Scholarlink

<p>Fall risk threatens independence in Parkinson’s disease (PD), particularly under combined cognitive–motor demands. This study proposes a video-based artificial intelligence (AI) framework to identify the most sensitive dual-task condition of the Four-Square Step Test (FSST) for fall-risk assessment. Thirty PD patients were recorded with a fixed RGB camera performing the FSST under single-task and three dual-task conditions: reciting days backward, holding a glass of water, and ball transfer. From each recording, silhouette masks and skeleton keypoints were extracted and fused into frame-level embeddings, fed into a multitask temporal convolutional network (TCN) jointly predicting task type and binary fall-risk. Videos were labeled high or low fall-risk using the clinician-measured 9.68&#xa0;s threshold; model weights were initialized via transfer learning from 40 healthy adults. Clinically, completion times correlated with the Timed Up and Go test (<InlineEquation ID="IEq1"><EquationSource Format="TEX">\(r = 0.50\)</EquationSource></InlineEquation>–0.66, <InlineEquation ID="IEq2"><EquationSource Format="TEX">\(p &lt; 0.01\)</EquationSource></InlineEquation>), and the reciting-days condition showed the strongest cognitive association (Montreal Cognitive Assessment, <InlineEquation ID="IEq3"><EquationSource Format="TEX">\(r = -0.48\)</EquationSource></InlineEquation>, <InlineEquation ID="IEq4"><EquationSource Format="TEX">\(p = 0.006\)</EquationSource></InlineEquation>), supporting construct validity. From the AI model, the holding-a-glass condition achieved the highest fall-risk discrimination under transfer learning, as assessed by F1-score and AUROC, and the model-derived cutoff (9.65&#xa0;s) matched the 9.68&#xa0;s threshold. These findings suggest dual-task design enhances fall-risk sensitivity. Pending larger-scale validation, this framework may offer a scalable, video-based approach for fall-risk screening in PD.</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

Video-based dual-task Four-Square Step Test for fall risk assessment in Parkinson’s disease

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月22日

查看全文
  • Ilhan Aytutuldu,
  • Guzin Kaya Aytutuldu,
  • Ezgi Eryildiz,
  • Ali Furkan Sanli,
  • Burcu Ersoz Huseyinsinoglu,
  • Yusuf Sinan Akgul,
  • Nazan Karagoz Sakalli

摘要

Fall risk threatens independence in Parkinson’s disease (PD), particularly under combined cognitive–motor demands. This study proposes a video-based artificial intelligence (AI) framework to identify the most sensitive dual-task condition of the Four-Square Step Test (FSST) for fall-risk assessment. Thirty PD patients were recorded with a fixed RGB camera performing the FSST under single-task and three dual-task conditions: reciting days backward, holding a glass of water, and ball transfer. From each recording, silhouette masks and skeleton keypoints were extracted and fused into frame-level embeddings, fed into a multitask temporal convolutional network (TCN) jointly predicting task type and binary fall-risk. Videos were labeled high or low fall-risk using the clinician-measured 9.68 s threshold; model weights were initialized via transfer learning from 40 healthy adults. Clinically, completion times correlated with the Timed Up and Go test (\(r = 0.50\)–0.66, \(p < 0.01\)), and the reciting-days condition showed the strongest cognitive association (Montreal Cognitive Assessment, \(r = -0.48\), \(p = 0.006\)), supporting construct validity. From the AI model, the holding-a-glass condition achieved the highest fall-risk discrimination under transfer learning, as assessed by F1-score and AUROC, and the model-derived cutoff (9.65 s) matched the 9.68 s threshold. These findings suggest dual-task design enhances fall-risk sensitivity. Pending larger-scale validation, this framework may offer a scalable, video-based approach for fall-risk screening in PD.