Severity of Illness Measures Derived From the Uniform Clinical Data Set (UCDSS)

Abstract

The Health Care Financing Administration (HCFA) plans to use the Uniform Clinical Data Set System (UCDSS) to collect data on hospitalized Medicare patients. This study examined the value of UCDSS data for creating severity of illness measures. UCDSS data were obtained from a study hospital and from a national data set for patients with pneumonia (n = 528) and stroke (n = 565). Models to predict length of stay or an adverse event were derived for each condition using HCFA claims data alone, UCDSS data alone, and UCDSS data supplemented with additional information also abstracted from charts. The models were derived from one set of patients and validated on another. The R2 for predicting length of stay in the validation data for the UCDSS model was 0.29 for pneumonia and 0.19 for stroke compared to R2 values from the claims model of 0.09 for stroke and 0.06 for pneumonia. UCDSS models also were better than claims models for predicting adverse events. The best UCDSS models included International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes and other information requiring clinical judgment, and were improved by adding more information on patient functional status. Some findings were more strongly associated with outcome for the study hospital than for the national data. These results suggest that UCDSS models will predict outcome much better than the claims based models currently used by HCFA for the analysis of hospitalization-related mortality; more functional status information should be added to UCDSS; and despite an extensive objective database, the most predictive UCDSS models require clinician-assigned diagnostic codes.