Bayesian network meta-analysis of 13 studies (54 models, 927,113 patients): machine learning generally predicted cardiac complications after non-cardiac surgery better than the Revised Cardiac Risk Index; none were externally validated, only six studies low risk of bias.
Meta-analysisn = 927,113
Dhaliwal et al. Machine learning vs. traditional methods for predicting postoperative cardiac complications after non-cardiac surgery: a systematic review and Bayesian network meta-analysis