Multivariate Markov chain analysis of the probability of pregnancy in infertile couples undergoing assisted reproduction

Abstract

Background: Estimating the probability of pregnancy leading to delivery and the influence of clinical factors on that probability is of fundamental importance in the treatment counselling of infertile couples. A variety of statistical techniques have been used to analyse fertility data, many borrowed from survival analysis.

Methods and results: We propose an alternative method of analysis which is based on a discrete time Markov chain approach, with states 'pregnancy (leading to a delivery)', 'not pregnant', and 'censored' and in which the transition probabilities are dependent both on the clinical characteristics of the patient and the treatment given.

Conclusions: We believe that the method of analysis presented here may be preferable to standard analyses in that it better reflects the clinical situation, it is a truly discrete time analysis applied to a discrete time situation, it explicitly models the censoring process (a process which in itself provides information of interest to the physician) and can be readily extended to a variety of clinical situations.