Key result
AI outperforms traditional models in predicting bariatric surgery complications but rarely exceeds 0.8 AUROC.
Why the study?
Machine learning and artificial intelligence models have the potential to outperform traditional predictive tools in forecasting postoperative complications after metabolic bariatric surgery, aiding decision making and improving patient selection.
Does the application of machine learning and artificial intelligence algorithms improve the prediction of postoperative complications in individuals living with obesity who have undergone metabolic bariatric surgery?
Systematic Review
Does the application of machine learning and artificial intelligence algorithms improve the prediction of postoperative complications in individuals living with obesity who have undergone metabolic bariatric surgery?
While AI and ML approaches generally outperform traditional predictive models in forecasting postoperative complications following metabolic bariatric surgery, few algorithms demonstrate clinically significant performance, highlighting the need for more rigorous methodologies.
AI models rarely reach clinically useful accuracy for post-MBS complications; leaves open the need for rigorous validation before adoption.
Background: Machine learning (ML) and other applications of artificial intelligence (AI) are revolutionizing medicine, particularly in the field of surgery. These models have the potential to outperform traditional predictive tools, aiding clinicians in decision making and enhancing operative safety through improved patient selection. Methods: A systematic search was conducted across PubMed/MEDLINE and Google Scholar, guided by the preferred reporting items for systematic reviews and meta-analyses (PRISMA) statement, to identify studies employing ML and AI algorithms to predict postoperative complications following metabolic bariatric surgery (MBS). The search included primary studies published in English up to November 2024. The area under the receiver operating characteristic curve (AUROC) was used as a surrogate metric for algorithm performance, with values exceeding 0.8 considered clinically significant; however, studies were not excluded based on AUROC thresholds. Results: The search identified 23 studies meeting the inclusion criteria. These were categorized into seven domains: general complications (8 studies, 34.8%), readmissions after MBS (4 studies, 17.4%), hemorrhage (1 study, 4.3%), leaks (1 study, 4.3%), venous thromboembolism (3 studies, 13.0%), nutritional deficiencies (4 studies, 17.4%), and miscellaneous complications such as gastroesophageal reflux disease, gallbladder disease, and major adverse cardiovascular events (MACE) (3 studies, 13.0%). The studies spanned from 2007 to 2024, with 87.0% (20/23) published in or after 2019. In total, 87 AI/ML algorithms were analyzed. While several studies reported AUROC values exceeding 0.7, the highest achieved was 0.94. However, most studies exhibited methodological limitations, including a lack of external validation and inadequate handling of imbalanced datasets, where complication events were markedly fewer than non-events. Conclusions: While AI and ML approaches generally outperform traditional predictive models in forecasting postoperative complications following MBS, few algorithms demonstrated clinically significant performance with AUROC values above 0.8. Future research should adopt more rigorous methodologies and implement strategies to address imbalanced datasets, ensuring broader clinical applicability of AI/ML tools.
No takes yet. Share an insight, caveat, or question.
Pantelis et al. (2025) conducted a systematic review in Obesity requiring metabolic bariatric surgery. Machine learning and artificial intelligence algorithms vs. Conventional predictive models was evaluated on Predictive performance (AUROC) for postoperative complications. Machine learning and artificial intelligence algorithms generally outperformed traditional predictive models in forecasting postoperative complications following metabolic bariatric surgery, though few achieved clinically significant AUROC values above 0.8.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: