 This research paper examined the use of machine learning, ML, models to identify patients at risk of developing aspiration during acute stroke. The authors found that the Gus, gugging swallowing screen, had a high accuracy rate when used as a predictive tool for identifying patients who would develop aspiration. Additionally, they found that the Ridge regression model was the most accurate of the ML models tested, with an area under the receiver operating characteristics curve, AUROC, of 0.81. Furthermore, the authors noted that the modified rank in scale was the most important feature in determining the accuracy of the model. This article was authored by Dofo Park, Sukulinoi Sun, Minit Sol Kim, and others.