OBJECTIVES: With the explosion of medical data, it is necessary to develop software tools to support the process of evidence review and synthesis that is fundamental to Evidence-Based Medicine. Furthermore, as predictive models are being increasingly integrated into clinical decision making for individual patients, there is an even greater need for a practical tool that enables development, validation, and uncertainty quantification of models in a robust, automatic and efficient way. METHODS: We developed Evidence Synthesis Engine (ESE), a software platform that enables users to display, compare and synthesize evidence from multiple data sources, to estimate disease risks, to validate risk models, to build predictive models, to recalibrate existing models as new data becomes available, to evaluate improvement in prediction performance between two models, and to quantify the accuracy of a predictive model in different subpopulations. RESULTS: We applied ESE to data from eight cardiovascular studies (six cohort studies and two clinical trials) with a total size of over 147,000 participants. ESE allows users to create customized pooled cohorts and subpopulations from these data sources. Users can assess the performance of predictive models for different subpopulations in real time. Several metrics were used for model evaluation: cumulative incidence, calibration plots, receiver operating curve and net reclassification index. ESE also allows users to generate and then assess models for risks of MI, stroke, heart failure, coronary death or composite cardiovascular outcome for a predefined subpopulation from selected datasets. We used ESE to evaluate the performance of five cardiovascular risk equations. The results suggested that compared to four other well-accepted cardiovascular risk equations, the 2013 Pooled Cohort Equations for 10-year risk of ASCVD could have superior performance for the individuals considered in these eight studies. CONCLUSIONS: ESE proves to be a useful tool for advancing the development and application of predictive modeling in medicine.