Changing Cycle Lengths in State-Transition Models: Challenges and Solutions

Jagpreet Chhatwal, Suren Jayasuriya, Elamin H. Elbasha

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

The choice of a cycle length in state-transition models should be determined by the frequency of clinical events and interventions. Sometimes there is need to decrease the cycle length of an existing state-transition model to reduce error in outcomes resulting from discretization of the underlying continuous-time phenomena or to increase the cycle length to gain computational efficiency. Cycle length conversion is also frequently required if a new state-transition model is built using observational data that have a different measurement interval than the model's cycle length. We show that a commonly used method of converting transition probabilities to different cycle lengths is incorrect and can provide imprecise estimates of model outcomes. We present an accurate approach that is based on finding the root of a transition probability matrix using eigendecomposition. We present underlying mathematical challenges of converting cycle length in state-transition models and provide numerical approximation methods when the eigendecomposition method fails. Several examples and analytical proofs show that our approach is more general and leads to more accurate estimates of model outcomes than the commonly used approach. MATLAB codes and a user-friendly online toolkit are made available for the implementation of the proposed methods.

Original languageEnglish (US)
Pages (from-to)952-964
Number of pages13
JournalMedical Decision Making
Volume36
Issue number8
DOIs
StatePublished - Nov 1 2016
Externally publishedYes

Keywords

  • cost-effectiveness analysis
  • decision analysis
  • global health
  • Markov models
  • mathematical models

ASJC Scopus subject areas

  • Health Policy

Cite this

Changing Cycle Lengths in State-Transition Models : Challenges and Solutions. / Chhatwal, Jagpreet; Jayasuriya, Suren; Elbasha, Elamin H.

In: Medical Decision Making, Vol. 36, No. 8, 01.11.2016, p. 952-964.

Research output: Contribution to journalArticle

Chhatwal, Jagpreet ; Jayasuriya, Suren ; Elbasha, Elamin H. / Changing Cycle Lengths in State-Transition Models : Challenges and Solutions. In: Medical Decision Making. 2016 ; Vol. 36, No. 8. pp. 952-964.
@article{bc4cac064fce48be9b6c9e946c21beed,
title = "Changing Cycle Lengths in State-Transition Models: Challenges and Solutions",
abstract = "The choice of a cycle length in state-transition models should be determined by the frequency of clinical events and interventions. Sometimes there is need to decrease the cycle length of an existing state-transition model to reduce error in outcomes resulting from discretization of the underlying continuous-time phenomena or to increase the cycle length to gain computational efficiency. Cycle length conversion is also frequently required if a new state-transition model is built using observational data that have a different measurement interval than the model's cycle length. We show that a commonly used method of converting transition probabilities to different cycle lengths is incorrect and can provide imprecise estimates of model outcomes. We present an accurate approach that is based on finding the root of a transition probability matrix using eigendecomposition. We present underlying mathematical challenges of converting cycle length in state-transition models and provide numerical approximation methods when the eigendecomposition method fails. Several examples and analytical proofs show that our approach is more general and leads to more accurate estimates of model outcomes than the commonly used approach. MATLAB codes and a user-friendly online toolkit are made available for the implementation of the proposed methods.",
keywords = "cost-effectiveness analysis, decision analysis, global health, Markov models, mathematical models",
author = "Jagpreet Chhatwal and Suren Jayasuriya and Elbasha, {Elamin H.}",
year = "2016",
month = "11",
day = "1",
doi = "10.1177/0272989X16656165",
language = "English (US)",
volume = "36",
pages = "952--964",
journal = "Medical Decision Making",
issn = "0272-989X",
publisher = "SAGE Publications Inc.",
number = "8",

}

TY - JOUR

T1 - Changing Cycle Lengths in State-Transition Models

T2 - Challenges and Solutions

AU - Chhatwal, Jagpreet

AU - Jayasuriya, Suren

AU - Elbasha, Elamin H.

PY - 2016/11/1

Y1 - 2016/11/1

N2 - The choice of a cycle length in state-transition models should be determined by the frequency of clinical events and interventions. Sometimes there is need to decrease the cycle length of an existing state-transition model to reduce error in outcomes resulting from discretization of the underlying continuous-time phenomena or to increase the cycle length to gain computational efficiency. Cycle length conversion is also frequently required if a new state-transition model is built using observational data that have a different measurement interval than the model's cycle length. We show that a commonly used method of converting transition probabilities to different cycle lengths is incorrect and can provide imprecise estimates of model outcomes. We present an accurate approach that is based on finding the root of a transition probability matrix using eigendecomposition. We present underlying mathematical challenges of converting cycle length in state-transition models and provide numerical approximation methods when the eigendecomposition method fails. Several examples and analytical proofs show that our approach is more general and leads to more accurate estimates of model outcomes than the commonly used approach. MATLAB codes and a user-friendly online toolkit are made available for the implementation of the proposed methods.

AB - The choice of a cycle length in state-transition models should be determined by the frequency of clinical events and interventions. Sometimes there is need to decrease the cycle length of an existing state-transition model to reduce error in outcomes resulting from discretization of the underlying continuous-time phenomena or to increase the cycle length to gain computational efficiency. Cycle length conversion is also frequently required if a new state-transition model is built using observational data that have a different measurement interval than the model's cycle length. We show that a commonly used method of converting transition probabilities to different cycle lengths is incorrect and can provide imprecise estimates of model outcomes. We present an accurate approach that is based on finding the root of a transition probability matrix using eigendecomposition. We present underlying mathematical challenges of converting cycle length in state-transition models and provide numerical approximation methods when the eigendecomposition method fails. Several examples and analytical proofs show that our approach is more general and leads to more accurate estimates of model outcomes than the commonly used approach. MATLAB codes and a user-friendly online toolkit are made available for the implementation of the proposed methods.

KW - cost-effectiveness analysis

KW - decision analysis

KW - global health

KW - Markov models

KW - mathematical models

UR - http://www.scopus.com/inward/record.url?scp=84989322133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84989322133&partnerID=8YFLogxK

U2 - 10.1177/0272989X16656165

DO - 10.1177/0272989X16656165

M3 - Article

C2 - 27369084

AN - SCOPUS:84989322133

VL - 36

SP - 952

EP - 964

JO - Medical Decision Making

JF - Medical Decision Making

SN - 0272-989X

IS - 8

ER -