The added value of incorporating information from repeated measurements of blood pressure and cholesterol for cardiovascular disease (CVD) risk prediction has not been rigorously assessed. We used data from the Emerging Risk Factors Collaboration on 191,445 adults (38 cohorts from across 17 countries with data from 1962-2014) with > 1 million measurements of systolic blood pressure, total cholesterol and high-density lipoprotein cholesterol; over a median 12 years of follow-up, 21,170 CVD events occurred. Risk prediction models using cumulative means of repeated measurements and summary measures from longitudinal modelling of the repeated measurements were compared to models using measurements from a single time point. Risk discrimination (C-index) and net reclassification were calculated, and changes in C-indices were meta-analysed across studies. Compared to the single time point model, the cumulative means and the longitudinal models increased the C-index by 0.0040 (95% CI: 0.0023, 0.0057) and 0.0023 (0.0005, 0.0042), respectively. Reclassification was also improved in both models; compared to the single time point model, overall net reclassification improvements were 0.0369 (0.0303, 0.0436) for the cumulative means model and 0.0177 (0.0110, 0.0243) for the longitudinal model. In conclusion, incorporating repeated measurements of blood pressure and cholesterol into CVD risk prediction models slightly improves risk prediction.