This is the authors' abstract. We don't add key points for this paper.
Purpose of Review Artificial intelligence (AI) particularly machine learning (ML) are increasingly used to predict perioperative risk in patients undergoing major cancer surgery. This narrative review aims to orient perioperative clinicians to contemporary AI-based predictive modelling, critically appraise the current evidence, and examine how these tools can be integrated into clinical decision-making within a Learning Health System framework. Recent Findings Recent studies show promise for AI-based prediction of perioperative outcomes compared with traditional tools in selected settings. However, performance gains are variable. Many models lack explainability, external validation, calibration assessment, or evidence of real-world clinical impact. Summary AI-based predictive models show promise for perioperative risk stratification in cancer surgery, but require external validation, interpretability, and links to actionable clinical pathways to be rigorously established. Future research should prioritise prospective evaluation, equity, workflow integration, and implementation science to translate predictive accuracy into meaningful clinical benefit.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Ismail et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: