To the Editor. —
In a recent article, Kruse and colleagues1 suggest that the prognostic predictions made by the Acute Physiology and Chronic Health Evaluation II (APACHE II) are no better than those of physicians in training and that therefore this model has little potential to improve clinical decision making for individual patients. They evaluated predictions using ROC curve analysis, which is an excellent method to assess ability to discriminate among patients with different outcomes.2 However, they did not assess the reliability of the predictions, ie, the agreement between predicted and actual outcome rates. Reliability may not be a useful criterion for evaluating diagnostic tests, since it depends on pretest disease probability and the cutoff for test positivity. However, unless one can meaningfully define pretest disease probability and cutoff criteria for the mental processes people use to make judgments, reliability would seem to be an appropriate paradigm for
Poses RM. Who Will Die in the ICU? APACHE II, ROC Curve Analysis, and, of Course, Cleone. JAMA. 1989;261(9):1279. doi:10.1001/jama.1989.03420090043023
Coronavirus Resource Center
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: