Machine Learning Predictions of Recovery in Bilingual Poststroke Aphasia: Aligning Insights With Clinical Evidence.

Journal: Stroke
PMID: 39744848

Abstract

BACKGROUND: Predicting treated language improvement (TLI) and transfer to the untreated language (cross-language generalization, CLG) after speech-language therapy in bilingual individuals with poststroke aphasia is crucial for personalized treatment planning. This study evaluated machine learning models to predict TLI and CLG and identified the key predictive features (eg, patient severity, demographics, and treatment variables) aligning with clinical evidence.

Authors

  • Manuel Jose Marte
    Center for Brain Recovery, Boston University, MA (M.J.M., E.C., M.S., M.R.-M., S.K.).
  • Erin Carpenter
    Center for Brain Recovery, Boston University, MA (M.J.M., E.C., M.S., M.R.-M., S.K.).
  • Michael Scimeca
    Center for Brain Recovery, Boston University, MA (M.J.M., E.C., M.S., M.R.-M., S.K.).
  • Marissa Russell-Meill
    Center for Brain Recovery, Boston University, MA (M.J.M., E.C., M.S., M.R.-M., S.K.).
  • Claudia Peñaloza
    Department of Cognition, Development and Educational Psychology, Faculty of Psychology (C.P.).
  • Uli Grasemann
    Department of Computer Sciences, University of Texas at Austin (U.G., R.M.).
  • Risto Miikkulainen
    The University of Texas at Austin, Austin, TX, 78712, USA; Cognizant AI Labs, 649 Front St., San Francisco, CA, 94111, USA. Electronic address: risto@cs.utexas.edu.
  • Swathi Kiran
    Center for Brain Recovery, Boston University, MA (M.J.M., E.C., M.S., M.R.-M., S.K.).

Keywords

External Resources

Popular Topics
Recent Journals