Freezing of Gait Prediction using Proactive Agent that Learns from Selected Experience and DDQN Algorithm

2026-03-03

AI Summary

This study addresses the critical need for early prediction of freezing of gait (FOG) in Parkinson’s disease patients to enable proactive interventions and reduce fall risk. The authors propose a reinforcement learning framework based on Double Deep Q-Networks (DDQN), enhanced with Prioritized Experience Replay (PER) and reward shaping to guide the agent toward recognizing high-value precursor signals and making robust decisions. Evaluated in both subject-independent and subject-dependent settings, the method achieves lead times of up to 8.72 seconds and 7.89 seconds, respectively, significantly improving cross-subject generalization. These results demonstrate the framework’s potential to deliver practical, forward-looking FOG warnings suitable for deployment on wearable devices.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Reinforcement Learning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

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.

Problem

• Freezing of Gait
• Parkinson's Disease
• prediction
• assistive technologies
• proactive intervention

Innovation

• Freezing of Gait
• Double Deep Q-Network
• Prioritized Experience Replay
• Reinforcement Learning
• Predictive Horizon