Predicting Elderly at Risk of Increased Future Healthcare Use: How Much Does Diagnostic Information Add to Prior Utilization?

We determined whether case-mix information from administrative data can identify those likely to be high users of healthcare in the following year. An individual's healthcare utilization equaled the number of days (between 1 and 365) during the year on which an individual received inpatient or outpatient services. A binary outcome was defined as using 92 days or more (i.e., being in the top 2%) in year two. We included case-mix data in the models from two risk adjustment systems, Adjusted Diagnostic Groups (ADGs) from Adjusted Clinical Groups and Hierarchical Condition Categories (HCCs) from Diagnostic Cost Groups. We examined three types of logistic regression models: (1) prior use models (year one utilization plus age and sex), (2) diagnostic models (HCCs and ADGs as dummy variables plus age and sex), and (3) combined models (prior use plus diagnostic models). For the models with the best c-statistics (i.e., area under the receiver operating characteristic (ROC) curve), we compared ROC curve plots. We also fit linear regression models and compared their sensitivity and specificity to the logistic models. Although diagnostic and prior use models performed comparably, the models with the best ROC curves in predicting high users of healthcare combined prior use and diagnostic information. Logistic and linear regression models discriminated between cases similarly. While prior utilization has traditionally been used to predict future healthcare use, we found that case-mix information may be as important as prior use in identifying those who may be the highest users of healthcare in the future. [PUBLICATION ABSTRACT]