A machine learning approach for predicting post-stroke aphasia recovery: A pilot study

Yiwen Gu; Murtadha Bahrani; Anne Billot; Sha Lai; Emily J. Braun; Maria Varkanitsa; Julia Bighetto; Brenda Rapp; Todd B. Parrish; David Caplan; Cynthia K. Thompson; Swathi Kiran; Margrit Betke

doi:10.1145/3389189.3389204

A machine learning approach for predicting post-stroke aphasia recovery: A pilot study

Yiwen Gu, Murtadha Bahrani, Anne Billot, Sha Lai, Emily J. Braun, Maria Varkanitsa, Julia Bighetto, Brenda Rapp, Todd B. Parrish, David Caplan, Cynthia K. Thompson, Swathi Kiran, Margrit Betke

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Scopus citations

Abstract

The potential recovery of post-stroke aphasia is highly variable and the rehabilitation outcomes are difficult to predict. This interdisciplinary collaboration builds on data collected as part of a large set of behavioral and brain variables in patients with post-stroke aphasia, charting the course of recovery associated with therapy across language domains and examining the basis of neuroplasticity. In this pilot study, we created and tested a predictive framework based on a subset of the data collected and developed machine-learning algorithms that take as input a complex set of brain and behavioral features to classify and predict the participants' responsiveness to therapy. We developed Random Forest models that enabled us to rank the importance of these features. We then compared the contributions of different feature sets and discussed their physiological implications. Our preliminary results suggest the potential of our framework, and, thus, this study takes an important first step towards predicting individualized rehabilitation outcomes.

Original language	English (US)
Title of host publication	13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020 - Conference Proceedings
Publisher	Association for Computing Machinery
Pages	161-169
Number of pages	9
ISBN (Electronic)	9781450377737
DOIs	https://doi.org/10.1145/3389189.3389204
State	Published - Jun 30 2020
Event	13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020 - Virtual, Online, Greece Duration: Jun 30 2020 → Jul 3 2020

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020
Country/Territory	Greece
City	Virtual, Online
Period	6/30/20 → 7/3/20

Funding

We would like to thank all the individuals with aphasia who participated in this study and their families. We also acknowledge the work of our collaborators through the Center for the Neurobiology of Language Recovery. This work was supported by the NIH/NIDCD Clinical Research Center Grant, P50DC012283, the Hariri Institute Artificial Intelligence Research (AIR) Initiative and the Institute for Health System Innovation & Policy (IHSIP) at Boston University.

Keywords

aphasia
machine learning
recovery
stroke

ASJC Scopus subject areas

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

Access to Document

10.1145/3389189.3389204

Cite this

Gu, Y., Bahrani, M., Billot, A., Lai, S., Braun, E. J., Varkanitsa, M., Bighetto, J., Rapp, B., Parrish, T. B., Caplan, D., Thompson, C. K., Kiran, S., & Betke, M. (2020). A machine learning approach for predicting post-stroke aphasia recovery: A pilot study. In 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020 - Conference Proceedings (pp. 161-169). Article 3389204 (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3389189.3389204

Gu, Yiwen ; Bahrani, Murtadha ; Billot, Anne et al. / A machine learning approach for predicting post-stroke aphasia recovery : A pilot study. 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020 - Conference Proceedings. Association for Computing Machinery, 2020. pp. 161-169 (ACM International Conference Proceeding Series).

@inproceedings{897e9b64197c4b56b4806858998abc51,

title = "A machine learning approach for predicting post-stroke aphasia recovery: A pilot study",

abstract = "The potential recovery of post-stroke aphasia is highly variable and the rehabilitation outcomes are difficult to predict. This interdisciplinary collaboration builds on data collected as part of a large set of behavioral and brain variables in patients with post-stroke aphasia, charting the course of recovery associated with therapy across language domains and examining the basis of neuroplasticity. In this pilot study, we created and tested a predictive framework based on a subset of the data collected and developed machine-learning algorithms that take as input a complex set of brain and behavioral features to classify and predict the participants' responsiveness to therapy. We developed Random Forest models that enabled us to rank the importance of these features. We then compared the contributions of different feature sets and discussed their physiological implications. Our preliminary results suggest the potential of our framework, and, thus, this study takes an important first step towards predicting individualized rehabilitation outcomes.",

keywords = "aphasia, machine learning, recovery, stroke",

author = "Yiwen Gu and Murtadha Bahrani and Anne Billot and Sha Lai and Braun, {Emily J.} and Maria Varkanitsa and Julia Bighetto and Brenda Rapp and Parrish, {Todd B.} and David Caplan and Thompson, {Cynthia K.} and Swathi Kiran and Margrit Betke",

note = "Publisher Copyright: {\textcopyright} 2020 ACM.; 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020 ; Conference date: 30-06-2020 Through 03-07-2020",

year = "2020",

month = jun,

day = "30",

doi = "10.1145/3389189.3389204",

language = "English (US)",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "161--169",

booktitle = "13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020 - Conference Proceedings",

}

Gu, Y, Bahrani, M, Billot, A, Lai, S, Braun, EJ, Varkanitsa, M, Bighetto, J, Rapp, B, Parrish, TB, Caplan, D, Thompson, CK, Kiran, S & Betke, M 2020, A machine learning approach for predicting post-stroke aphasia recovery: A pilot study. in 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020 - Conference Proceedings., 3389204, ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 161-169, 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020, Virtual, Online, Greece, 6/30/20. https://doi.org/10.1145/3389189.3389204

A machine learning approach for predicting post-stroke aphasia recovery: A pilot study. / Gu, Yiwen; Bahrani, Murtadha; Billot, Anne et al.
13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020 - Conference Proceedings. Association for Computing Machinery, 2020. p. 161-169 3389204 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A machine learning approach for predicting post-stroke aphasia recovery

T2 - 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020

AU - Gu, Yiwen

AU - Bahrani, Murtadha

AU - Billot, Anne

AU - Lai, Sha

AU - Braun, Emily J.

AU - Varkanitsa, Maria

AU - Bighetto, Julia

AU - Rapp, Brenda

AU - Parrish, Todd B.

AU - Caplan, David

AU - Thompson, Cynthia K.

AU - Kiran, Swathi

AU - Betke, Margrit

PY - 2020/6/30

Y1 - 2020/6/30

N2 - The potential recovery of post-stroke aphasia is highly variable and the rehabilitation outcomes are difficult to predict. This interdisciplinary collaboration builds on data collected as part of a large set of behavioral and brain variables in patients with post-stroke aphasia, charting the course of recovery associated with therapy across language domains and examining the basis of neuroplasticity. In this pilot study, we created and tested a predictive framework based on a subset of the data collected and developed machine-learning algorithms that take as input a complex set of brain and behavioral features to classify and predict the participants' responsiveness to therapy. We developed Random Forest models that enabled us to rank the importance of these features. We then compared the contributions of different feature sets and discussed their physiological implications. Our preliminary results suggest the potential of our framework, and, thus, this study takes an important first step towards predicting individualized rehabilitation outcomes.

AB - The potential recovery of post-stroke aphasia is highly variable and the rehabilitation outcomes are difficult to predict. This interdisciplinary collaboration builds on data collected as part of a large set of behavioral and brain variables in patients with post-stroke aphasia, charting the course of recovery associated with therapy across language domains and examining the basis of neuroplasticity. In this pilot study, we created and tested a predictive framework based on a subset of the data collected and developed machine-learning algorithms that take as input a complex set of brain and behavioral features to classify and predict the participants' responsiveness to therapy. We developed Random Forest models that enabled us to rank the importance of these features. We then compared the contributions of different feature sets and discussed their physiological implications. Our preliminary results suggest the potential of our framework, and, thus, this study takes an important first step towards predicting individualized rehabilitation outcomes.

KW - aphasia

KW - machine learning

KW - recovery

KW - stroke

UR - http://www.scopus.com/inward/record.url?scp=85088403723&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85088403723&partnerID=8YFLogxK

U2 - 10.1145/3389189.3389204

DO - 10.1145/3389189.3389204

M3 - Conference contribution

AN - SCOPUS:85088403723

T3 - ACM International Conference Proceeding Series

SP - 161

EP - 169

BT - 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020 - Conference Proceedings

PB - Association for Computing Machinery

Y2 - 30 June 2020 through 3 July 2020

ER -

Gu Y, Bahrani M, Billot A, Lai S, Braun EJ, Varkanitsa M et al. A machine learning approach for predicting post-stroke aphasia recovery: A pilot study. In 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2020 - Conference Proceedings. Association for Computing Machinery. 2020. p. 161-169. 3389204. (ACM International Conference Proceeding Series). doi: 10.1145/3389189.3389204

A machine learning approach for predicting post-stroke aphasia recovery: A pilot study

Abstract

Publication series

Conference

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this