within groups of similar interventions. Comparison between our CART models and previously published results demonstrated concurrence with standard regression techniques while providing additional insights regarding the role of the funding environment and the structure of decision-maker preferences.

KW - CART

KW - cost-effectiveness

KW - funding of health care

UR - https://www-scopus-com.ezproxy.lib.monash.edu.au/record/display.uri?eid=2-s2.0-85009782201&origin=resultslist&

U2 - 10.1177/0272989X16638846

DO - 10.1177/0272989X16638846

M3 - Article

VL - 37

SP - 173

EP - 182

JO - Medical Decision Making

JF - Medical Decision Making

SN - 0272-989X

IS - 2

ER -