A recent meta-analysis to evaluate the impact of metformin on cardiovascular disease has been unable to demonstrate convincingly that it is associated with a reduction of risk. The investigators searched Medline, Embase and the Cochrane Library for relevant papers in all languages.  The final yield was ten articles, reporting 13 trials of metformin, virtually all carried out in Northern Europe or North America. In total, 2,079 patients with type 2 diabetes were allocated to metformin and a similar number to comparison groups. All the outcomes, with the exception of stroke, favoured metformin but none achieved statistical significance.