Exploring Medicare Costs using Machine Learning

Document Type

Capstone

Lead Author Type

MBI Masters Student

Advisors

Dr. Guenter Tusch, tuschg@gvsu.edu

Embargo Period

5-17-2016

Abstract

As various forms of technology become more ubiquitous in the field of health care, an enormous amount of data is being collected in hope of making new scientific discoveries and reforming the way we understand health care as a society. Specifically, data mining has opened up a portal to discovery and comprehension of otherwise meaningless information. Preprocessing and cleaning techniques, advanced machine learning algorithms, and data visualization tools can be of extraordinary use when trying to make sense of the vast amount of health information at our fingertips. One area of health care that is always undergoing reform and debate is Medicare. I decided to analyze inpatient Medicare coverage data in R for the years 2011 through 2013 to get a better idea of how Medicare dollars are being spent in recent years, how they compare to past spending rates, and what future rates may look like. I was able to determine that among the medical procedures that receive the most Medicare coverage, the top causes of death among the elderly were not included. Many other factors contribute to Medicare costs and were not explored during my research, but the data that I was able to analyze using data mining techniques provides a great deal of insight into an area of much discussion and controversy.

This document is currently not available here.

Share

COinS