MCLPD:Multi-view Contrastive Learning for EEG-based PD Detection Across Datasets

TL;DR

This paper introduces MCLPD, a semi-supervised multi-view contrastive learning framework that significantly improves cross-dataset Parkinson's disease detection from EEG data with minimal labeled samples.

Contribution

It proposes a novel semi-supervised contrastive learning approach combining multi-view pre-training and lightweight fine-tuning for robust cross-dataset PD detection.

Findings

Achieves F1 scores of 0.91 and 0.81 with only 1% labeled data.

Further improves to 0.97 and 0.87 with 5% labeled data.

Substantially enhances cross-dataset generalization and reduces labeled data dependency.

Abstract

Electroencephalography has been validated as an effective technique for detecting Parkinson's disease,particularly in its early stages.However,the high cost of EEG data annotation often results in limited dataset size and considerable discrepancies across datasets,including differences in acquisition protocols and subject demographics,significantly hinder the robustness and generalizability of models in cross-dataset detection scenarios.To address such challenges,this paper proposes a semi-supervised learning framework named MCLPD,which integrates multi-view contrastive pre-training with lightweight supervised fine-tuning to enhance cross-dataset PD detection performance.During pre-training,MCLPD uses self-supervised learning on the unlabeled UNM dataset.To build contrastive pairs,it applies dual augmentations in both time and frequency domains,which enrich the data and naturally fuse time-frequency information.In the fine-tuning phase,only a small proportion of labeled data from another two datasets (UI and UC)is used for supervised optimization.Experimental results show that MCLPD achieves F1 scores of 0.91 on UI and 0.81 on UC using only 1%of labeled data,which further improve to 0.97 and 0.87,respectively,when 5%of labeled data is used.Compared to existing methods,MCLPD substantially improves cross-dataset generalization while reducing the dependency on labeled data,demonstrating the effectiveness of the proposed framework.