• Ben Li, Badr Aljabri, Raj Verma, Derek Beaton, Naomi Eisenberg, Douglas S Lee, Duminda N Wijeysundera, Thomas L Forbes, Ori D Rotstein, Charles de Mestral, Muhammad Mamdani, Graham Roche-Nagle, and Mohammed Al-Omran.
• Department of Surgery, University of Toronto, Toronto, Ontario, Canada.
• Br J Surg. 2023 Nov 9; 110 (12): 184018491840-1849.

BackgroundEndovascular aneurysm repair (EVAR) for abdominal aortic aneurysm (AAA) carries important perioperative risks; however, there are no widely used outcome prediction tools. The aim of this study was to apply machine learning (ML) to develop automated algorithms that predict 1-year mortality following EVAR.MethodsThe Vascular Quality Initiative database was used to identify patients who underwent elective EVAR for infrarenal AAA between 2003 and 2023. Input features included 47 preoperative demographic/clinical variables. The primary outcome was 1-year all-cause mortality. Data were split into training (70 per cent) and test (30 per cent) sets. Using 10-fold cross-validation, 6 ML models were trained using preoperative features with logistic regression as the baseline comparator. The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was evaluated with calibration plot and Brier score.ResultsSome 63 655 patients were included. One-year mortality occurred in 3122 (4.9 per cent) patients. The best performing prediction model for 1-year mortality was XGBoost, achieving an AUROC (95 per cent c.i.) of 0.96 (0.95-0.97). Comparatively, logistic regression had an AUROC (95 per cent c.i.) of 0.69 (0.68-0.71). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.04. The top 3 predictive features in the algorithm were 1) unfit for open AAA repair, 2) functional status, and 3) preoperative dialysis.ConclusionsIn this data set, machine learning was able to predict 1-year mortality following EVAR using preoperative data and outperformed standard logistic regression models.© The Author(s) 2023. Published by Oxford University Press on behalf of BJS Society Ltd. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

20 keywords...

hide…