An SBM-based machine learning model for identifying mild cognitive impairment in patients with Parkinson's disease

Abstract

Objective: To identify Parkinson's disease with mild cognitive impairment (PD-MCI) through surface-based morphometry (SBM) based machine learning model.

Methods: 93 patients with parkinson's disease (35 PD with normal cognition, 58 PD-MCI) were examined, obtaining 276 SBM variables per subject. 20 healthy control subjects were used as the reference. After extracting features with statistically significance, support vector machine (SVM) model with grid search method was applied to identify patients with PD-MCI. Accuracy, matthews correlation coefficient (MCC), receiver operating characteristic curve (ROC), precision-recall curve (PR), AUC-ROC, AUC-PR and leave-one-out cross validation (LOOCV) strategy were employed for model evaluation.

Results: PD-MCI is characterized by widespread structural abnormality. SVM model with SBM features achieved an accuracy of 80.00% and area under the ROC of 0.86 for identifying PD-MCI. MCC, AUC-PR, and LOOCV classification accuracy were 0.56, 0.89, and 78.08%, respectively.

Conclusion: Automatic identification of PD-MCI could be realized by SBM-based machine learning model.

Keywords: Machine learning; Mild cognitive impairment; Parkinson's disease; Support vector machine; Surface-based morphometry.