Scholarlink

This study explores the implementation of advanced surface electromyography (sEMG) technologies in medical education and neurorehabilitation, using real datasets to evaluate their effectiveness in both contexts. Two publicly available databases were analyzed: a high-density EMG and EEG dataset from healthy individuals performing reaching tasks with and without robotic assistance, and a clinical dataset involving post-stroke patients undergoing sEMG-driven robotic rehabilitation. In the educational setting, interactive EMG-EEG modules significantly improved medical students’ understanding of neuromuscular physiology, with a 25.9% increase in test scores. In the clinical domain, EMG-based assessments correlated strongly with expert manual evaluations of motor function (r = 0.92 for Fugl-Meyer scores), while muscle activation (RMS amplitude) improved by over 50% after therapy. These findings highlight the dual value of EMG systems for both interactive learning and objective clinical assessment. The study concludes that EMG technologies offer scalable, data-driven solutions to enhance diagnostic precision, support educational innovation, and personalize neurorehabilitation. Future work will focus on integrating EMG with AI and wearable systems for broader applications in remote and adaptive healthcare.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Implementation of Advanced Electromyography (EMG) Technologies for Medical Education and Diagnosis in Neurorehabilitation: Evidence from Public Databases

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Bogart Yail Marquez,
  • Carlos Hurtado-Sanchez,
  • Arnulfo Alanis,
  • Jose Sergio Magdaleno-Palencia

摘要

This study explores the implementation of advanced surface electromyography (sEMG) technologies in medical education and neurorehabilitation, using real datasets to evaluate their effectiveness in both contexts. Two publicly available databases were analyzed: a high-density EMG and EEG dataset from healthy individuals performing reaching tasks with and without robotic assistance, and a clinical dataset involving post-stroke patients undergoing sEMG-driven robotic rehabilitation. In the educational setting, interactive EMG-EEG modules significantly improved medical students’ understanding of neuromuscular physiology, with a 25.9% increase in test scores. In the clinical domain, EMG-based assessments correlated strongly with expert manual evaluations of motor function (r = 0.92 for Fugl-Meyer scores), while muscle activation (RMS amplitude) improved by over 50% after therapy. These findings highlight the dual value of EMG systems for both interactive learning and objective clinical assessment. The study concludes that EMG technologies offer scalable, data-driven solutions to enhance diagnostic precision, support educational innovation, and personalize neurorehabilitation. Future work will focus on integrating EMG with AI and wearable systems for broader applications in remote and adaptive healthcare.