Expenditure variations analysis using residuals for identifying high health care utilizers in a state Medicaid program

Chengliang Yang,Sanjay Ranka,Elizabeth Shenkman,Chris Delcher

doi:10.1186/s12911-019-0870-4

Chengliang Yang, Sanjay Ranka + Show 2 more

Open Access

https://doi.org/10.1186/s12911-019-0870-4

Copy DOI

Abstract

BackgroundHigh utilizers receive great attention in health care research because they have a largely disproportionate spending. Existing analyses usually identify high utilizers with an empirical threshold on the number of health care visits or associated expenditures. However, such count-and-cost based criteria might not be best for identifying impactable high utilizers.MethodsWe propose an approach to identify impactable high utilizers using residuals from regression-based health care utilization risk adjustment models to analyze the variations in health care expenditures. We develop linear and tree-based models to best adjust per-member per-month health care cost by clinical and socioeconomic risk factors using a large administrative claims dataset from a state public insurance program.ResultsThe risk adjustment models identify a group of patients with high residuals whose demographics and categorization of comorbidities are similar to other patients but who have a significant amount of unexplained health care utilization. Deeper analysis of the essential hypertension cohort and chronic kidney disease cohort shows these variations in expenditures could be within individual ICD-9-CM codes and from different mixtures of ICD-9-CM codes. Additionally, correlation analysis with 3M™ Potentially Preventable Events (PPE) software shows that a portion of this utilization may be preventable. In addition, the high utilizers persist from year to year.ConclusionsAfter risk adjustment, patients with higher than expected expenditures (high residuals) are associated with more potentially preventable events. These residuals are temporally consistent and hence may be useful in identifying and intervening impactable high utilizers.

Highlights

High utilizers receive great attention in health care research because they have a largely disproportionate spending
We look at the characteristics and temporal consistency of high utilizers identified by the models
We present the stratified risk adjustment model where we cross-validate the preventability of identified high utilization with 3MTM Potentially Preventable Events (PPE) software

Summary

Introduction

High utilizers receive great attention in health care research because they have a largely disproportionate spending. The Agency for Healthcare Research and Quality (AHRQ) reports that in 2012, the top 10% of the health careutilizing population accounted for 66% of overall health care expenditures in the United States [1] This highly disproportionate spending pattern frequently is interpreted as a sign of inefficient health care delivery and partially associated with avoidable, preventable or otherwise unnecessary health care events. Existing studies find that historic utilization is indicative for future utilization [12] While using such data-driven methods may be a relatively straightforward starting point for Medicaid programs with limited analytic resources, the approach is blunt and may fail to identify patient populations with health conditions most responsive to prevention and, by extension, cost reduction. Patients with serious conditions, such as cancer or traumatic injuries, may require expensive medical treatments that seem excessive as financial data points but that are medically appropriate and necessary

Objectives

Methods

Results

Discussion

Conclusion