Machine learning trained with quantitative susceptibility mapping to detect mild cognitive impairment in Parkinson's disease

This preliminary study mainly compared the performance for predicting mild cognitive impairment in Parkinson’s disease (PDMCI) between single machine learning and hybrid machine learning. This study analyzed 185 patients with Parkinson’s disease (75 Parkinson’s disease) patients with normal cognition, and 110 patients with PDMCI. PDMCI, an outcome variable, was divided into “with PDMCI” and “with normal cognition” according to the diagnosis of the neurologist. This study used 48 variables (diagnostic data), including motor symptoms of Parkinson’s disease, non-motor symptoms of Parkinson’s disease, and sleep disorders, as explanatory variables. This study developed seven machine learning models using blending (three hybrid models (polydot + C5.0, vanilladot + C5.0, and RBFdot + C5.0) and four single machine learning models (polydot, vanilladot, RBFdot, and C5.0)). The results of this study showed that the RBFdot + C5.0 was the model with the best performance to predict PDMCI in Parkinson’s disease patients with normal cognition (AUC = 0.88) among the seven machine learning models. We will develop interpretable machine learning using C5.0 in a follow-up study based on the results of this study.

Download Full-text

Effective Connectivity in the Limbic System in Parkinson's Disease with Mild Cognitive Impairment

SSRN Electronic Journal ◽

10.2139/ssrn.3506114 ◽

2019 ◽

Author(s):

Binyin Li ◽

Liche Zhou ◽

Wenyan Kang ◽

Lina Zhang ◽

Guanyu Ye ◽

...

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Cognitive Impairment ◽

Mild Cognitive Impairment ◽

Limbic System ◽

Effective Connectivity

Download Full-text

Assessment of White Matter Lesions in Parkinson's Disease: Voxel-based Analysis and Tract-based Spatial Statistics Analysis of Parkinson's Disease with Mild Cognitive Impairment

Current Neurovascular Research ◽

10.2174/1567202617666200901181842 ◽

2020 ◽

Vol 17 (4) ◽

pp. 480-486

Author(s):

Wei Pu ◽

Xudong Shen ◽

Mingming Huang ◽

Zhiqian Li ◽

Xianchun Zeng ◽

...

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Cognitive Impairment ◽

Mild Cognitive Impairment ◽

White Matter ◽

Corpus Callosum ◽

Fractional Anisotropy ◽

Spatial Statistics ◽

Diffusion Tensor ◽

Tract Based Spatial Statistics

Objective: Application of diffusion tensor imaging (DTI) to explore the changes of FA value in patients with Parkinson's disease (PD) with mild cognitive impairment. Methods: 27 patients with PD were divided into PD with mild cognitive impairment (PD-MCI) group (n = 7) and PD group (n = 20). The original images were processed using voxel-based analysis (VBA) and tract-based spatial statistics (TBSS). Results: The average age of pd-mci group was longer than that of PD group, and the course of disease was longer than that of PD group. Compared with PD group, the voxel based analysis-fractional anisotropy (VBA-FA) values of PD-MCI group decreased in the following areas: bilateral frontal lobe, bilateral temporal lobe, bilateral parietal lobe, bilateral subthalamic nucleus, corpus callosum, and gyrus cingula. Tract-based spatial statistics-fractional anisotropy (TBSS-FA) values in PD-MCI group decreased in bilateral corticospinal tract, anterior cingulum, posterior cingulum, fornix tract, bilateral superior thalamic radiation, corpus callosum(genu, body and splenium), bilateral uncinate fasciculus, bilateral inferior longitudinal fasciculus, bilateral superior longitudinal fasciculus, bilateral superior fronto-occipital fasciculus, bilateral inferior fronto-occipital fasciculus, and bilateral parietal-occipital tracts. The mean age of onset in the PD-MCI group was greater than that in the PD group, and the disease course was longer than that in the PD group. Conclusion: DTI-based VBA and TBSS post-processing methods can detect abnormalities in multiple brain areas and white matter fiber tracts in PD-MCI patients. Impairment of multiple cerebral cortex and white matter fiber pathways may be an important causes of cognitive dysfunction in PD-MCI.

Download Full-text

Donepezil for mild cognitive impairment in Parkinson’s disease

Scientific Reports ◽

10.1038/s41598-021-84243-4 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Kyoungwon Baik ◽

Seon Myeong Kim ◽

Jin Ho Jung ◽

Yang Hyun Lee ◽

Seok Jong Chung ◽

...

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Cognitive Impairment ◽

Mild Cognitive Impairment ◽

Treatment Group ◽

Outcome Measures ◽

Rating Scale ◽

Secondary Outcome ◽

Control Group ◽

Significant Difference

AbstractWe investigated the efficacy of donepezil for mild cognitive impairment in Parkinson’s disease (PD-MCI). This was a prospective, non-randomized, open-label, two-arm study. Eighty PD-MCI patients were assigned to either a treatment or control group. The treatment group received donepezil for 48 weeks. The primary outcome measures were the Korean version of Mini-Mental State Exam and Montreal Cognitive Assessment scores. Secondary outcome measures were the Clinical Dementia Rating, Unified Parkinson’s Disease Rating Scale part III, Clinical Global Impression scores. Progression of dementia was assessed at 48-week. Comprehensive neuropsychological tests and electroencephalography (EEG) were performed at baseline and after 48 weeks. The spectral power ratio of the theta to beta2 band (TB2R) in the electroencephalogram was analyzed. There was no significant difference in the primary and secondary outcome measures between the two groups. However, the treatment group showed a significant decrease in TB2R at bilateral frontotemporoparietal channels compared to the control group. Although we could not demonstrate improvements in the cognitive functions, donepezil treatment had a modulatory effect on the EEG in PD-MCI patients. EEG might be a sensitive biomarker for detecting changes in PD-MCI after donepezil treatment.

Download Full-text

Analyses of Visuospatial and Visuoperceptual Errors as Predictors of Dementia in Parkinson’s Disease Patients with Subjective Cognitive Decline and Mild Cognitive Impairment

Journal of the International Neuropsychological Society ◽

10.1017/s1355617720001216 ◽

2020 ◽

pp. 1-11

Author(s):

Iván Galtier ◽

Antonieta Nieto ◽

María Mata ◽

Jesús N. Lorenzo ◽

José Barroso

Keyword(s):

Risk Factors ◽

Parkinson’S Disease ◽

Parkinson's Disease ◽

Cognitive Impairment ◽

Mild Cognitive Impairment ◽

Cognitive Decline ◽

Poor Performance ◽

Subjective Cognitive Decline ◽

Independent Risk Factors

ABSTRACT Objective: Subjective cognitive decline (SCD) and mild cognitive impairment (MCI) in Parkinson’s disease (PD) are considered as the risk factors for dementia (PDD). Posterior cortically based functions, such as visuospatial and visuoperceptual (VS-VP) processing, have been described as predictors of PDD. However, no investigations have focused on the qualitative analysis of the Judgment of Line Orientation Test (JLOT) and the Facial Recognition Test (FRT) in PD-SCD and PD-MCI. The aim of this work was to study the VS-VP errors in JLOT and FRT. Moreover, these variables are considered as predictors of PDD. Method: Forty-two PD patients and 19 controls were evaluated with a neuropsychological protocol. Patients were classified as PD-SCD and PD-MCI. Analyses of errors were conducted following the procedure described by Ska, Poissant, and Joanette (1990). Follow-up assessment was conducted to a mean of 7.5 years after the baseline. Results: PD-MCI patients showed a poor performance in JLOT and FRT total score and made a greater proportion of severe intraquadrant (QO2) and interquadrant errors (IQO). PD-SCD showed a poor performance in FRT and made mild errors in JLOT. PD-MCI and QO2/IQO errors were independent risk factors for PDD during the follow-up. Moreover, the combination of both PD-MCI diagnosis and QO2/IQO errors was associated with a greater risk. Conclusions: PD-MCI patients presented a greater alteration in VS-VP processing observable by the presence of severe misjudgments. PD-SCD patients also showed mild difficulties in VS-SP functions. Finally, QO2/IQO errors in PD-MCI are a useful predictor of PDD, more than PD-MCI diagnosis alone.

Download Full-text