Multimodal Neural and Behavioral Data Predict Response to Rehabilitation in Chronic Poststroke Aphasia

Anne Billot*, Sha Lai, Maria Varkanitsa, Emily J. Braun, Brenda Rapp, Todd B. Parrish, James Higgins, Ajay S. Kurani, David Caplan, Cynthia K Thompson, Prakash Ishwar, Margrit Betke, Swathi Kiran

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Background: Poststroke recovery depends on multiple factors and varies greatly across individuals. Using machine learning models, this study investigated the independent and complementary prognostic role of different patient-related factors in predicting response to language rehabilitation after a stroke. Methods: Fifty-five individuals with chronic poststroke aphasia underwent a battery of standardized assessments and structural and functional magnetic resonance imaging scans, and received 12 weeks of language treatment. Support vector machine and random forest models were constructed to predict responsiveness to treatment using pretreatment behavioral, demographic, and structural and functional neuroimaging data. Results: The best prediction performance was achieved by a support vector machine model trained on aphasia severity, demographics, measures of anatomic integrity and resting-state functional connectivity (F1=0.94). This model resulted in a significantly superior prediction performance compared with support vector machine models trained on all feature sets (F1=0.82, P<0.001) or a single feature set (F1 range=0.68-0.84, P<0.001). Across random forest models, training on resting-state functional magnetic resonance imaging connectivity data yielded the best F1 score (F1=0.87). Conclusions: While behavioral, multimodal neuroimaging data and demographic information carry complementary information in predicting response to rehabilitation in chronic poststroke aphasia, functional connectivity of the brain at rest after stroke is a particularly important predictor of responsiveness to treatment, both alone and combined with other patient-related factors.

Original languageEnglish (US)
Pages (from-to)1606-1614
Number of pages9
JournalStroke
Volume53
Issue number5
DOIs
StatePublished - May 1 2022

Keywords

  • aphasia
  • language
  • machine learning
  • magnetic resonance imaging
  • neuroimaging
  • rehabilitation

ASJC Scopus subject areas

  • Clinical Neurology
  • Cardiology and Cardiovascular Medicine
  • Advanced and Specialized Nursing

Fingerprint

Dive into the research topics of 'Multimodal Neural and Behavioral Data Predict Response to Rehabilitation in Chronic Poststroke Aphasia'. Together they form a unique fingerprint.

Cite this