Addressing Multiple Challenges in Early Gait Freezing Prediction for Parkinson's Disease: A Practical Deep Learning Approach.

Abstract

Freezing of Gait (FOG) significantly impacts daily activities of Parkinson's disease (PD) patients. Despite the potential of wearable sensors in predicting FOG, challenges persist, including the brief prediction interval before FOG onset, limited generalization across patients, and the inconvenience of multiple sensors. Addressing one issue often aggravates others, making it difficult to achieve suitable concurrent solutions to all these challenges. We introduce the PhysioGait Predictive Network (PhysioGPN), a deep learning framework designed to predict FOG events in PD patients at least 2 seconds prior to onset. The model architecture incorporates four key strategies: 1) Detection of progressive motion changes using large convolutional kernels; 2) Unraveling the complexity of motion coordination and gait dynamics using multi-dimensional and multi-scale convolution; 3) Capture gait self-similarity and asymmetry with twin-tower structure; 4) Promoting cross-domain information exchange with multi-domain attention. Furthermore, we propose a framework based on knowledge distillation (KD), reducing the model's dependence on multiple sensors while maintaining prediction accuracy. The model achieves an 85.8% Area Under the Curve (AUC) in FOG prediction. When reducing the number of sensors, KD mitigates the decline in performance and increases the AUC by 5.1%, compared to scenarios without KD. Our research proposes a practical solution to the challenges of FOG prediction, demonstrating the effectiveness of the KD approach for lightweight wearable sensors in rehabilitation engineering. Our findings offer valuable insights for addressing multiple challenges in the practical application of wearable devices.