Transfer Learning improves MI BCI models classification accuracy in Parkinson's disease patients
This work addresses the problem of improving neurorehabilitation accuracy for Parkinson's disease patients using BCI, but it is incremental as it builds on existing FBCSP methods with transfer learning.
The study tackled the challenge of low accuracy and time-consuming calibration in Motor-Imagery BCI for Parkinson's disease patients by proposing a multi-session transfer learning method, resulting in a significant median accuracy improvement from 61.1% to 81.3%.
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.