BackgroundConflicting evidence suggests that statins act chemopreventively against prostate cancer (PCa). Whether the association of statin use with PCa risk is Gleason score‐dependent, time‐, dose‐respondent is not well studied.MethodsWe conducted a cohort study at a tertiary hospital in the Southeastern US using longitudinal data of electronic medical records (EMR) from 1994 to 2016. Only cancer‐free men aged >18 years at baseline with follow‐up time of ≥12 months were included. Time‐dependent Cox proportional hazards regression was used to estimate adjusted hazard ratios (aHRs) with 95% confidence intervals (CIs).ResultsAmong 13 065 men, 2976 were diagnosed with PCa over median follow‐up of 6.6 years. Statin use was associated with lower risk of both Gleason low‐ (score <7: aHR, 0.85; 95% CI, 0.74‐0.96) and high‐grade PCa (score ≥7: aHR, 0.54; 95% CI, 0.42‐0.69). The protective association was observed only when statins had been used for a relatively longer duration (≥11 months) or higher dose (≥121 defined daily doses), and were more pronounced for PCa of higher Gleason score (<7: aHR, 0.85, 95% CI, 0.74‐0.96; 7 [3 + 4]: aHR, 0.62, 95% CI, 0.43‐0.90; 7 [4 + 3]: aHR, 0.49, 95% CI, 0.29‐0.82; 8: aHR, 0.60, 95% CI, 0.37‐0.96; 9‐10: aHR, 0.24, 95% CI, 0.11‐0.54). Lipophilic statins (aHR, 0.83; 95% CI, 0.72‐0.95) might be more protective than hydrophilic statins (aHR, 0.91, 95% CI, 0.63‐1.33) against PCa.ConclusionStatin use might be associated with reduced PCa risk only when used for a relatively longer duration, and the risk reduction was higher for PCa of higher Gleason score.