Polypilot product mascot

Introducing PolyPilot:

Our AI-Powered Mentorship Program

Start your trial today

Learn More
Back to projects

Hereditary Disease Decision Making: A Game Theoretic Model

Project by Polygence alum Anirudh

Hereditary Disease Decision Making: A Game Theoretic Model

Project's result

A research paper showing a model that can be used to consider decisions regarding genetic testing.

They started it from zero. Are you ready to level up with us?


Genetic diseases affect around 200,000 people in the United States (Cleveland Clinic, 2021). These are the result of mutations passed down through families leaving a history of disease by inheritance. Several genetic testing kits have become popular in recent years, and have led to positive outcomes for those affected by specific conditions which can be identified and treated before becoming more problematic later in life (e.g. BRCA). However, the decision about whether or not to take a test is not always clear-cut due to financial and psychological implications. For this reason, I have created a model that aids in the decision-making process for someone considering a genetic test. My analysis assumes that patients start with an initial belief about harboring a genetic mutation based on their family history of the disease. As patients receive results for genetic tests, this belief changes. Besides the initial belief, the two other inputs into this analysis are test accuracies and insurance thresholds1. At each given test accuracy and insurance threshold, some patients will opt to take the genetic test, and some will not, depending on their initial beliefs. There is a breakpoint2 in initial beliefs in which the optimal choice switches from not taking the test to taking the test. As tests become more accurate, patients will become more confident in future health problems arising and more willing to pay for preventive procedures regardless of whether their health insurance will reimburse the costs. These dynamics are captured in the model discussed below.



Polygence mentor

PhD Doctor of Philosophy candidate


Computer Science, Quantitative


Economics, Machine Learning




Graduation Year


Project review

“Overall, I was surprised by how organized the process of organizing sessions was, and enjoyed how much the program kept you on track with scheduling and the like. ”

About my mentor

“My mentor was very helpful in guiding me through what needed to be done and informing me how and what I should try to accomplish each session, but leaving me to myself enough that I learned in my own time and did a lot of work on my own. ”