We compared the predictive performance of an artificial neural network to traditional pharmacometric modelling for population prediction of plasma concentrations of valproate in real-world data. We included individuals aged 65 years or older with epilepsy who redeemed their first prescription of valproate after the diagnosis of epilepsy and had at least one valproate plasma concentration measured. A long short-term memory neural network (LSTM) was developed using the training dataset to fit the LSTM and the test dataset to validate the model. Predictions from the LSTM were compared with those obtained from the population predictions from a pharmacometric model by Birnbaum et al. which had the best predictive performance for population predictions of valproate concentrations in Danish databases. We used the cut-off of ±20 mg/L of prediction error to define good predictions. A total of 1252 individuals were included in the study. The LSTM fitted using the training dataset had poor predictive performance in the test dataset, but better than that of the pharmacometric model. The proportion of individuals with at least one predicted concentration within ±20 mg/L of observed concentration was largest in case of the LSTM (64.4% (95% confidence interval 58.4-70.2%)) compared with the pharmacometric model by Birnbaum et al. (49.8% (47.0-52.6%)). LSTM shows better predictive performance to predict valproate plasma concentrations compared with a traditional pharmacometric model in the investigated setting with real-world data in older patients with epilepsy where information on exact time points for both dosing and plasma concentration measurement are missing.