Chowdhury MZI, et al. - Via performing the systematic review of relevant literature, researchers sought to recognize the available stroke prediction models specifically developed or validated in patients with diabetes and via performing a meta-analysis, they examined their predictive performance. The search yielded 26,202 relevant papers, finally yielding 38 stroke prediction models. Of these, 34 were specifically developed for patients with diabetes and 4 were developed in general populations but validated in patients with diabetes. External validation of only a small number of models have been done; these might provide generalizable predictions that would support their use in another clinical setting. As none of these models showed superior discriminative performance, and in addition, no single model consistently performed well, choosing one model over another is difficult. Given the general perception of an elevated risk of stroke among persons with diabetes, the current practice is to treat to common HbA1C, blood pressure and low-density lipoprotein targets based on diabetes status alone and not on calculated risk. However, this non-risk based approach may be leading to unnecessary overtreatment. This highlights the necessity for research to identify and incorporate new risk factors into the model to improve models’ predictive ability and avoiding unnecessary overtreatment.