FM-FoG: A Real-Time Foundation Model-based Wearable System for Freezing-of-Gait Mitigation

2025-09-28

AI Summary

To address the limitations of conventional supervised approaches for freezing-of-gait (FoG) detection in Parkinson’s disease—including heavy reliance on patient-specific labeled data, poor cross-subject generalizability, and clinical deployment challenges—this work proposes the first wearable real-time FoG detection system built upon a self-supervised pretrained foundation model. Methodologically, it introduces the first self-supervised pretraining framework for multi-source inertial measurement unit (IMU) signals and integrates activity-context awareness: a lightweight CNN-LSTM classifier is activated only during standing or walking phases. This enables zero-shot cross-patient generalization. Evaluated on the VCU FoG-IMU dataset, the system achieves 98.5% F1-score on unseen subjects. Deployed on mobile devices, it incurs <20 ms inference latency and reduces energy consumption by 72%. By eliminating dependence on subject-specific annotations, this work establishes a novel paradigm for resource-efficient, highly generalizable, and real-time neuromotor disorder monitoring.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Motion & Tracking
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Freezing-of-Gait (FoG) affects over 50% of mid-to-late stage Parkinson's disease (PD) patients, significantly impairing patients' mobility independence and reducing quality of life. FoG is characterized by sudden episodes where walking cannot start or is interrupted, occurring exclusively during standing or walking, and never while sitting or lying down. Current FoG detection systems require extensive patient-specific training data and lack generalization, limiting clinical deployment. To address these issues, we introduce FM-FoG, a real-time foundation model-based wearable system achieving FoG detection in unseen patients without patient-specific training. Our approach combines self-supervised pretraining on diverse Inertial Measurement Unit (IMU) datasets with sensor context integration. Since FoG occurs only during ambulatory activities, a lightweight CNN-LSTM activity classifier selectively activates the foundation model only during walking or standing, avoiding unnecessary computation. Evaluated on the VCU FoG-IMU dataset with 23 PD patients, FM-FoG achieves a 98.5% F1-score when tested on previously unseen patients, substantially outperforming competitive baseline methods. Deployed on a Google Pixel 8a smartphone, the system extends battery life by up to 72% while maintaining sub-20ms intervention latency. The results indicate that our FM-FoG can enable practical, energy-efficient healthcare applications that generalize across patients without individual training requirements.

Problem

• Detects Freezing-of-Gait in unseen Parkinson's patients without individual training
• Eliminates need for extensive patient-specific data to enhance generalization
• Reduces computational load and energy use via selective real-time activation

Innovation

• Foundation model-based wearable system for real-time FoG detection
• Self-supervised pretraining with sensor context integration
• Lightweight activity classifier selectively activates during walking