Lee WH, et al. - In patients with poststroke dysphagia, researchers examined clinical and radiological prognostic factors for long-term swallowing recovery and developed and validated a prognostic model using a machine learning algorithm. One hundred thirty-seven consecutive patients with acute ischemic stroke referred for swallowing examinations have been retrospectively reviewed. Using the Kaplan-Meier method and Cox regression model, dysphagia was monitored in the 6 months poststroke period and then analyzed for clinical and radiological factors. For the first 6 months, 24 patients exhibited persistent dysphagia with a mean duration of 65.6 days. Initial severity of dysphagia and bilateral corona radiata, basal ganglia, or internal capsule lesions were found to be significant prognostic factors for 6-month swallowing recovery. The anticipation of a 6-month swallowing recovery using the Bayesian network model was feasible based on clinical and radiological factors. The importance of bilateral subcortical lesions as prognostic factors that could be utilized to develop prediction models for long-term swallowing recovery was highlighted.