Role of Markov Modeling Approaches to Understand the Impact of Infertility Treatments

Abstract

We are proposing to use Markov modeling type of analysis to understand data generated by treatments for infertility in women receiving ovarian stimulations. We describe the conceptual novelties, need for such an analysis, basics of the proposed methods, and theoretical constructions of various probabilities associated with practical level implementation of the Markov modeling procedures. This method can be adopted to infertility-related data visualizations whenever progression of outcome stages in infertility treatment is recorded. These methods if implemented should be able to enhance the understanding of treatment impacts of gonadotropins, clomiphene citrate, or an aromatase inhibitor at the beginning of treatment cycles of infertile women. This framework will be very useful for infertility treatment practitioners to compute the values of success rates of treatment for total population or population divided by demographic, clinical, and genetic factors. These methods can be continuously updated with newer data and translated into a mobile app to be used by clinical practitioners.

Keywords: infertility data; modeling; probability of conception.

Figure 1.

Schematic diagram for describing possible transitions within each state space for which Markov modeling is proposed. Each number within a circle from (A) to (D) indicates a state in the Markov chain whose description is given in the section on State-Spaces Constructions. Some of the women in a given state might remain in the same state within a short time period (eg, a woman who conceives remains pregnant for 40 weeks before delivery) or a woman in a given state might move to another state and return to the original state after some time (eg, a woman who has initiated a treatment might move to the state of ectopic pregnancy and then return back to a no-pregnancy state prior to initiation of another cycle of treatment).