This study investigates whether machine-learning algorithms can improve cardiovascular risk prediction using routine clinical data. The research involved 378,256 patients from UK family practices, free from cardiovascular disease at the outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, and neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular events over a 10-year period. The results showed that all machine-learning algorithms significantly improved prediction accuracy compared to the established algorithm, with neural networks performing the best, increasing the area under the receiver operating curve (AUC) by 3.6%. The study concluded that machine-learning can enhance the accuracy of cardiovascular risk prediction, helping to identify more patients who would benefit from preventive treatment while avoiding unnecessary interventions.This study investigates whether machine-learning algorithms can improve cardiovascular risk prediction using routine clinical data. The research involved 378,256 patients from UK family practices, free from cardiovascular disease at the outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, and neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular events over a 10-year period. The results showed that all machine-learning algorithms significantly improved prediction accuracy compared to the established algorithm, with neural networks performing the best, increasing the area under the receiver operating curve (AUC) by 3.6%. The study concluded that machine-learning can enhance the accuracy of cardiovascular risk prediction, helping to identify more patients who would benefit from preventive treatment while avoiding unnecessary interventions.