P78. Can Phase Lag Index (PLI) be beneficial in distinguishing Parkinsons disease Dementia (PDD) patients from Parkinsons disease (PD) patients?

Abstract

Aims To find the best EEG parameters to discriminate between Parkinson’s disease (PD) and Parkinson’s Disease Dementia (PDD) patients and to evaluate the significance of Phase Lag Index as a parameter for classification of PD and PDD patients, in contrast to the use of frequency-band power measures alone. The study also deals with the challenge of handling imbalanced data for classification. Methods EEG data for a group of 81 PD patients and 19 PDD patients were collected from three centres and analysed using automated segmentation and Inverse Solution post-processing. The PD group was a mix of MCI, Non MCI and unclassified early stage PD patients. 63 Frequency measures and 216 Phase Lag Index measures were obtained for all patients. To overcome the problem of imbalanced data, Random Forest was applied with stratified sampling, in which equal numbers of patients (19) were taken from both the groups for training. This process was repeated 100 times and average AUC measures were obtained. Classification models were built using frequency measures, PLI measures and frequency combined with PLI measures respectively. Results Using 63 frequency measures for classification gave a ROC curve with average AUC value of 0.68. The AUC value increased to 0.75 when using PLI measures alone, which further increased to 0.8 when combining PLI and frequency measures. Further analysis revealed many more PLI measures than frequency measures to be amongst the top features distinguishing the two groups accurately. Conclusion Phase Lag Index measures may contain more information and can be a more accurate way to distinguish PD patients from PDD rather than using EEG band-power measures alone. Furthermore, band-power and PLI measures contain non-redundant information.