PREDICTING INPATIENT COSTS WITH ADMITTING CLINICAL-DATA

Hospital cost-containment programs should themselves be cost-effective , targeting high-cost physicians (which requires adjusting for case mi x) and patients (which requires early identification). In this study, clinical data available within 24 hours of admission from an electroni c medical record system were used to develop statistical models to pre dict hospital costs. In this retrospective analysis of clinical data a nd diagnosis-related groups (DRGs), study subjects were 2,355 patients admitted for at least 1 day to the medicine service at an urban teach ing hospital with sophisticated electronic medical records. Of these 2 ,355 patients, 1,663 (71%) had one of the 41 most common DRGs. Predict ive models were derived on a random subset of two thirds of the patien ts and were validated on the remaining third. The following patient da ta were obtained: admission and prior diagnostic test results, diagnos es, vital signs; demographic data; prior inpatient and outpatient visi ts; tests and treatments ordered within 24 hours of admission (discret ionary data); DRGs; and total inpatient costs (estimated from charges) . Diagnosis-related groups explained 24% of the variance in total cost s in the derivation patient set and 16% in the validation set. When on ly nondiscretionary data were used, the models retained only clinical laboratory results and prior diagnoses, explaining 20% of the derivati on set variance in total costs and 16% in the validation set. Adding D RGs increased the variance explained in the derivation set to 34%, but decreased to 24% in the validation set. Adding discretionary data sub stantially increased the explained variance in the derivation and vali dation patient sets. The models' median predicted costs underestimated true costs by 10% to 13%, with the lowest error in the models using a ll types of variables. Clinical data gathered during routine clinical care can be used to adjust for case mix and identify high-cost patient s early in their hospital stays, when they could be targeted by cost-c ontainment interventions.