ABMA study data and code

The data and code provided here are related to the following paper (currently submitted) :Walking towards the future – Exploring OpenTUG's validity in automatic walking activity analyses and the relationship with cognition in vestibular patients.<br>Vestibular disorders impair body orientation and spatial navigation, often causing cognitive and affective symptoms reducing quality of life. Traditional assessments involve time-consuming physiological and neuropsychological evaluations. This study investigates the feasibility and validity of applying a 2D human pose estimation (OpenTUG) to automatically analyse the walking activity of patients with vestibular disorders trough the Timed-Up &amp; Go (TUG) task.Complementary, the relations between TUG and cognition are explored. Forty-eight patients undergoing treatment for vestibular disorders and 26 mean age-matched controls performed the TUG at normal, slow, and fast walking speeds; neuropsychological evaluations assessing attention (Test for Attentional Performance -TAP-) and quality-of-life questionnaires. Video-recorded TUG performances were analyzed manually and using OpenTUG, which automatically extracted gait parameters. Retrospective neuro-otological and postural data were also reviewed. Both manual and automated analyses showed similar results. Patients took significantly more time and steps to complete the TUG at normal and slow speeds. TUG measures significantly correlated between manual and OpenTUG evaluations for all participants. Patients reported significantly more physical and emotional complaints (DHI, HADS, and NVI-emotion) than controls, but showed no differences in objective neuropsychological tasks. Moderate significant correlations between TUG measures and several measures of postural testing and neuropsychological assessment were observed. These findings demonstrate the feasibility and validity of using OpenTUG to automatically extract clinically relevant gait parameters. The relationship between TUG performance and neuropsychological measures highlights the potential for integrating simple walking tasks with pose estimation as a rapid, cost-effective preliminary assessment of vestibular patient’s difficulties.<br><br>

本文提供的数据与代码关联于下述已投稿（待发表）论文：《迈向未来——探索OpenTUG在前庭障碍患者步行活动自动分析中的有效性及其与认知功能的关联》

前庭功能障碍会损害人体定向与空间导航能力，常伴随认知与情感症状，进而降低生活质量。传统评估方式需开展耗时较长的生理学与神经心理学检查。本研究旨在探究应用二维人体姿态估计技术OpenTUG，通过计时起立行走（Timed-Up & Go, TUG）任务自动分析前庭障碍患者步行活动的可行性与有效性，并同步探索TUG与认知功能间的关联。

本研究共纳入48名接受前庭障碍治疗的患者，以及26名平均年龄与患者组匹配的健康对照受试者，所有受试者分别以正常、慢速与快速三种步行速度完成TUG任务；同时完成了评估注意力的神经心理学检查（注意力性能测试，Test for Attentional Performance, TAP）以及生活质量问卷。研究人员对受试者的TUG任务录像分别进行人工分析与OpenTUG自动分析，该工具可自动提取步态参数。此外，研究团队还回顾分析了受试者的神经耳科学与姿势控制相关回顾性数据。

人工分析与自动化分析结果显示二者具有高度一致性。患者在正常与慢速步行速度下完成TUG任务的完成时长与步数均显著多于对照组。所有受试者的TUG指标在人工评估与OpenTUG自动评估间均呈现显著相关性。患者报告的躯体与情感不适相关量表评分（包括眩晕障碍量表DHI、医院焦虑抑郁量表HADS以及NVI-emotion）均显著高于对照组，但在客观神经心理学任务中未表现出显著差异。研究还观察到TUG指标与多项姿势测试及神经心理学评估指标间存在中等程度的显著相关性。

本研究结果证实了使用OpenTUG自动提取临床相关步态参数的可行性与有效性。TUG任务表现与神经心理学评估指标间的关联，提示可将简单步行任务与姿态估计相结合，作为一种快速、低成本的前庭障碍患者临床初步评估手段，具备潜在应用价值。