Comparison of the flexible parametric survival model and Cox model in estimating Markov transition probabilities using real-world data

Abstract

Background and objectiveMarkov micro-simulation models are being increasingly used in health economic evaluations. An important feature of the Markov micro-simulation model is its ability to consider transition probabilities of heterogeneous subgroups with different risk profiles. A survival analysis is generally performed to accurately estimate the transition probabilities associated with the risk profiles. This study aimed to apply a flexible parametric survival model (FPSM) to estimate individual transition probabilities.Materials and methodsThe data were obtained from a cohort study investigating ischemic stroke outcomes in Western China. In total, 585 subjects were included in the analysis. To explore the goodness of fit of the FPSM, we compared the estimated hazard ratios and baseline cumulative hazards, both of which are necessary to the calculate individual transition probabilities, and the Markov micro-simulation models constructed using the FPSM and Cox model to determine the validity of the two Markov micro-simulation models and cost-effectiveness results.ResultsThe flexible parametric proportional hazards model produced hazard ratio and baseline cumulative hazard estimates that were similar to those obtained using the Cox proportional hazards model. The simulated cumulative incidence of recurrent ischemic stroke and 5-years cost-effectiveness of Incremental cost-effectiveness Ratios (ICERs) were also similar using the two approaches. A discrepancy in the results was evident between the 5-years cost-effectiveness and the 10-years cost-effectiveness of ICERs, which were approximately 0.9 million (China Yuan) and 0.5 million (China Yuan), respectively.ConclusionsThe flexible parametric survival model represents a good approach for estimating individual transition probabilities for a Markov micro-simulation model.

Long term outcomes for elderly patients after emergency intensive care admission: A cohort study

“…The most parsimonious model which avoided overfitting was identified at five internal splines using the Bayesian information criterion method ( S2 Table ). Estimates from the flexible parametric model were similar to that of a Cox regression model (<5% difference in coefficients) [ 24 ]. Nomograms for possible prognostics factors associated with survival were therefore produced from the output from the Cox-regression model using R V.3.5.1 (R Development Core Team, Vienna, Austria).…”

Performance evaluation of survival regression models in analysing Swedish dental implant complication data with frailty

“…The alternative, traditional survival regression models, divided into parametric (Poisson, Weibull), semiparametric (Cox), and nonparametric (Kaplan–Meier) have distinct disadvantages that could make them unsuitable to correctly predict survival outcomes [ 1 , 9 ]. For instance, the Kaplan-Meier model does not accommodate covariates, hence its utilization is limited [ 1 , 5 ].…”

“…Further, its distribution-free assumption is often violated in long-term studies. In either case, many of the subjects may not have experienced the event of interest and, thus, survival and cumulative hazard functions are incomplete and cannot be extrapolated in the CPH [ 1 ]. The CPH models assume a constant hazard, an assumption that is also frequently violated [ 14 , 15 ].…”

“…Parametric models, such as the exponential and Weibull models [ 1 ], attempted to overcome some of the shortcomings of the CPH model by producing smooth predictions by assuming a functional form of the hazard [ 1 , 17 ] and directly estimating the absolute and relative effects [ 14 ]. The models can be used to estimate the smooth cumulative hazard functions and hazard ratios of risk factors and extrapolate survival and cumulative functions [ 1 ]. Nonetheless, the models assume that the survival and hazard functions have a specific distribution which is often too structured and sometimes unrealistic for use with real data [ 9 , 10 ].…”

“…While the disadvantages of non-parametric models can be overcome by the use of stratification, the number of factors used for such stratification may be limited [ 1 ]. Another way of alleviating the challenges of the CPH is to use a sufficiently large sample size and extensive study duration [ 20 ].…”