Modeling, Detecting, and Tracking Freezing of Gait in Parkinson Disease Using Inertial Sensors

Area of Science:

• Biomedical Engineering
• Neurology
• Wearable Technology

Background:

• Freezing of gait (FOG) is a debilitating symptom in Parkinson disease (PD), significantly impacting mobility and quality of life.
• Accurate, real-time detection of FOG events is crucial for developing effective interventions and monitoring disease progression.

Purpose of the Study:

• To develop and validate a novel, real-time system for automatic detection of FOG onset and duration in individuals with PD.
• To enhance the accuracy and reduce the false-alarm rate of FOG detection compared to existing methods.

Main Methods:

• Development of a physical model for FOG-related trembling motion.
• Design of a generalized likelihood ratio test framework for detecting zero-velocity and trembling events.
• Implementation of a point-process filter integrating gait speed data from an inertial navigation system to refine FOG detection.

Main Results:

• The proposed system achieved 81.03% accuracy in detecting FOG events.
• A threefold decrease in the false-alarm rate was observed compared to a method using only accelerometer data.
• Validation performed using real-world data from PD patients during various gait tasks.

Conclusions:

• The developed system offers a robust and accurate method for real-time FOG detection in Parkinson disease.
• This technology has the potential to improve clinical monitoring and the development of personalized FOG management strategies.