The aim of this study is to review the predictive value of visit-to-visit variability in glycaemic or lipid tests for forecasting major adverse cardiovascular events (MACE) in diabetes mellitus. Data from existing studies suggests that such variability is an independent predictor of adverse outcomes in this patient cohort. This understanding is then applied to the development of PowerAI-Diabetes, a Chinese-specific artificial intelligence-enhanced predictive model for predicting the risks of major adverse cardiovascular events and diabetic complications. The model integrates an amalgam of variables including demographics, laboratory and medication information to assess the risk of MACE. Future efforts should focus on the incorporation of treatment effects and non-traditional cardiovascular risk factors, such as social determinants of health variables, to improve the performance of predictive models.