EUVIMEDEUVIMED entdecken
Open Access

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

Manuel Jose Marte iD, Erin Carpenter iD, Michael Scimeca iD, Marissa Russell-Meill iD, Claudia Peñaloza iD, Uli Grasemann iD, Risto Miikkulainen iD, Swathi Kiran iD

Stroke · 2025

DOI: 10.1161/strokeaha.124.047867 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Stroke, 2025. Verfasst von Manuel Jose Marte und 7 weiteren Autor:innen. Beteiligte Einrichtung: Center for Brain Recovery, Boston University, MA (M.J.M., E.C., M.S., M.R.-M., S.K.). Hauptthemen laut MEDLINE: Machine Learning, Aphasia, Multilingualism, Stroke. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 77 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDCD NIH HHS, NINDS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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. METHODS: Forty-eight Spanish-English bilingual individuals with poststroke aphasia received 20 sessions of semantic feature-based naming treatment in either their first or second language. Comprehensive language, cognitive, and background bilingual experience assessments were administered pre- and post-treatment. Sixteen curated features spanning demographics, language abilities, cognition, and bilingual experience were used as inputs to 6 machine learning algorithms to predict treatment responders versus nonresponders and CLG vs no CLG. RESULTS: The top 2 machine learning models achieved F1 scores of 0.767±0.153 for TLI and 0.790±0.172 for CLG. Interpretability analyses revealed that aphasia severity in the trained language, education, and cognitive performance were key predictors of TLI. Aphasia severity in the untreated language and cognitive performance emerged as influential features of CLG. These aligned with expectations based on prior literature. CONCLUSIONS: For the first time, machine learning models reveal that factors such as patient severity and demographics predict TLI and CLG after therapy in Spanish-English bilingual individuals with poststroke aphasia. Consideration of both treated and untreated language severity, as well as cognitive assessment performance, when forecasting treatment outcomes in an underserved population such Spanish-English stroke survivors, can meaningfully impact their short-term and long-term clinical care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningAphasiaMultilingualismStrokeRecovery of FunctionHumansMaleFemaleMiddle AgedAgedStroke RehabilitationLanguage TherapyTreatment OutcomeAdult

Stichwörter der Autor:innen

aphasiacognitionlanguage therapymachine learningmultilingualismstroke

Autor:innen und Institutionen

  • Center for Brain Recovery, Boston University, MA (M.J.M., E.C., M.S., M.R.-M., S.K.).
  • Department of Cognition, Development and Educational Psychology, Faculty of Psychology (C.P.).
  • Institute of Neurosciences (C.P.).
  • University of Barcelona, Spain (C.P.).
  • Cognition and Brain Plasticity Unit, Bellvitge Biomedical Research Institute-IDIBELL, L'Hospitalet de Llobregat, Barcelona, Spain (C.P.).
  • Department of Computer Sciences, University of Texas at Austin (U.G., R.M.).

ORCID-Profile: Manuel Jose Marte, Erin Carpenter, Michael Scimeca, Marissa Russell-Meill, Claudia Peñaloza, Uli Grasemann, Risto Miikkulainen, Swathi Kiran

Förderung

  • NIDCD NIH HHS
  • NINDS NIH HHS

Zitieren

APA

Marte, M. J., Carpenter, E., Scimeca, M., Russell-Meill, M., Peñaloza, C., Grasemann, U., Miikkulainen, R., & Kiran, S. (2025). Machine Learning Predictions of Recovery in Bilingual Poststroke Aphasia: Aligning Insights With Clinical Evidence. Stroke. https://doi.org/10.1161/strokeaha.124.047867

Vancouver

Marte MJ, Carpenter E, Scimeca M, Russell-Meill M, Peñaloza C, Grasemann U, et al. Machine Learning Predictions of Recovery in Bilingual Poststroke Aphasia: Aligning Insights With Clinical Evidence. Stroke. 2025. doi:10.1161/strokeaha.124.047867

BibTeX
@article{Marte2025,
  author = {Marte, Manuel Jose and Carpenter, Erin and Scimeca, Michael and Russell-Meill, Marissa and Peñaloza, Claudia and Grasemann, Uli and Miikkulainen, Risto and Kiran, Swathi},
  title = {Machine Learning Predictions of Recovery in Bilingual Poststroke Aphasia: Aligning Insights With Clinical Evidence},
  journal = {Stroke},
  year = {2025},
  doi = {10.1161/strokeaha.124.047867}
}
Kostenlos starten →