As the potential impact of statins on cognitive decline and dementia is still debated, we conducted a meta-analysis of observational studies to examine the effect of statin use on the risk of Alzheimer's disease (AD) and dementia. PubMed, Cochrane, and EMBASE were searched since inception to January 2021. Inclusion criteria were: (i) cohort or case-control studies; (ii) statin users compared to non-users; and (iii) AD and/or dementia risk as outcome. Estimates from original studies were pooled using restricted maximum-likelihood random-effect model. Measure of effects were reported as odds ratio (OR) and 95% confidence intervals (CIs). In the pooled analyses, statins were associated with a decreased risk of dementia [36 studies, OR 0.80 (CI 0.75-0.86)] and of AD [21 studies, OR 0.68 (CI 0.56-0.81)]. In the stratified analysis by sex, no difference was observed in the risk reduction of dementia between men [OR 0.86 (CI 0.81-0.92)] and women [OR 0.86 (CI 0.81-0.92)]. Similar risks were observed for lipophilic and hydrophilic statins for both dementia and AD, while high-potency statins showed a 20% reduction of dementia risk compared with a 16% risk reduction associated with low-potency statins, suggesting a greater efficacy of the former, although a borderline statistical significance (P = 0.05) for the heterogeneity between estimates. These results confirm the absence of a neurocognitive risk associated with statin treatment and suggest a potential favourable role of statins. Randomized clinical trials with an ad hoc design are needed to explore this potential neuroprotective effect. © The Author(s) 2021. Published by Oxford University Press on behalf of the European Society of Cardiology.