Previous estimates of the utility of polygenic risk score analysis for the prediction of Alzheimer disease have given area under the curve (AUC) estimates of <80%. However, these have been based on the genetic analysis of clinical case–control series. Here, we apply the same analytic approaches to a pathological case–control series and show a predictive AUC of 84%. We suggest that this analysis has clinical utility and that there is limited room for further improvement using genetic data. Ann Neurol 2017;82:311–314.