Objectives The aim was to examine the association between disease duration and risk of myocardial infarction (MI) in patients with PsA. Methods We used nationwide registry data from Denmark to estimate incidence rates per 1000 person-years and the risk of MI [adjusted hazard ratios (HRs) with 95% CIs] in rheumatologistdiagnosed patients with PsA using Cox regression models. The study period was between 1 January 2008 and 31 December 2012. Results The study population comprised a total of 8071 patients with PsA and 4 348 857 general population control subjects. A total of 156 and 54 215 MIs occurred during follow-up among patients with PsA and the reference population, respectively. There was a significant association between the duration of PsA and risk of MI (adjusted HR = 1.02; 95% CI: 1.01, 1.03 for each additional year after PsA diagnosis). Stratified based on short ( < 2 years) and long (≥2 years) disease duration, the adjusted HRs were 0.96 (95% CI: 0.60, 1.52; P=0.8487) and 1.29 (95% CI: 1.09, 1.53; P=0.0026), respectively. Other significant predictors included age, sex, socio-economic status, smoking, alcohol abuse, diabetes, hypertension and previous cardiovascular disease. Conclusions We observed an increased risk of MI associated with longer duration of PsA. Our findings call for increased focus on disease duration in the cardiovascular risk assessment among patients with PsA.