Text and Data Mining to Investigate Expenditures on Prescribed Medicines

Overview

This Prescribed Medicines File from MEPS (Medical Expenditure Panel Survey) provides detailed information on household-reported prescribed medicines for a nationally representative sample of the civilian, non-institutionalized population of the United States and can be used to make estimates of prescribed medicine utilization and expenditures. For this study, the paper focused on the total cost, self-pay, Medicare cost, Medicaid cost and private insurance. It is the purpose of this study to determine the relationship between medication and patient condition, and to examine cost and patient condition in the analysis of these data. The paper uses Text Miner to examine combinations of medications used in relationship to patient therapeutics. In addition, the paper uses time series methods to investigate costs in relationship to patient therapeutics.