Bi-cephalic self-attended model to classify Parkinson's disease patients with freezing of gait

2025-07-28

AI Summary

Current freezing of gait (FoG) diagnosis in Parkinson’s disease suffers from high subjectivity and reliance on specialized equipment. To address this, we propose BiSAM—a lightweight, multimodal classification framework that jointly models sparse resting-state electroencephalography (EEG) (4 or 8 channels) and clinical-demographic variables (e.g., age, disease duration) via a dual-branch self-attention architecture. This design enables resource-efficient, interpretable feature fusion without requiring dense neuroimaging or extensive computational infrastructure. Evaluated on a cohort of 124 patients, BiSAM-4 and BiSAM-8 achieve 88% classification accuracy—significantly outperforming unimodal baselines. To our knowledge, this is the first study to demonstrate that FoG can be robustly identified using only sparse EEG combined with readily available clinical metadata. BiSAM thus provides a deployable, scalable, and objective tool for primary-care screening and longitudinal monitoring of FoG.

Technology Category

• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements

Abstract

Parkinson Disease (PD) often results in motor and cognitive impairments, including gait dysfunction, particularly in patients with freezing of gait (FOG). Current detection methods are either subjective or reliant on specialized gait analysis tools. This study aims to develop an objective, data-driven, and multi-modal classification model to detect gait dysfunction in PD patients using resting-state EEG signals combined with demographic and clinical variables. We utilized a dataset of 124 participants: 42 PD patients with FOG (PDFOG+), 41 without FOG (PDFOG-), and 41 age-matched healthy controls. Features extracted from resting-state EEG and descriptive variables (age, education, disease duration) were used to train a novel Bi-cephalic Self-Attention Model (BiSAM). We tested three modalities: signal-only, descriptive-only, and multi-modal, across different EEG channel subsets (BiSAM-63, -16, -8, and -4). Signal-only and descriptive-only models showed limited performance, achieving a maximum accuracy of 55% and 68%, respectively. In contrast, the multi-modal models significantly outperformed both, with BiSAM-8 and BiSAM-4 achieving the highest classification accuracy of 88%. These results demonstrate the value of integrating EEG with objective descriptive features for robust PDFOG+ detection. This study introduces a multi-modal, attention-based architecture that objectively classifies PDFOG+ using minimal EEG channels and descriptive variables. This approach offers a scalable and efficient alternative to traditional assessments, with potential applications in routine clinical monitoring and early diagnosis of PD-related gait dysfunction.

Problem

• Classify Parkinson's disease patients with freezing of gait
• Develop objective multi-modal model using EEG signals
• Improve detection accuracy with minimal EEG channels

Innovation

• Bi-cephalic self-attention model for EEG analysis
• Multi-modal integration of EEG and clinical data
• Minimal EEG channels for high classification accuracy