Validation of a Retrospective Computing Model for Mortality Risk in the Intensive Care Unit

• Published in: Mayo Clinic proceedings. Innovations, quality & outcomes Vol. 4; no. 5; pp. 575 - 582
• Main Authors: Tan, Eugene M., Kashyap, Rahul, Olson, Ian C., O’Horo, John C.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Inc 01.10.2020; Elsevier
• Subjects: Original; AUROC; ICU; IMRM; APACHE; APACHE, Acute Physiology and Chronic Health Evaluation; AUROC, area under the receiver operating characteristic curve; ICU, intensive care unit; IMRM, Intensive Care Unit Mortality Risk Model
• ISSN: 2542-4548; 2542-4548
• DOI: 10.1016/j.mayocpiqo.2020.09.001

To compare the predictive performance of Epic Systems Corporation’s proprietary intensive care unit (ICU) mortality risk model (IMRM) with that of the Acute Physiology and Chronic Health Evaluation (APACHE) IV score. This is a retrospective cohort study of patients treated from January 1, 2008, through January 1, 2018. This single-center study was performed at Mayo Clinic (Rochester, MN), a tertiary care teaching and referral center. The primary outcome was death in the ICU. Discrimination of each risk model for hospital mortality was assessed by comparing area under the receiver operating characteristic curve (AUROC). The cohort mostly comprised older patients (median age, 64 years) and men (56.7%). The mortality rate of the cohort was 3.5% (2251 of 63,775 patients). The AUROC for mortality prediction was 89.7% (95% CI, 89.5% to 89.9%) for the IMRM, which was significantly greater than the AUROC of 88.2% (95% CI, 87.9% to 88.4%) for APACHE IV (P<.001). The IMRM was superior to the commonly used APACHE IV score and may be easily integrated into electronic health records at any hospital using Epic software.