window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); gtag('config', 'UA-115625534-1');
Azra Bihorac, Tezcan Ozrazgat-Baslanti, Ashkan Ebadi, Amir Motaei, Mohcine Madkour, Panagote M Pardalos, Gloria Lipori, William R Hogan, Philip A Efron, Frederick Moore, Lyle L Moldawer, Daisy Zhe Wang, Charles E Hobson, Parisa Rashidi, Xiaolin Li, Petar Momcilovic
Annals of Surgery
Publication year: 2018

In a single-center cohort of 51,457 surgical patients undergoing major inpatient surgery, we have developed and validated an automated analytics framework for a preoperative risk algorithm (MySurgeryRisk) that uses existing clinical data in electronic health records to forecast patient-level probabilistic risk scores for 8 major postoperative complications (acute kidney injury, sepsis, venous thromboembolism, intensive care unit admission >48 hours, mechanical ventilation >48 hours, wound, neurologic, and cardiovascular complications) and death up to 24 months after surgery. We used the area under the receiver characteristic curve (AUC) and predictiveness curves to evaluate model performance.

Leave a Reply