It has been advocated that using the stress followed by rest protocol, if the stress images were normal there is no need of rest images, reducing radiation exposure and costs. Our purpose was to assess the prognosis of a group of patients with normal stress-only gated-SPECT myocardial perfusion imaging. This was retrospective study that includes 790 patients with normal myocardial stress only perfusion gated SPECT images. Images were considered as normal if a homogeneous myocardial distribution of the tracer was associated with a normal ejection fraction. The mean follow-up was of 42.8 ± 13.3 months. The considered events were death of all causes, myocardial infarction and myocardial revascularization. During this period there were 85 events (10.8 %), including 57 deaths of all causes (67.1 %), 9 myocardial infarctions (10.6 %), 19 revascularizations (2.4 %). In the first year of follow-up there were 32 events (4.0 %) and excluding non cardiac deaths there were 8 events (1.0 %). Using Cox survival analysis, diabetes (HR = 2.2; CI = 1.4-3.4; p ≤ 0.0005), the history of coronary artery disease (CAD) (HR = 2.1; CI = 1.3-3.2; p ≤ 0.001), age (HR = 1.0; CI = 1.0-1.0; p ≤ 0.05) and type of stress protocol were related with events (exercise test vs. adenosine) (Exercise test: HR = 0.5; CI = 0.3-0.8; p ≤ 0.01). In a multivariate analysis the independent predictors were diabetes, CAD and the type of stress protocol. Based on these results, normal stress-only images are associated with an excellent prognosis even in patients at higher risk, diabetics and patients with known CAD.