用强化学习提前预测帕金森患者步态冻结，最长可提前8.7秒预警。
Freezing of Gait Prediction using Proactive Agent that Learns from Selected Experience and DDQN Algorithm
- 基于双深度Q网络与优先经验回放，智能体从关键数据中学习
- 跨受试者预测最远达8.72秒前，受试者内预测达7.89秒
- 适合开发可穿戴设备，为帕金森患者提供及时干预
步态冻结（Freezing of Gait, FOG）是帕金森病（Parkinson's Disease, PD）患者常见的严重运动症状，常导致跌倒和活动能力下降。及时准确地预测FOG发作对通过辅助技术实施主动干预至关重要。本研究提出一种基于强化学习的框架，旨在识别最优的预-FOG发作点，从而延长预测窗口。模型采用增强双深度Q网络（DDQN）架构并结合优先经验回放（PER），使智能体聚焦于高影响经验并优化策略。在9000个训练回合中，通过奖励塑形策略促进谨慎决策，该模型在受试者相关与无关评估中均表现出稳健性能。在受试者无关场景下，预测窗口长达8.72秒；受试者相关设置下为7.89秒。结果表明，该模型具备集成至可穿戴辅助设备的潜力，可为PD患者提供及时且个性化的干预方案。
原文摘要 · Abstract (English)
Freezing of Gait (FOG) is a debilitating motor symptom commonly experienced by individuals with Parkinson's Disease (PD) which often leads to falls and reduced mobility. Timely and accurate prediction of FOG episodes is essential for enabling proactive interventions through assistive technologies. This study presents a reinforcement learning-based framework designed to identify optimal pre-FOG onset points, thereby extending the prediction horizon for anticipatory cueing systems. The model implements a Double Deep Q-Network (DDQN) architecture enhanced with Prioritized Experience Replay (PER) allowing the agent to focus learning on high-impact experiences and refine its policy. Trained over 9000 episodes with a reward shaping strategy that promotes cautious decision-making, the agent demonstrated robust performance in both subject-dependent and subject-independent evaluations. The model achieved a prediction horizon of up to 8.72 seconds prior to FOG onset in subject-independent scenarios and 7.89 seconds in subject-dependent settings. These results highlight the model's potential for integration into wearable assistive devices, offering timely and personalized interventions to mitigate FOG in PD patients.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。