Validation and comparison of models predicting survival following intracerebral hemorrhage

Abstract

Objective: To compare the performance of two previously reported logistic regression models using data independent from those data used to derive the models.

Design: Prospective.

Setting: Acute stroke unit of a tertiary care hospital.

Patients: One hundred twenty-nine patients with supratentorial intracerebral hemorrhage.

Measurements and main results: Model 1 contains the initial Glasgow Coma Scale score, hemorrhage size, and pulse pressure. The more complex model 2 includes, in addition to those three variables, the presence or absence of intraventricular hemorrhage and a term representing the interaction of intraventricular hemorrhage and Glasgow Coma Scale score. The areas under the receiver operating characteristic curves generated for each model were statistically indistinguishable.

Conclusions: Model 1 predicts 30-day patient status as well as the more complex model 2. Model 1 provides a valid, easy-to-use means of categorizing supratentorial intracerebral hemorrhage patients in terms of their probability of survival.