Scholarlink

<p>Assessment of human gait is a useful diagnostic tool for identifying musculoskeletal abnormalities and disorders. Most clinicians use qualitative approaches based on visual observations to analyze gait, leading to repetitive exercises that require subjective evaluation. This study proposes a system to automate and objectify traditional observational gait tests using a transformer encoder network that analyzes data captured with a 3D optical motion system. This preliminary study focused on the Tinetti test, or Performance-Oriented Mobility Assessment for gait evaluation (POMA-G), using data collected with an OptiTrack camera system. An optical motion capture system consisting of eight OptiTrack Prime 13-W cameras, sampled at 60 Hz and synchronized with the Clinical 3D Motion Analysis (3DMA) software was used. Anthropometric measurements of the participants were recorded and their gait movements were captured while simulating various pathologies evaluated in the POMA-G test. The algorithms were designed and implemented in an artificial neural network model based on transformer process information to monitor and classify the gait components. On average, the machine learning models achieved an accuracy of 97.56% ± 4.79%, F1 score of 96.39% ± 7.95%, and area under the receiver operating characteristic curve (AUC-ROC) value of 99.29% ± 1.81%, demonstrating a high capability to identify and classify the gait components evaluated using the POMA-G scale. Automating the observational evaluation of gait using a 3D optical motion system and machine learning methods offers a quantitative and objective approach to gait analysis. This system not only promises to facilitate more accurate diagnoses and effectively monitor gait-related disorders, but also highlights the potential of motion capture technology and machine learning for clinical gait assessment. This study establishes a foundation for future research aimed at improving the accuracy and applicability of automatic gait assessment tools.</p>

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

Automation of observational gait assessment through an optical 3D motion system and transformers

  • 期刊论文

  • 发表日期：

    2025年1月2日

查看全文
  • David Carneros-Prado,
  • Sergio González-Velázquez,
  • Cosmin C. Dobrescu,
  • Iván González,
  • Jesús Fontecha,
  • Ramón Hervás

摘要

Assessment of human gait is a useful diagnostic tool for identifying musculoskeletal abnormalities and disorders. Most clinicians use qualitative approaches based on visual observations to analyze gait, leading to repetitive exercises that require subjective evaluation. This study proposes a system to automate and objectify traditional observational gait tests using a transformer encoder network that analyzes data captured with a 3D optical motion system. This preliminary study focused on the Tinetti test, or Performance-Oriented Mobility Assessment for gait evaluation (POMA-G), using data collected with an OptiTrack camera system. An optical motion capture system consisting of eight OptiTrack Prime 13-W cameras, sampled at 60 Hz and synchronized with the Clinical 3D Motion Analysis (3DMA) software was used. Anthropometric measurements of the participants were recorded and their gait movements were captured while simulating various pathologies evaluated in the POMA-G test. The algorithms were designed and implemented in an artificial neural network model based on transformer process information to monitor and classify the gait components. On average, the machine learning models achieved an accuracy of 97.56% ± 4.79%, F1 score of 96.39% ± 7.95%, and area under the receiver operating characteristic curve (AUC-ROC) value of 99.29% ± 1.81%, demonstrating a high capability to identify and classify the gait components evaluated using the POMA-G scale. Automating the observational evaluation of gait using a 3D optical motion system and machine learning methods offers a quantitative and objective approach to gait analysis. This system not only promises to facilitate more accurate diagnoses and effectively monitor gait-related disorders, but also highlights the potential of motion capture technology and machine learning for clinical gait assessment. This study establishes a foundation for future research aimed at improving the accuracy and applicability of automatic gait assessment tools.