Statistical analysis and machine learning of TMS-induced MEPs for predicting poststroke motor impairment and performance

Stroke severity is associated with the presence or absence of motor-evoked potentials (MEPs) induced by transcranial magnetic stimulation (TMS). However, there is limited evidence regarding the relationship between MEP waveforms, post-stroke motor impairment, and functional performance. This study a...

Full description

Saved in:
Bibliographic Details
Main Authors: Chun-Ren Phang, Shintaro Uehara, Sachiko Kodera, Akiko Yuasa, Shin Kitamura, Yohei Otaka, Akimasa Hirata
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Informatics in Medicine Unlocked
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352914825000310
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849322147062743040
author Chun-Ren Phang
Shintaro Uehara
Sachiko Kodera
Akiko Yuasa
Shin Kitamura
Yohei Otaka
Akimasa Hirata
author_facet Chun-Ren Phang
Shintaro Uehara
Sachiko Kodera
Akiko Yuasa
Shin Kitamura
Yohei Otaka
Akimasa Hirata
author_sort Chun-Ren Phang
collection DOAJ
description Stroke severity is associated with the presence or absence of motor-evoked potentials (MEPs) induced by transcranial magnetic stimulation (TMS). However, there is limited evidence regarding the relationship between MEP waveforms, post-stroke motor impairment, and functional performance. This study aimed to evaluate the predictive value of inter-trial correlation (ITC), a novel metric reflecting waveform consistency, along with MEP amplitude and resting motor threshold (rMT), in estimating post-stroke motor outcomes. Thirty-eight stroke participants were enrolled, and TMS was applied to the hotspot of the first dorsal interosseous muscle in the ipsilesional or contralesional hemisphere to elicit MEPs. MEP amplitude, ITC, and rMT were analyzed in 20 participants with detectable MEPs. Pearson correlation coefficient (PCC) analysis assessed the relationships between MEP features and motor outcomes, including the Stroke Impairment Assessment Set (SIAS), Fugl-Meyer Assessment (FMA), and Action Research Arm Test (ARAT). A linear support vector machine (SVM) was trained using leave-one-subject-out cross-validation to predict the motor outcomes. Participants without detectable MEPs (n = 18) had significantly lower motor scores than those with detectable MEPs did. MEP amplitude from the contralesional side was positively correlated with SIAS, FMA, and ARAT (PCC = 0.51, 0.47, and 0.55, respectively), whereas LICI amplitude and ITC from the ipsilesional side were negatively correlated with motor scores. The SVM model predicted motor outcomes with an R2 of 0.42 and a normalized root mean square error of 0.26. A Gaussian classifier achieved 75 % accuracy in classifying motor outcome improvements. These findings suggest that bilateral MEP features, particularly those from the contralesional hemisphere, offer valuable prognostic information. This study proposes a practical framework for post-stroke motor outcome prediction based on MEP analysis with potential utility in individualized rehabilitation planning.
format Article
id doaj-art-49207d21616e4d1ebea483ded1e26c7d
institution Kabale University
issn 2352-9148
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Informatics in Medicine Unlocked
spelling doaj-art-49207d21616e4d1ebea483ded1e26c7d2025-08-20T03:49:31ZengElsevierInformatics in Medicine Unlocked2352-91482025-01-015510164310.1016/j.imu.2025.101643Statistical analysis and machine learning of TMS-induced MEPs for predicting poststroke motor impairment and performanceChun-Ren Phang0Shintaro Uehara1Sachiko Kodera2Akiko Yuasa3Shin Kitamura4Yohei Otaka5Akimasa Hirata6Department of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya, Aichi, Japan; Center of Biomedical Physics and Information Technology, Nagoya Institute of Technology, Nagoya, Aichi, JapanFaculty of Rehabilitation, Fujita Health University School of Health Sciences, Toyoake, Aichi, JapanDepartment of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya, Aichi, Japan; Center of Biomedical Physics and Information Technology, Nagoya Institute of Technology, Nagoya, Aichi, JapanDepartment of Rehabilitation Medicine, Fujita Health University School of Medicine, Toyoake, Aichi, Japan; The Japan Society for the Promotion of Science, Chiyoda-ku, Tokyo, JapanFaculty of Rehabilitation, Fujita Health University School of Health Sciences, Toyoake, Aichi, JapanDepartment of Rehabilitation Medicine, Fujita Health University School of Medicine, Toyoake, Aichi, JapanDepartment of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya, Aichi, Japan; Center of Biomedical Physics and Information Technology, Nagoya Institute of Technology, Nagoya, Aichi, Japan; Corresponding author. Center of Biomedical Physics and Information Technology, Nagoya Institute of Technology, Nagoya, Aichi, 466-8555, Japan.Stroke severity is associated with the presence or absence of motor-evoked potentials (MEPs) induced by transcranial magnetic stimulation (TMS). However, there is limited evidence regarding the relationship between MEP waveforms, post-stroke motor impairment, and functional performance. This study aimed to evaluate the predictive value of inter-trial correlation (ITC), a novel metric reflecting waveform consistency, along with MEP amplitude and resting motor threshold (rMT), in estimating post-stroke motor outcomes. Thirty-eight stroke participants were enrolled, and TMS was applied to the hotspot of the first dorsal interosseous muscle in the ipsilesional or contralesional hemisphere to elicit MEPs. MEP amplitude, ITC, and rMT were analyzed in 20 participants with detectable MEPs. Pearson correlation coefficient (PCC) analysis assessed the relationships between MEP features and motor outcomes, including the Stroke Impairment Assessment Set (SIAS), Fugl-Meyer Assessment (FMA), and Action Research Arm Test (ARAT). A linear support vector machine (SVM) was trained using leave-one-subject-out cross-validation to predict the motor outcomes. Participants without detectable MEPs (n = 18) had significantly lower motor scores than those with detectable MEPs did. MEP amplitude from the contralesional side was positively correlated with SIAS, FMA, and ARAT (PCC = 0.51, 0.47, and 0.55, respectively), whereas LICI amplitude and ITC from the ipsilesional side were negatively correlated with motor scores. The SVM model predicted motor outcomes with an R2 of 0.42 and a normalized root mean square error of 0.26. A Gaussian classifier achieved 75 % accuracy in classifying motor outcome improvements. These findings suggest that bilateral MEP features, particularly those from the contralesional hemisphere, offer valuable prognostic information. This study proposes a practical framework for post-stroke motor outcome prediction based on MEP analysis with potential utility in individualized rehabilitation planning.http://www.sciencedirect.com/science/article/pii/S2352914825000310Transcranial magnetic stimulationMotor-evoked potentialMotor outcomeMachine learningPrediction
spellingShingle Chun-Ren Phang
Shintaro Uehara
Sachiko Kodera
Akiko Yuasa
Shin Kitamura
Yohei Otaka
Akimasa Hirata
Statistical analysis and machine learning of TMS-induced MEPs for predicting poststroke motor impairment and performance
Informatics in Medicine Unlocked
Transcranial magnetic stimulation
Motor-evoked potential
Motor outcome
Machine learning
Prediction
title Statistical analysis and machine learning of TMS-induced MEPs for predicting poststroke motor impairment and performance
title_full Statistical analysis and machine learning of TMS-induced MEPs for predicting poststroke motor impairment and performance
title_fullStr Statistical analysis and machine learning of TMS-induced MEPs for predicting poststroke motor impairment and performance
title_full_unstemmed Statistical analysis and machine learning of TMS-induced MEPs for predicting poststroke motor impairment and performance
title_short Statistical analysis and machine learning of TMS-induced MEPs for predicting poststroke motor impairment and performance
title_sort statistical analysis and machine learning of tms induced meps for predicting poststroke motor impairment and performance
topic Transcranial magnetic stimulation
Motor-evoked potential
Motor outcome
Machine learning
Prediction
url http://www.sciencedirect.com/science/article/pii/S2352914825000310
work_keys_str_mv AT chunrenphang statisticalanalysisandmachinelearningoftmsinducedmepsforpredictingpoststrokemotorimpairmentandperformance
AT shintarouehara statisticalanalysisandmachinelearningoftmsinducedmepsforpredictingpoststrokemotorimpairmentandperformance
AT sachikokodera statisticalanalysisandmachinelearningoftmsinducedmepsforpredictingpoststrokemotorimpairmentandperformance
AT akikoyuasa statisticalanalysisandmachinelearningoftmsinducedmepsforpredictingpoststrokemotorimpairmentandperformance
AT shinkitamura statisticalanalysisandmachinelearningoftmsinducedmepsforpredictingpoststrokemotorimpairmentandperformance
AT yoheiotaka statisticalanalysisandmachinelearningoftmsinducedmepsforpredictingpoststrokemotorimpairmentandperformance
AT akimasahirata statisticalanalysisandmachinelearningoftmsinducedmepsforpredictingpoststrokemotorimpairmentandperformance