Machine learning trained with quantitative susceptibility mapping to detect mild cognitive impairment in Parkinson's disease. (January 2022)

• Record Type: Journal Article
• Authors: Shibata, Haruto; Uchida, Yuto; Inui, Shohei; Kan, Hirohito; Sakurai, Keita; Oishi, Naoya; Ueki, Yoshino; Oishi, Kenichi; Matsukawa, Noriyuki
• Is Part Of: Parkinsonism & related disorders. Volume 94(2022)
• Page Start: 104
• Page End: 110
• Publication Date: 2022-01
• Subjects: Machine learning -- Mild cognitive impairment -- MRI -- Parkinson's disease -- Quantitative susceptibility mapping; Parkinson's disease -- Periodicals; Movement disorders -- Periodicals; Movement Disorders -- Periodicals; Nerve Degeneration -- Periodicals; Nervous System Diseases -- Periodicals; Parkinson Disease -- Periodicals; Tremor -- Periodicals; Parkinson, Maladie de -- Périodiques; Parkinson's disease; 616.833
• DOI: 10.1016/j.parkreldis.2021.12.004
• Languages: English
• ISSNs: 1353-8020

Abstract

Abstract: Background: Cognitive decline is commonly observed in Parkinson's disease (PD). Identifying PD with mild cognitive impairment (PD-MCI) is crucial for early initiation of therapeutic interventions and preventing cognitive decline. Objective: We aimed to develop a machine learning model trained with magnetic susceptibility values based on the multi-atlas label-fusion method to classify PD without dementia into PD-MCI and normal cognition (PD-CN). Methods: This multicenter observational cohort study retrospectively reviewed 61 PD-MCI and 59 PD-CN cases for the internal validation cohort and 22 PD-MCI and 21 PD-CN cases for the external validation cohort. The multi-atlas method parcellated the quantitative susceptibility mapping (QSM) images into 20 regions of interest and extracted QSM-based magnetic susceptibility values. Random forest, extreme gradient boosting, and light gradient boosting were selected as machine learning algorithms. Results: All classifiers demonstrated substantial performances in the classification task, particularly the random forest model. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve for this model were 79.1%, 77.3%, 81.0%, and 0.78, respectively. The QSM values in the caudate nucleus, which were important features, were inversely correlated with the Montreal Cognitive Assessment scores (right caudate nucleus: r = −0.573, 95% CI: −0.801 to −0.298, p = 0.003; left caudate nucleus: r = −0.659, 95% CI: −0.894 to −0.392, p < 0.001). Conclusions: Machine learning models trained with QSM values successfully classified PD without dementia into PD-MCI and PD-CN groups, suggesting the potential of QSM values as an auxiliary biomarker for early evaluation of cognitive decline in patients with PD. Highlights: The multi-atlas label-fusion method could reliably extract QSM values. Machine learning model trained with QSM values could detect PD-MCI. QSM values in the caudate nucleus were inversely correlated with the MoCA scores.