发表机构
University of Exeter; École Polytechnique Fédérale de Lausanne (EPFL); University of Cambridge; University of Exeter Medical School; NIHR Exeter BRC（埃克塞特大学; 洛桑联邦理工学院; 剑桥大学; 埃克塞特大学医学院; 英国国立卫生研究院埃克塞特生物医学研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究首次提出混合CNN-BiLSTM深度学习框架，用优化的IMU数据集估计帕金森患者垂直地面反作用力，仅需2个IMU即可实现稳健估计，为相关可穿戴系统提供实用方案。
AI 中文摘要
帕金森病（Parkinson's disease, PD）的精准步态分析通常依赖实验室系统捕捉地面反作用力（ground reaction forces, GRFs）等生物力学数据，而使用惯性测量单元（inertial measurement units, IMUs）估计GRFs是可行替代方案。但PD等病理步态因高变异性和复杂性，该方法仍具挑战性；现有监测方法常需多身体传感器，实用性差且患者依从性低，迄今尚无研究将深度学习应用于该挑战。本研究首次提出深度学习框架，使用优化的可穿戴IMU数据集估计PD患者双侧垂直GRFs（vertical GRFs, vGRFs）。采用混合CNN-BiLSTM模型，分别用13个IMU采集的61名PD患者和65名健康对照（healthy controls, HC）数据训练；模型实现高受试者内精度（$R^2$=0.98）和强受试者间泛化能力（HC的$R^2$=0.93，PD的$R^2$=0.91）。传感器配置显著影响估计精度，PD患者与HC的最优传感器布置不同：PD患者减少至单个IMU时精度显著下降，最优配置为4个IMU，仅用2个IMU的最小设置仍能实现稳健估计，该紧凑方案具实用性和可扩展性。总体而言，所提方法支持开发基于可穿戴vGRF的帕金森步态及潜在其他病理状态的步态分析系统，实现可及的临床评估、远程监测和个性化康复。
英文摘要
Accurate gait analysis in Parkinson's disease (PD) typically relies on laboratory-based systems to capture biomechanical data, such as ground reaction forces (GRFs). Estimating GRFs using inertial measurement units (IMUs) provides a feasible alternative. However, this approach remains challenging in pathological gait like PD due to its high variability and complexity. Moreover, existing monitoring approaches often require multiple body-mounted sensors, which limit practicality and reduce patient compliance. To date, no study has investigated the application of deep learning approaches to address this challenge. This study proposes, for the first time, a deep learning framework to estimate bilateral vertical GRFs (vGRFs) in PD using an optimized set of wearable IMUs. A hybrid CNN-BiLSTM model was trained separately on data from 61 PD patients and 65 healthy controls (HC) using 13 IMUs. The model achieved high intra-subject accuracy ($R^2$ = 0.98) and strong inter-subject generalization ($R^2$ = 0.93 for HC, $R^2$ = 0.91 for PD). Sensor configuration was found to significantly influence estimation accuracy, with optimal sensor placement varying between PD patients and HC. For PD patients, estimation accuracy dropped markedly when reducing to a single IMU. The optimal configuration for PD used four IMUs. We identified a minimal setup with only two IMUs still enabled robust estimation. This compact setup offers a practical and scalable solution. Overall, the proposed approach supports the development of wearable vGRF-based gait analysis systems for Parkinsonian gait and potentially other pathological conditions, enabling accessible clinical assessments, remote monitoring, and personalized rehabilitation.
Comments13 pages, 5 figures, 6 tables. Published in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Journal refIEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 34, pp. 2729-2740, 2026
DOI：10.1109/TNSRE.2026.3697513
