BACKGROUND: We present a case study in the use of Markov chain models of disease progression, with exponential regression to model the effects of covariates. METHODS: An exponential regression model was developed for a three-state Markov chain to model progression of cataracts in diabetic patients, with a view to estimation of absolute progression rates. Two methods of estimation were applied, a non-linear least squares approximation, and Markov Chain Monte Carlo (MCMC). RESULTS: Both methods gave estimated transition rates which can readily be transformed to absolute progression probabilities. Agreement was reasonable for most but not all of the parameters. CONCLUSIONS: The MCMC estimates had more conservative variance estimates.
BACKGROUND: We present a case study in the use of Markov chain models of disease progression, with exponential regression to model the effects of covariates. METHODS: An exponential regression model was developed for a three-state Markov chain to model progression of cataracts in diabeticpatients, with a view to estimation of absolute progression rates. Two methods of estimation were applied, a non-linear least squares approximation, and Markov Chain Monte Carlo (MCMC). RESULTS: Both methods gave estimated transition rates which can readily be transformed to absolute progression probabilities. Agreement was reasonable for most but not all of the parameters. CONCLUSIONS: The MCMC estimates had more conservative variance estimates.