Risk-adjusted control charts were considered to be the most effective method for monitoring surgical outcomes in previous studies. However, existing methods focus only on monitoring postoperative mortality, while ignoring other important outcome indicators. In this paper, we develop a new monitoring model based on a multi-label learning framework to monitor multivariate surgical outcomes. The monitoring model is based on the Classifier Chain in multi-label learning to depict the unidirectional correlations between multiple outcome indicators. Comparing the proposed chart to existing multivariate methods, simulation results demonstrate that the proposed chart is more effective at detecting small changes in surgical risk. The proposed method is also more stable than a univariate control chart that only measures mortality risk. The utility of our chart was demonstrated by using a data set of the Surgical Outcome Monitoring and Improvement Program in Hong Kong.