An Exploration of Machine Learning Methods for Predicting Post-stroke Aphasia Recovery

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Predicting the potential recovery outcome of post-stroke aphasia remains a challenging task. Our previous work[10] applied machine learning algorithms to predict participant response to therapy using a complex set of brain and behavioral data in individuals with post-stroke aphasia. The present work explores the additional predictive value of cognitive composite scores (CS), which measure visuo-spatial processing and verbal working memory; high-dimensional resting-state (RS) functional magnetic resonance imaging (fMRI) data, which measures the functional connectivity between brain regions; and diffusion tensor imaging (DTI) data, which provides information related to microstructural integrity via fractional anisotropy (FA) values. We first perform feature selection on the RS data as it has about 5 times more features than than all the other feature-sets combined. Next, we append these RS features, CS scores, and FA values to our existing data set. Finally, we train Support Vector Machine (SVM) and Random Forest (RF) classifiers for various combinations of feature-sets and compare their performance in terms of accuracy, F1-score, sensitivity and selectivity. Results show that combinations of feature-sets outperform most individual feature-sets and whereas each feature-set is present among the top 20 combinations, many of them contain RS.

Original languageEnglish (US)
Title of host publication14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021
PublisherAssociation for Computing Machinery
Pages556-564
Number of pages9
ISBN (Electronic)9781450387927
DOIs
StatePublished - Jun 29 2021
Externally publishedYes
Event14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021 - Virtual, Online, Greece
Duration: Jun 29 2021Jul 1 2021

Publication series

NameACM International Conference Proceeding Series

Conference

Conference14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021
Country/TerritoryGreece
CityVirtual, Online
Period6/29/217/1/21

Keywords

  • Aphasia
  • Feature Selection
  • Machine Learning
  • Recovery
  • Stroke

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'An Exploration of Machine Learning Methods for Predicting Post-stroke Aphasia Recovery'. Together they form a unique fingerprint.

Cite this