Effective analysis of post-vaccination adverse events is vital to assuring the safety of vaccines, a key public health intervention for reducing the frequency of vaccine-preventable illnesses. The CDC/FDA Vaccine Adverse Event Reporting System (VAERS) contains up to 20,000 reports per year over the past 25 years. Effective analyses of time trends for post-vaccine adverse events can boost clinical research in different areas such as vaccine safety analyses, temporal associations and risk predictions. With extracted temporal information contained in the narratives, we propose a novel method to conduct risk prediction through temporal phenotyping. We demonstrate how clinical information contained in Medical Dictionary for Regulatory Activities (MedDRA) can be incorporated into the temporal phenotyping procedure in order to enhance the prediction of risk of severe AEs.