Practical Limits of Preoperative Registry-based Risk Prediction After Bariatric Surgery: A National MBSAQIP Temporal Validation
Archives of Iranian Medicine · 01.03.2026 · 29 (3) · 148-155
DOI: 10.34172/aim.36838 ↗Kurz gefasst
Fachartikel in der Zeitschrift Archives of Iranian Medicine, online erschienen am 01.03.2026. Verfasst von Amir Monshizadeh und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Preoperative registry variables are widely used for bariatric risk counseling; however, the ceiling of patient-level prediction using routinely collected data remains uncertain.
Objective
To benchmark the performance of logistic regression versus gradient-boosted decision trees for prediction of 30-day outcomes after bariatric surgery using contemporary MBSAQIP data and to evaluate achievable discrimination, calibration, and clinical utility when models are restricted to standard preoperative registry variables.
Methods
We analyzed adults undergoing bariatric surgery in the 2020–2023 MBSAQIP Participant Use Files. Models were developed using 2020–2022 data and temporally validated in an independent 2023 cohort. Using 30 fixed preoperative predictors, we assessed discrimination (AUROC), calibration (Brier score; calibration intercept and slope), and decision-curve utility across 1–10% risk thresholds. Performance was examined by procedure type and procedural intent.
Results
Among 702,614 patients, several outcomes were rare (leak 0.2%, mortality 0.03%). Discrimination was modest across outcomes and subgroups (typical AUROC 0.58–0.62), and XGBoost did not consistently outperform logistic regression. For sleeve gastrectomy readmission, both models demonstrated acceptable population-level calibration (Brier 0.022; slopes near 1), but net clinical benefit was limited. For rare outcomes such as leak, calibration was poor, and no meaningful net benefit was observed.
Conclusion
Using standard preoperative MBSAQIP variables, both logistic regression and XGBoost provide limited individual-level prediction of 30-day outcomes, particularly rare events. Clinically actionable improvement will likely require richer perioperative inputs rather than increased algorithmic complexity alone.
Zitieren
APA
Monshizadeh, A., Rezvani, M., Najjari, K., Nourzad, S. H. H., & Latif, A. H. (2026). Practical Limits of Preoperative Registry-based Risk Prediction After Bariatric Surgery: A National MBSAQIP Temporal Validation. Archives of Iranian Medicine, 29(3), 148-155. https://doi.org/10.34172/aim.36838
Vancouver
Monshizadeh A, Rezvani M, Najjari K, Nourzad SHH, Latif AH. Practical Limits of Preoperative Registry-based Risk Prediction After Bariatric Surgery: A National MBSAQIP Temporal Validation. Archives of Iranian Medicine. 2026;29(3):148-155. doi:10.34172/aim.36838
BibTeX
@article{Monshizadeh2026,
author = {Monshizadeh, Amir and Rezvani, Masoud and Najjari, Khosrow and Nourzad, Seyed Hossein Hosseini and Latif, Amir Hossein},
title = {Practical Limits of Preoperative Registry-based Risk Prediction After Bariatric Surgery: A National MBSAQIP Temporal Validation},
journal = {Archives of Iranian Medicine},
year = {2026},
volume = {29},
number = {3},
pages = {148--155},
doi = {10.34172/aim.36838}
}
EUVIMED