MCLPD:Multi-view Contrastive Learning for EEG-based PD Detection Across Datasets
This work addresses the challenge of robust cross-dataset PD detection for medical applications, offering an incremental improvement in generalization with reduced labeled data dependency.
The paper tackles the problem of limited and inconsistent EEG datasets for Parkinson's disease detection by proposing MCLPD, a semi-supervised framework that uses multi-view contrastive pre-training and lightweight fine-tuning, achieving F1 scores of up to 0.97 and 0.87 on cross-dataset tests with only 5% labeled data.
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.