Transfer Learning improves MI BCI models classification accuracy in Parkinson's disease patients

TL;DR

This paper introduces a transfer learning-based multi-session FBCSP method that significantly enhances classification accuracy in Motor-Imagery Brain-Computer Interfaces for Parkinson's disease patients, addressing calibration challenges.

Contribution

It presents a novel multi-session FBCSP approach utilizing transfer learning, improving MI-BCI calibration accuracy in Parkinson's disease patients over single-session methods.

Findings

Significantly higher median accuracy with msFBCSP (81.3%) compared to single-session FBCSP (61.1%).

Statistical significance with p<0.001 for accuracy improvement.

Demonstrates effectiveness of transfer learning in multi-session MI-BCI calibration.

Abstract

Motor-Imagery based BCI (MI-BCI) neurorehabilitation can improve locomotor ability and reduce the deficit symptoms in Parkinson's Disease patients. Advanced Motor-Imagery BCI methods are needed to overcome the accuracy and time-related MI BCI calibration challenges in such patients. In this study, we proposed a Multi-session FBCSP (msFBCSP) based on inter-session transfer learning and we investigated its performance compared to the single-session based FBSCP. The main result of this study is the significantly improved accuracy obtained by proposed msFBCSP compared to single-session FBCSP in PD patients (median 81.3%, range 41.2-100.0% vs median 61.1%, range 25.0-100.0%, respectively; p<0.001). In conclusion, this study proposes a transfer learning-based multi-session based FBCSP approach which allowed to significantly improve calibration accuracy in MI BCI performed on PD patients.