Background: Patients with type 2 diabetes (T2D) are at high risk of cardiovascular (CV) morbidity/mortality. The ACCORD trial (NCT00000620) tested intensive glycemic, lipid and blood pressure interventions on major CV events in 10,251 T2D patients with baseline HbA1c concentration >7.5%. Despite its landmark findings, a data-driven systematic evaluation of predictors for major cardiovascular events among hundreds of ACCORD variables has not been conducted. Methods: Random Survival Forest (RSF), a machine-learning method for survival analysis, identified important predictors for total mortality (TM), CV death (CVd), hospitalization/death due to heart failure (hdHF), fatal/non-fatal stroke (CVA), non-fatal myocardial infarction (MI) and MACE (composite of CVd, MI and CVA). Among 378 risk factors, including some highly correlated features, the top-ranked predictors (collected at baseline or derived from repeated measures prior to events) were selected, resulting in a hierarchy of predictive variables. Effects of RSF-selected predictors were then evaluated by multivariate Cox Proportional Hazards Models. Results: Table 1 presented the top ten predictors for six major events. Variables associated with changes in renal function predicted TM, CVd, and hdHF with ~90% accuracy. Insulin use was an important predictor along with predefined composite renal microvascular events for MI, CVA and MACE (74-79% accuracy). The Cox regression models based on RSF variable selection yielded similar findings for these important predictors of events. Conclusions: RSF approach revealed that insulin use and overt renal microvascular events were predictors for the occurrence of MI, stroke, and MACE in T2D patients. Moreover, dynamic changes in urinary renal function biomarkers had additional predictive values for fatal events. These results provide important clinical insights for reducing CV events in Type 2 diabetes patients.