Wearable-Based Real-time Freezing of Gait Detection in Parkinson's Disease Using Self-Supervised Learning

TL;DR

LIFT-PD is a self-supervised learning framework that detects Freezing of Gait in Parkinson's patients in real-time using a single accelerometer, reducing labeled data needs and energy consumption.

Contribution

It introduces a novel self-supervised approach with DHWT and an Opportunistic Inference Module for efficient, real-time FoG detection in PD patients.

Findings

Improved precision by 7.25% over supervised models

Achieved 4.4% higher accuracy

Reduced inference time by 67%

Abstract

LIFT-PD is an innovative self-supervised learning framework developed for real-time detection of Freezing of Gait (FoG) in Parkinson's Disease (PD) patients, using a single triaxial accelerometer. It minimizes the reliance on large labeled datasets by applying a Differential Hopping Windowing Technique (DHWT) to address imbalanced data during training. Additionally, an Opportunistic Inference Module is used to reduce energy consumption by activating the model only during active movement periods. Extensive testing on publicly available datasets showed that LIFT-PD improved precision by 7.25% and accuracy by 4.4% compared to supervised models, while using 40% fewer labeled samples and reducing inference time by 67%. These findings make LIFT-PD a highly practical and energy-efficient solution for continuous, in-home monitoring of PD patients.