![Sample our Health and Social Care journals, sign in here to start your FREE access for 14 days]({"type":"image" , "src" : "/sda/5938/TOC-Subject-Sample-2021-Health-Social-Care.jpg"})
Abstract
Objective
Although Markov cohort models represent one of the most common forms of decision-analytic models used in health care decision-making, correct implementation of such models requires reliable estimation of transition probabilities. This study sought to identify consensus statements or guidelines that detail how such transition probability matrices should be estimated.
Methods
A literature review was performed to identify relevant publications in the following databases: Medline, Embase, the Cochrane Library, and PubMed. Electronic searches were supplemented by manual-searches of health technology assessment (HTA) websites in Australia, Belgium, Canada, France, Germany, Ireland, Norway, Portugal, Sweden, and the UK. One reviewer assessed studies for eligibility.
Results
Of the 1,931 citations identified in the electronic searches, no studies met the inclusion criteria for full-text review, and no guidelines on transition probabilities in Markov models were identified. Manual-searching of the websites of HTA agencies identified ten guidelines on economic evaluations (Australia, Belgium, Canada, France, Germany, Ireland, Norway, Portugal, Sweden, and UK). All identified guidelines provided general guidance on how to develop economic models, but none provided guidance on the calculation of transition probabilities. One relevant publication was identified following review of the reference lists of HTA agency guidelines: the International Society for Pharmacoeconomics and Outcomes Research taskforce guidance. This provided limited guidance on the use of rates and probabilities.
Conclusions
There is limited formal guidance available on the estimation of transition probabilities for use in decision-analytic models. Given the increasing importance of cost-effectiveness analysis in the decision-making processes of HTA bodies and other medical decision-makers, there is a need for additional guidance to inform a more consistent approach to decision-analytic modeling. Further research should be done to develop more detailed guidelines on the estimation of transition probabilities.
Supplementary materials
Figure S1 Search strategy.
Table S1 Potentially relevant publications identified via the electronic searches
References
- AalenOOBorganOFekjaerHCovariate adjustment of event histories estimated from Markov chains: the additive approach.[Erratum appears in Biometrics. 2003 Jun;59(2):452–453]Biometrics2001574993100111764270
- AlamMFBartonPMonahanMInvestigating the impact of structural changes in a NICE single technology appraisal cost-effectiveness modelValue Health2015187A696
- Alarid-EscuderoFEnnsEPeralta-TorresYEMaclehoseRKuntzKMCalibration of piecewise Markov models using a change-point analysis through an iterative convex optimization algorithmValue Health2015187A814
- AlbertPSWaclawiwMAA two-state Markov chain for heterogeneous transitional data: a quasi-likelihood approachStat Med19981713148114939695193
- AllignolABeyersmannJGerdsTLatoucheAA competing risks approach for nonparametric estimation of transition probabilities in a non-Markov illness-death modelLifetime Data Anal201420449551323807694
- AndersenPKPohar PermeMInference for outcome probabilities in multi-state modelsLifetime Data Anal200814440543118791824
- BlackWCNeaseRFJrWelchHGDetermining transition probabilities from mortality rates and autopsy findingsMed Decis Making199717187938994155
- BorganOEstimation of covariate-dependent Markov transition probabilities from nested case-control dataStat Methods Med Res200211218320212040696
- BorganOErratum: Estimation of covariate-dependent Markov transition probabilities from nested case-control dataStat Methods Med Res2003122124
- BoruvkaACookRJSieve estimation in a Markov illness-death process under dual censoringBiostatistics201617235036326598559
- CohenJEOn estimating the equilibrium and transition probabilities of a finite-state Markov chain from the same dataBiometrics19682411851875642403
- CooperNJSuttonAJAbramsKRTurnerDWailooAComprehensive decision analytical modeling in economic evaluation: a Bayesian approachHealth Econ200413320322614981647
- CraigBASendiPPEstimation of the transition matrix of a discrete-time Markov chainHealth Econ2002111334211788980
- DabrowskaDMHoWTConfidence bands for comparison of transition probabilities in a Markov chain modelLifetime Data Anal20006152110763558
- DebosscherAUnifying stochastic Markov process and its transition probability density functionPhys Rev A19914412792979389905942
- DentonFTSpencerBGModeling the age dynamics of chronic health conditions: life-table-consistent transition probabilities and their applicationCan J Aging201534217619325917602
- DiabyVAdunlinGMonteroAJSurvival modeling for the estimation of transition probabilities in model-based economic evaluations in the absence of individual patient data: a tutorialPharmacoeconomics201432210110824338265
- GaveauBSchulmanLSMultiple phases in stochastic dynamics: geometry and probabilitiesPhys Rev E Stat Nonlin Soft Matter Phys2006733 Pt 203612416605615
- GuptaSBhattacharyyaSSonathiVBakuliAMathurAKLeteneuxCTransition probability estimation using repeated sampling from a fitted mixed modelValue Health2014177A326
- GuptaSChattopadhyaySGundaPGeneralized implementation of Em algorithm for estimation of transition probability matrixValue Health2015187A694
- HawkinsDLHanCPEstimating transition probabilities from aggregate samples plus partial transition dataBiometrics200056384885410985225
- HealyBCEnglerDModeling disease-state transition heterogeneity through Bayesian variable selectionStat Med20092891353136819206077
- HuangGHIntegrated analysis of incidence, progression, regression and disappearance probabilitiesBMC Med Res Methodol200884018577235
- IacobelliSCarstensenBMultiple time scales in multi-state modelsStat Med201332305315532724027131
- KassteeleJvHoogenveenRTEngelfrietPMBaalPHBoshuizenHCEstimating net transition probabilities from cross-sectional data with application to risk factors in chronic disease modelingStat Med201231653354322139860
- KaushikACellerBGAmbikairajahEA methodology to monitor the changing trends in health status of an elderly person by developing a Markov modelConf Proc IEEE Eng Med Biol Soc200522171217417282661
- LiZPackSAn application of Markov models in estimating transition probabilities for postmenopausal women with osteoporosisDrug Info J20043814146
- LimwattananonCLimwattananonSConstructing a state-transition model for an economic evaluation of cancer treatmentsJ Med Assoc Thai201497Suppl 5S108S112
- McCombsJSPharmacoeconomics: what is it and where is it going?Am J Hypertens1998118 Pt 2112S119S discussion 135S–137S9717852
- MeidaniHGhanemRUncertainty quantification for Markov chain modelsChaos201222404310223278037
- Meira-MachadoLde Una-AlvarezJCadarso-SuarezCNonparametric estimation of transition probabilities in a non-Markov illness-death modelLifetime Data Anal200612332534416917736
- Meira-MachadoLde Una-AlvarezJCadarso-SuarezCAndersenPKMulti-state models for the analysis of time-to-event dataStat Methods Med Res200918219522218562394
- MillerDKHomanSMDetermining transition probabilities: confusion and suggestionsMed Decis Making199414152588152357
- MilneRJPharmacoeconomic models in disease management. A guide for the novice or the perplexedDis Manag Health Outcomes199843119134
- MoussaMAHathoutHKasraouiRSalehAKMeasuring the change in contingency tables using Markov models application to the effect of preceding conception on the next oneMethods Inf Med198221131337057716
- MuenzLRRubinsteinLVMarkov models for covariate dependence of binary sequencesBiometrics1985411911014005390
- NagylakiTThe distribution of sojourn times in finite absorbing Markov chainsMath Biosci1976281–26972
- NeineMBriquetBMokdadCEVataireALAballeaSBayesian calibration method to estimate transition probabilities for a Markov model based on a continuous outcome measure: application in Parkinson’s diseaseValue Health2013167A325A326
- NgETCookRJModeling two-state disease processes with random effectsLifetime Data Anal1997343153359503879
- O’MahonyJFNewallATvan RosmalenJDealing with time in health economic evaluation: methodological issues and recommendations for practicePharmacoeconomics201533121255126826105525
- OppeMAlMRutten-van MolkenMComparing methods of data synthesis: re-estimating parameters of an existing probabilistic cost-effectiveness modelPharmacoeconomics201129323925021142288
- PaesATde LimaACA SAS macro for estimating transition probabilities in semiparametric models for recurrent eventsComput Methods Programs Biomed2004751596515158048
- PutterHFioccoMGekusRBTutorial in biostatistics: competing risk and multi-state modelsStat Med200726112389243017031868
- RegnierEDShechterSMState-space size considerations for disease-progression modelsStat Med201332223862388023609629
- Rodriguez-GirondoMde Una-AlvarezJA nonparametric test for Markovianity in the illness-death modelStat Med201231304416442722975898
- Rodriguez-GirondoMde Una-AlvarezJTesting Markovianity in the three-state progressive model via future-past associationBiom J201254216318022522376
- Rodriguez-GirondoMUna-AlvarezJdMethods for testing the Markov condition in the illness-death model: a comparative studyStat Med201635203549356226990971
- RosychukRJShengXStuberJLComparison of variance estimation approaches in a two-state Markov model for longitudinal data with misclassificationStat Med200625111906192116220512
- RosychukRJThompsonMEBias correction of two-state latent Markov process parameter estimates under misclassificationStat Med200322122035205512802821
- Saint-PierrePCombescureCDauresJPGodardPThe analysis of asthma control under a Markov assumption with use of covariatesStat Med200322243755377014673936
- SpitoniCVerduijnMPutterHEstimation and asymptotic theory for transition probabilities in Markov renewal multi-state modelsInt J Biostat2012812322944722
- TattarPNVamanHJTesting transition probability matrix of a multi-state model with censored dataLifetime Data Anal200814221623017874296
- TattarPNVamanHJThe k-sample problem in a multi-state model and testing transition probability matricesLifetime Data Anal201420338740323722306
- TitmanACTransition probability estimates for non-Markov multi-state modelsBiometrics20157141034104126148652
- TsangKPWangBCMGarrisonLEstimating Markov chain transition matrices in limited data samples: A Monte Carlo experimentValue Health2012154A164A165
- WeltonNJAdesAEEstimation of Markov chain transition probabilities and rates from fully and partially observed data: uncertainty propagation, evidence synthesis, and model calibrationMed Decis Making200525663364516282214
Acknowledgments
We would like to thank Richard Grieve for the critical review of this manuscript and Dave Fox for developing the search strategy. This study was sponsored by Takeda Pharmaceuticals International AG. The abstract of this article was presented as a poster at the International Society for Pharmacoeconomics and Outcomes Research 19th Annual European Congress in 2016. The poster’s abstract has also been published.Citation16
Disclosure
HCS is a permanent employee of Takeda Pharmaceuticals International AG. EO, KKC, EH, and DT have received consulting fees from Takeda Pharmaceuticals International AG. The authors report no other conflicts of interest in this work.