EUVIMEDEUVIMED entdecken
Crossref

Clinical machine learning predicting best stroke rehabilitation responders to exoskeletal robotic gait rehabilitation

Seonmi Park, Jongeun Choi, Yonghoon Kim, Joshua Sung H You

NeuroRehabilitation · 2024

DOI: 10.3233/nre-240070 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NeuroRehabilitation, 2024. Verfasst von Seonmi Park und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physical Therapy, Sports·Movement Artificial-Intelligence Robotics Technology (SMART) Institute, Yonsei University, Wonju, South Korea. Hauptthemen laut MEDLINE: Stroke Rehabilitation, Machine Learning, Gait Disorders, Neurologic. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 28 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Although clinical machine learning (ML) algorithms offer promising potential in forecasting optimal stroke rehabilitation outcomes, their specific capacity to ascertain favorable outcomes and identify responders to robotic-assisted gait training (RAGT) in individuals with hemiparetic stroke undergoing such intervention remains unexplored. OBJECTIVE: We aimed to determine the best predictive model based on the international classification of functioning impairment domain features (Fugl– Meyer assessment (FMA), Modified Barthel index related-gait scale (MBI), Berg balance scale (BBS)) and reveal their responsiveness to robotic assisted gait training (RAGT) in patients with subacute stroke. METHODS: Data from 187 people with subacute stroke who underwent a 12-week Walkbot RAGT intervention were obtained and analyzed. Overall, 18 potential predictors encompassed demographic characteristics and the baseline score of functional and structural features. Five predictive ML models, including decision tree, random forest, eXtreme Gradient Boosting, light gradient boosting machine, and categorical boosting, were used. RESULTS: The initial and final BBS, initial BBS, final Modified Ashworth scale, and initial MBI scores were important features, predicting functional improvements. eXtreme Gradient Boosting demonstrated superior performance compared to other models in predicting functional recovery after RAGT in patients with subacute stroke. CONCLUSION: eXtreme Gradient Boosting may be an invaluable prognostic tool, providing clinicians and caregivers with a robust framework to make precise clinical decisions regarding the identification of optimal responders and effectively pinpoint those who are most likely to derive maximum benefits from RAGT interventions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Stroke RehabilitationMachine LearningGait Disorders, NeurologicHumansFemaleMaleMiddle AgedAgedRoboticsExoskeleton DeviceStrokeRecovery of FunctionAdultPrognosisOutcome Assessment, Health CareExercise TherapyGait

Stichwörter der Autor:innen

Machine learningrobotic assisted gait trainingstroke rehabilitation

Autor:innen und Institutionen

  • Department of Physical Therapy, Sports·Movement Artificial-Intelligence Robotics Technology (SMART) Institute, Yonsei University, Wonju, South Korea.
  • Department of Mechanical Engineering, Machine Learning and Control Systems Lab, Yonsei University, South Korea.
  • Chungdam Rehabilitation Hospital Center, Seoul, South Korea.

Zitieren

APA

Park, S., Choi, J., Kim, Y., & You, J. S. H. (2024). Clinical machine learning predicting best stroke rehabilitation responders to exoskeletal robotic gait rehabilitation. NeuroRehabilitation. https://doi.org/10.3233/nre-240070

Vancouver

Park S, Choi J, Kim Y, You JSH. Clinical machine learning predicting best stroke rehabilitation responders to exoskeletal robotic gait rehabilitation. NeuroRehabilitation. 2024. doi:10.3233/nre-240070

BibTeX
@article{Park2024,
  author = {Park, Seonmi and Choi, Jongeun and Kim, Yonghoon and You, Joshua Sung H},
  title = {Clinical machine learning predicting best stroke rehabilitation responders to exoskeletal robotic gait rehabilitation},
  journal = {NeuroRehabilitation},
  year = {2024},
  doi = {10.3233/nre-240070}
}
Kostenlos starten →