The epidemic of coronary artery disease continues to affect a large number of individuals who often experience sudden and unexpected events. This underscores the need to develop more effective programs to detect silent atherosclerosis, with the ultimate goal of preventing coronary events. The use of conventional risk factors is helpful in assessing the median risk of a population, but it is often unsatisfactory in estimating the actual risk of an individual patient. As a consequence, newer imaging modalities are being developed to detect atherosclerosis in its early developmental phases. Technologies such as electron-beam computed tomography (EBCT) may render risk stratification more accurate if used in the appropriate patient populations and with the right diagnostic approach. Several studies have already demonstrated the power of coronary calcification as a strong predictor of future cardiovascular events. Nonetheless, the medical literature is currently pervaded by an animated debate, as some investigators still have concerns about the effectiveness of a preventive approach driven by technology. The use of Bayesian models to interpret data acquired with EBCT screening may provide practitioners with valuable evidence to aid in their decision making.