BYU

Abstract by Zoe Gibbs

Personal Infomation


Presenter's Name

Zoe Gibbs

Co-Presenters

None

Degree Level

Undergraduate

Co-Authors

None

Abstract Infomation


Department

Statistics

Faculty Advisor

Brian Hartman

Title

Using Machine Learning to Predict High Cost Patients

Abstract

A small number of patients incur a disproportionate amount of total healthcare expenditures.  To reduce the risk of loss, actuaries would like to predict which policyholders are likely to be high cost (incur over $100,000 in medical expenses in one year).  With a dataset from a large insurance company that includes policyholder characteristics and health care costs in 2012 and 2013, we employ machine learning techniques to develop such a model.  Through extreme gradient boosting, we found that diagnosis count, risk adjustment score, and total costs in 2012 are excellent predictors of high cost patients.