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

TL;DR

Extensive testing on publicly available datasets showed that LIFT-PD improved precision and accuracy by 7.25% and accuracy by 4.4% compared to supervised models, while using 40% fewer labeled samples and reducing 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.

Figures (2)

• Figure 1: Self-supervised training pipeline. Pretrain: Encoder reconstructs masked signal segments, outputting predicted values $h_i$ for missing data. Fine-tuning: Encoder weights are frozen while the MLP is optimized using cross-entropy loss on labeled data. Model Activation Module selectively activates the computationally intensive FoG detection model.
• Figure 2: Receiver Operating Characteristic (ROC) curves for supervised and self-supervised models