Song JY, et al. - In order to appraise the external validity of a carbapenem-resistant Enterobacteriaceae colonization risk prediction model (CREP-model), researchers conducted this retrospective cohort study of 414 patients admitted to the intensive care units of a tertiary hospital. CREP-model showed good calibration and excellent discrimination in the validation sample. Using the CREP-model at a threshold probability of 0.10 or above, they noted the net benefit of > 0, reducing at least 54 unnecessary preventive interventions per 100 patients. Given a good performance of the CREP-model, they recommend its application to CRE high-risk patients who need preemptive isolation in hospitals without an active surveillance program.