The Neuropsychological Profile of Mild Cognitive Impairment in Lewy Body Dementias

Differentiating Prodromal Dementia with Lewy Bodies from Prodromal Alzheimer's Disease: A Pragmatic Review for Clinicians

This pragmatic review synthesises the current understanding of prodromal dementia with Lewy bodies (pDLB) and prodromal Alzheimer's disease (pAD), including clinical presentations, neuropsychological profiles, neuropsychiatric symptoms, biomarkers, and indications for disease management. The core clinical features of dementia with Lewy bodies (DLB)-parkinsonism, complex visual hallucinations, cognitive fluctuations, and REM sleep behaviour disorder are common prodromal symptoms. Supportive clinical features of pDLB include severe neuroleptic sensitivity, as well as autonomic and neuropsychiatric symptoms. The neuropsychological profile in mild cognitive impairment attributable to Lewy body pathology (MCI-LB) tends to include impairment in visuospatial skills and executive functioning, distinguishing it from MCI due to AD, which typically presents with impairment in memory. pDLB may present with cognitive impairment, psychiatric symptoms, and/or recurrent episodes of delirium, indicating that it is not necessarily synonymous with MCI-LB. Imaging, fluid and other biomarkers may play a crucial role in differentiating pDLB from pAD. The current MCI-LB criteria recognise low dopamine transporter uptake using positron emission tomography or single photon emission computed tomography (SPECT), loss of REM atonia on polysomnography, and sympathetic cardiac denervation using meta-iodobenzylguanidine SPECT as indicative biomarkers with slowing of dominant frequency on EEG among others as supportive biomarkers. This review also highlights the emergence of fluid and skin-based biomarkers. There is little research evidence for the treatment of pDLB, but pharmacological and non-pharmacological treatments for DLB may be discussed with patients. Non-pharmacological interventions such as diet, exercise, and cognitive stimulation may provide benefit, while evaluation and management of contributing factors like medications and sleep disturbances are vital. There is a need to expand research across diverse patient populations to address existing disparities in clinical trial participation. In conclusion, an early and accurate diagnosis of pDLB or pAD presents an opportunity for tailored interventions, improved healthcare outcomes, and enhanced quality of life for patients and care partners.

Integrating Biomarkers From Virtual Reality and Magnetic Resonance Imaging for the Early Detection of Mild Cognitive Impairment Using a Multimodal Learning Approach: Validation Study

BACKGROUND

Early detection of mild cognitive impairment (MCI), a transitional stage between normal aging and Alzheimer disease, is crucial for preventing the progression of dementia. Virtual reality (VR) biomarkers have proven to be effective in capturing behaviors associated with subtle deficits in instrumental activities of daily living, such as challenges in using a food-ordering kiosk, for early detection of MCI. On the other hand, magnetic resonance imaging (MRI) biomarkers have demonstrated their efficacy in quantifying observable structural brain changes that can aid in early MCI detection. Nevertheless, the relationship between VR-derived and MRI biomarkers remains an open question. In this context, we explored the integration of VR-derived and MRI biomarkers to enhance early MCI detection through a multimodal learning approach.

OBJECTIVE

We aimed to evaluate and compare the efficacy of VR-derived and MRI biomarkers in the classification of MCI while also examining the strengths and weaknesses of each approach. Furthermore, we focused on improving early MCI detection by leveraging multimodal learning to integrate VR-derived and MRI biomarkers.

METHODS

The study encompassed a total of 54 participants, comprising 22 (41%) healthy controls and 32 (59%) patients with MCI. Participants completed a virtual kiosk test to collect 4 VR-derived biomarkers (hand movement speed, scanpath length, time to completion, and the number of errors), and T1-weighted MRI scans were performed to collect 22 MRI biomarkers from both hemispheres. Analyses of covariance were used to compare these biomarkers between healthy controls and patients with MCI, with age considered as a covariate. Subsequently, the biomarkers that exhibited significant differences between the 2 groups were used to train and validate a multimodal learning model aimed at early screening for patients with MCI among healthy controls.

RESULTS

The support vector machine (SVM) using only VR-derived biomarkers achieved a sensitivity of 87.5% and specificity of 90%, whereas the MRI biomarkers showed a sensitivity of 90.9% and specificity of 71.4%. Moreover, a correlation analysis revealed a significant association between MRI-observed brain atrophy and impaired performance in instrumental activities of daily living in the VR environment. Notably, the integration of both VR-derived and MRI biomarkers into a multimodal SVM model yielded superior results compared to unimodal SVM models, achieving higher accuracy (94.4%), sensitivity (100%), specificity (90.9%), precision (87.5%), and F1-score (93.3%).

CONCLUSIONS

The results indicate that VR-derived biomarkers, characterized by their high specificity, can be valuable as a robust, early screening tool for MCI in a broader older adult population. On the other hand, MRI biomarkers, known for their high sensitivity, excel at confirming the presence of MCI. Moreover, the multimodal learning approach introduced in our study provides valuable insights into the improvement of early MCI detection by integrating a diverse set of biomarkers.

Striato-cortical functional connectivity changes in mild cognitive impairment with Lewy bodies

BACKGROUND

Functional connectivity changes in clinically overt neurodegenerative diseases such as dementia with Lewy bodies have been described, but studies on connectivity changes in the pre-dementia phase are scarce.

OBJECTIVES

We concentrated on evaluating striato-cortical functional connectivity differences between patients with Mild Cognitive Impairment with Lewy bodies and healthy controls and on assessing the relation to cognition.

METHODS

Altogether, we enrolled 77 participants (47 patients, of which 35 met all the inclusion criteria for the final analysis, and 30 age- and gender-matched healthy controls, of which 28 met all the inclusion criteria for the final analysis) to study the seed-based connectivity of the dorsal, middle, and ventral striatum. We assessed correlations between functional connectivity in the regions of between-group differences and neuropsychological scores of interest (visuospatial and executive domains z-scores).

RESULTS

Subjects with Mild Cognitive Impairment with Lewy Bodies, as compared to healthy controls, showed increased connectivity from the dorsal part of the striatum particularly to the bilateral anterior part of the temporal cortex with an association with executive functions.

CONCLUSIONS

We were able to capture early abnormal connectivity within cholinergic and noradrenergic pathways that correlated with cognitive functions known to be linked to cholinergic/noradrenergic deficits. The knowledge of specific alterations may improve our understanding of early neural changes in pre-dementia stages and enhance research of disease modifying therapy.

A clinical 3D pointing test differentiates spatial memory deficits in dementia and bilateral vestibular failure

BACKGROUND

Deficits in spatial memory, orientation, and navigation are often neglected early signs of cognitive impairment or loss of vestibular function. Real-world navigation tests require complex setups. In contrast, simple pointing at targets in a three-dimensional environment is a basic sensorimotor ability which provides an alternative measure of spatial orientation and memory at bedside. The aim of this study was to test the reliability of a previously established 3D-Real-World Pointing Test (3D-RWPT) in patients with cognitive impairment due to different neurodegenerative disorders, bilateral vestibulopathy, or a combination of both compared to healthy participants.

METHODS

The 3D-RWPT was performed using a static array of targets in front of the seated participant before and, as a transformation task, after a 90-degree body rotation around the yaw-axis. Three groups of patients were enrolled: (1) chronic bilateral vestibulopathy (BVP) with normal cognition (n = 32), (2) cognitive impairment with normal vestibular function (n = 28), and (3) combined BVP and cognitive impairment (n = 9). The control group consisted of age-matched participants (HP) without cognitive and vestibular deficits (n = 67). Analyses focused on paradigm-specific mean angular deviation of pointing in the azimuth (horizontal) and polar (vertical) spatial planes, of the preferred pointing strategy (egocentric or allocentric), and the resulting shape configuration of the pointing array relative to the stimulus array. Statistical analysis was performed using age-corrected ANCOVA-testing with Bonferroni correction and correlation analysis using Spearman's rho.

RESULTS

Patients with cognitive impairment employed more egocentric pointing strategies while patients with BVP but normal cognition and HP used more world-based solutions (pBonf 5.78 × 10-3**). Differences in pointing accuracy were only found in the azimuth plane, unveiling unique patterns where patients with cognitive impairment showed decreased accuracy in the transformation tasks of the 3D-RWPT (pBonf < 0.001***) while patients with BVP struggled in the post-rotation tasks (pBonf < 0.001***). Overall azimuth pointing performance was still adequate in some patients with BVP but significantly decreased when combined with a cognitive deficit.

CONCLUSION

The 3D-RWPT provides a simple and fast measure of spatial orientation and memory. Cognitive impairment often led to a shift from world-based allocentric pointing strategy to an egocentric performance with less azimuth accuracy compared to age-matched controls. This supports the view that cognitive deficits hinder the mental buildup of the stimulus pattern represented as a geometrical form. Vestibular hypofunction negatively affected spatial memory and pointing performance in the azimuth plane. The most severe spatial impairments (angular deviation, figure frame configuration) were found in patients with combined cognitive and vestibular deficits.

Predicting cognitive decline using neuropsychiatric symptoms in prodromal Lewy body dementia: A longitudinal study

INTRODUCTION

Neuropsychiatric symptoms (NPS) in Lewy body dementias (LBD) occur frequently and early in disease progression. Such symptoms are associated with worse quality of life, caregiver burden and functional limitations. Limited evidence exists, however, outlining the longitudinal relationship between NPS and cognitive decline in prodromal LBD.

METHODS

123 participants were derived from three cohort studies. Patients with mild cognitive impairment (MCI) relating to probable dementia with Lewy bodies (MCI-LB, n = 67) and Parkinson's disease (PD-MCI, n = 56) completed comprehensive cognitive and neuropsychiatric assessment and were followed up longitudinally. Linear regression and mixed effects models assessed the relationship between baseline NPS and cognition at baseline and over time.

RESULTS

In MCI-LB, overall NPS burden was associated with declines over time in executive function (p = 0.026) and processing speed (p = 0.028) and baseline aberrant motor behaviour was associated with declines in attention (p < 0.025). Anxiety was significantly associated with poorer visuospatial functioning (p = 0.016) at baseline and poorer attention both at baseline (p = 0.017) and across time points (p = 0.024). In PD-MCI, psychosis was associated with poorer executive functioning at baseline (p = 0.008) and across time points (p = 0.002) but had no association with changes longitudinally.

CONCLUSIONS

Core neuropsychiatric components of LBD are not strongly associated with cognition in prodromal disease. This may suggest that neuropathological mechanisms underlying NPS may not be the same as those underlying cognitive impairment. Non-core NPS, however, may be more directly associated with cognitive change. Future studies utilising neuroimaging techniques are needed to explore the neuropathological basis of NPS in prodromal LBD.

Sex differences in dementia with Lewy bodies: Focused review of available evidence and future directions

In this review, we summarize the current knowledge on sex differences in dementia with Lewy bodies (DLB) relating to epidemiology, clinical features, neuropathology, biomarkers, disease progression, and caregiving. While many studies show a higher DLB prevalence in men, this finding is inconsistent and varies by study approach. Visual hallucinations may be more common and occur earlier in women with DLB, whereas REM sleep behavior disorder may be more common and occur earlier in men. Several studies report a higher frequency of parkinsonism in men with DLB, while the frequency of fluctuations appears similar between sexes. Women tend to be older, have greater cognitive impairment at their initial visit, and are delayed in meeting DLB criteria compared to men. Women are also more likely to have Lewy body disease with co-existing AD-related pathology than so-called "pure" Lewy body disease, while men may present with either. Research is mixed regarding the impact of sex on DLB progression. Biomarker and treatment research assessing for sex differences is lacking. Women provide the majority of caregiving in DLB but how this affects the caregiving experience is uncertain. Gaining a better understanding of sex differences will be instrumental in aiding future development of sex-specific strategies in DLB for early diagnosis, care, and drug development.

New Insights into Potential Biomarkers in Patients with Mild Cognitive Impairment Occurring in the Prodromal Stage of Dementia with Lewy Bodies

BACKGROUND

Prodromal dementia with Lewy bodies (DLB) can emerge with the onset of mild cognitive impairment (MCI). Standard biomarkers can help identify such patients to improve therapy and treatment strategies. Our review aims to describe the latest evidence on promising biomarkers in prodromal DLB with MCI onset (MCI-LB).

METHODS

We selected articles on different biomarkers in MCI-LB from PubMed and conducted a narrative review.

RESULTS

We identified potentially promising clinical biomarkers, e.g., (1) assessing autonomic symptoms specifically, (2) describing the cognitive profile in several subdomains including executive and visual functions, and (3) measuring the speed of speech. In addition, we describe the measurement of seeding amplification assays of alpha-synuclein in cerebrospinal fluid as a relevant biomarker for MCI-LB. Electroencephalographic markers, as in calculating the theta/beta ratio or intermittent delta activity, or analyzing peak frequency in electroencephalography-methods also potentially useful once they have been validated in large patient cohorts. The 18F fluorodesoxyglucose positron emission tomography (FDG-PET) technique is also discussed to investigate metabolic signatures, as well as a specific magnetic resonance imaging (MRI) technique such as for the volumetric region of interest analysis.

CONCLUSIONS

These biomarker results suggest that MCI-LB is a promising field for the use of biomarkers other than established ones to diagnose early prodromal DLB. Further large-scale studies are needed to better evaluate and subsequently use these promising biomarkers in prodromal DLB.

Neuropsychological Impairments and Their Cognitive Architecture in Mild Cognitive Impairment (MCI) with Lewy Bodies and MCI-Alzheimer's Disease

OBJECTIVE

The present study aimed to clarify the neuropsychological profile of the emergent diagnostic category of Mild Cognitive Impairment with Lewy bodies (MCI-LB) and determine whether domain-specific impairments such as in memory were related to deficits in domain-general cognitive processes (executive function or processing speed).

METHOD

Patients (n = 83) and healthy age- and sex-matched controls (n = 34) underwent clinical and imaging assessments. Probable MCI-LB (n = 44) and MCI-Alzheimer's disease (AD) (n = 39) were diagnosed following National Institute on Aging-Alzheimer's Association (NIA-AA) and dementia with Lewy bodies (DLB) consortium criteria. Neuropsychological measures included cognitive and psychomotor speed, executive function, working memory, and verbal and visuospatial recall.

RESULTS

MCI-LB scored significantly lower than MCI-AD on processing speed [Trail Making Test B: p = .03, g = .45; Digit Symbol Substitution Test (DSST): p = .04, g = .47; DSST Error Check: p < .001, g = .68] and executive function [Trail Making Test Ratio (A/B): p = .04, g = .52] tasks. MCI-AD performed worse than MCI-LB on memory tasks, specifically visuospatial (Modified Taylor Complex Figure: p = .01, g = .46) and verbal (Rey Auditory Verbal Learning Test: p = .04, g = .42) delayed recall measures. Stepwise discriminant analysis correctly classified the subtype in 65.1% of MCI patients (72.7% specificity, 56.4% sensitivity). Processing speed accounted for more group-associated variance in visuospatial and verbal memory in both MCI subtypes than executive function, while no significant relationships between measures were observed in controls (all ps > .05).

CONCLUSIONS

MCI-LB was characterized by executive dysfunction and slowed processing speed but did not show the visuospatial dysfunction expected, while MCI-AD displayed an amnestic profile. However, there was considerable neuropsychological profile overlap and processing speed mediated performance in both MCI subtypes.

Cognitive and Brain Metabolism Profiles of Mild Cognitive Impairment in Prodromal Alpha-Synucleinopathy

Background: Mild cognitive impairment (MCI) is a heterogeneous condition. Idiopathic REM sleep behavior disorder (iRBD) can be associated with MCI (MCI-RBD). Objective: To investigate neuropsychological and brain metabolism features of patients with MCI-RBD by comparison with matched MCI-AD patients. To explore their predictive value toward conversion to a full-blown neurodegenerative disease. Methods: Seventeen MCI-RBD patients (73.6±6.5 years) were enrolled. Thirty-four patients with MCI-AD were matched for age (74.8±4.4 years), Mini-Mental State Exam score and education with a case-control criterion. All patients underwent a neuropsychological assessment and brain 18F-FDG-PET. Images were compared between groups to identify hypometabolic volumes of interest (MCI-RBD-VOI and MCI-AD-VOI). The dependency of whole-brain scaled metabolism levels in MCI-RBD-VOI and MCI-AD-VOI on neuropsychological test scores was explored with linear regression analyses in both groups, adjusting for age and education. Survival analysis was performed to investigate VOIs phenoconversion prediction power. Results: MCI-RBD group scored lower in executive functions and higher in verbal memory compared to MCI-AD group. Also, compared with MCI-AD, MCI-RBD group showed relative hypometabolism in a posterior brain area including cuneus, precuneus, and occipital regions while the inverse comparison revealed relative hypometabolism in the hippocampus/parahippocampal areas in MCI-AD group. MCI-RBD-VOI metabolism directly correlated with executive functions in MCI-RBD (p = 0.04). MCI-AD-VOI metabolism directly correlated with verbal memory in MCI-AD (p = 0.001). MCI-RBD-VOI metabolism predicted (p = 0.03) phenoconversion to an alpha-synucleinopathy. MCI-AD-VOI metabolism showed a trend (p = 0.07) in predicting phenoconversion to dementia. Conclusion: MCI-RBD and MCI-AD showed distinct neuropsychological and brain metabolism profiles, that may be helpful for both diagnosis and prognosis purposes.

Validation of the NIH Toolbox-Cognition Battery against legacy neurocognitive measures in adults with cognitive impairments: An exploratory analysis

OBJECTIVE

The purpose of this exploratory study was to describe associations between NIH Toolbox-Cognition Battery subtests and legacy measures of neurocognitive function in two samples with neurological conditions (stroke and sickle cell disease (SCD)).

METHOD

This exploratory secondary analysis uses data from two studies that assessed cognition at one time point using the NIH Toolbox-Cognition Battery, the Repeatable Battery for the Assessment of Neuropsychological Status (RBANS), and subtests from the Delis-Kaplan Executive Functions System (DKEFS). People with stroke (n = 26) and SCD (n = 64) were included. Associations between the NIH Toolbox-Cognition Battery subtests and corresponding legacy measures were examined using linear correlations, Bland-Altman analysis, and Lin's Concordance Correlation Coefficient.

RESULTS

Linear correlations and Lin's Concordance Correlation Coefficient were poor to strong in both samples on NIH Toolbox-CB subtests: Flanker Inhibitory Control and Attention (r = .35 to .48, Lin CCC = .27 to .37), Pattern Comparison Processing Speed (r = .40 to .65, Lin CCC = .37 to .62), Picture Sequence Memory (r = .19 to .55, Lin CCC = .18 to .48), Dimensional Change Card Sort (r = .39 to .77, Lin CCC = .38 to .63), Fluid Cognition Composite (r = .88 to .90, Lin CCC = .60 to .79), and Total Cognition Composite (r = .64 to .83, Lin CCC = .60 to .78). Bland-Altman analyses demonstrated wide limits of agreement across all subtests (-3.17 to 3.78).

CONCLUSIONS

The NIH Toolbox-Cognition Battery subtests may behave similarly to legacy measures as an overall assessment of cognition across samples at risk for neurological impairment. Findings should be replicated across additional clinical samples.

Mild cognitive impairment with Lewy bodies: neuropsychiatric supportive symptoms and cognitive profile

BACKGROUND

Recently published diagnostic criteria for mild cognitive impairment with Lewy bodies (MCI-LB) include five neuropsychiatric supportive features (non-visual hallucinations, systematised delusions, apathy, anxiety and depression). We have previously demonstrated that the presence of two or more of these symptoms differentiates MCI-LB from MCI due to Alzheimer's disease (MCI-AD) with a likelihood ratio >4. The aim of this study was to replicate the findings in an independent cohort.

METHODS

Participants ⩾60 years old with MCI were recruited. Each participant had a detailed clinical, cognitive and imaging assessment including FP-CIT SPECT and cardiac MIBG. The presence of neuropsychiatric supportive symptoms was determined using the Neuropsychiatric Inventory (NPI). Participants were classified as MCI-AD, possible MCI-LB and probable MCI-LB based on current diagnostic criteria. Participants with possible MCI-LB were excluded from further analysis.

RESULTS

Probable MCI-LB (n = 28) had higher NPI total and distress scores than MCI-AD (n = 30). In total, 59% of MCI-LB had two or more neuropsychiatric supportive symptoms compared with 9% of MCI-AD (likelihood ratio 6.5, p < 0.001). MCI-LB participants also had a significantly greater delayed recall and a lower Trails A:Trails B ratio than MCI-AD.

CONCLUSIONS

MCI-LB is associated with significantly greater neuropsychiatric symptoms than MCI-AD. The presence of two or more neuropsychiatric supportive symptoms as defined by MCI-LB diagnostic criteria is highly specific and moderately sensitive for a diagnosis of MCI-LB. The cognitive profile of MCI-LB differs from MCI-AD, with greater executive and lesser memory impairment, but these differences are not sufficient to differentiate MCI-LB from MCI-AD.

The Cognitive Profile of Mild Cognitive Impairment Due to Dementia With Lewy Bodies-An Updated Review

Objective: Dementia with Lewy Bodies (DLB) is the second most common type of neurodegenerative dementia. Yet, the domain-specific cognitive impairment of the mild cognitive impairment (MCI) phase of this disease (DLB-MCI) is still not been established. This article gives an updated review on the neuropsychological profile of DLB-MCI, building on the findings from a previous review. Methods: We performed systematic review and searched five different electronic databases (Scopus, Cochrane, EMBASE, MEDLINE, and PsycINFO) in May 2020 based on a PICO scheme. Our search was then restricted to articles published in 2019 and 2020. Ending up with a total of 90 articles to be reviewed by abstract and/or full text. Results: In total four papers were included, whereof only one met our full inclusion criteria. Despite a substantial heterogeneity, our findings indicate that DLB-MCI patients have a pattern of executive, visuospatial, and attentional deficits. Conclusion: The findings indicate that the neuropsychological profile of DLB-MCI is characterized by executive, visuospatial, and attentional deficits. Furthermore, the shortage of studies clearly underlines the paucity of published research into DLB-MCI and emphasizes the need for well-controlled studies.

Striatal dopamine transporters and cognitive function in Parkinson's disease

BACKGROUND

Idiopathic Parkinson's disease (PD) is characterized by clinical motor symptoms including hypokinesia, rigidity and tremor. In addition to the movement disorder, cognitive deficits are commonly described. In the present study, we applied FP-CIT SPECT to investigate the impact of nigrostriatal dopaminergic degeneration on cognitive function in PD patients.

METHODS

Fifty-four PD patients underwent [¹²³I]FP-CIT SPECT and CERAD (Consortium to Establish a Registry for Alzheimer's Disease) testing. FP-CIT SPECT visualized the density of presynaptic dopamine transporters in both striata, each subdivided into a limbic, executive and sensorimotor subregion according to the atlas of Tziortzi et al (Cereb Cortex 24, 2014, 1165). CERAD testing quantified cognitive function.

RESULTS

In the CERAD testing, PD patients exhibited deficits in the domains of semantic memory, attention, visuospatial function, non-verbal memory and executive function. After correction for multiple testing, the performance of the subtests Figure Recall and Trail-Making Test A correlated significantly with FP-CIT uptake into the ipsilateral executive subregion. The performance of the subtest Figure Saving correlated significantly with FP-CIT uptake into the contralateral executive subregion.

CONCLUSIONS

The significant correlation between cognitive function and density of nigrostriatal dopamine transporters, as assessed by FP-CIT SPECT, indicate that striatal dopaminergic pathways-primarily the executive striatal subregion-are relevant to cognitive processing in PD.

Visuo-Perceptual and Decision-Making Contributions to Visual Hallucinations in Mild Cognitive Impairment in Lewy Body Disease: Insights from a Drift Diffusion Analysis

Background: Visual hallucinations (VH) are a common symptom in dementia with Lewy bodies (DLB); however, their cognitive underpinnings remain unclear. Hallucinations have been related to cognitive slowing in DLB and may arise due to impaired sensory input, dysregulation in top-down influences over perception, or an imbalance between the two, resulting in false visual inferences. Methods: Here we employed a drift diffusion model yielding estimates of perceptual encoding time, decision threshold, and drift rate of evidence accumulation to (i) investigate the nature of DLB-related slowing of responses and (ii) their relationship to visuospatial performance and visual hallucinations. The EZ drift diffusion model was fitted to mean reaction time (RT), accuracy and RT variance from two-choice reaction time (CRT) tasks and data were compared between groups of mild cognitive impairment (MCI-LB) LB patients (n = 49) and healthy older adults (n = 25). Results: No difference was detected in drift rate between patients and controls, but MCI-LB patients showed slower non-decision times and boundary separation values than control participants. Furthermore, non-decision time was negatively correlated with visuospatial performance in MCI-LB, and score on visual hallucinations inventory. However, only boundary separation was related to clinical incidence of visual hallucinations. Conclusions: These results suggest that a primary impairment in perceptual encoding may contribute to the visuospatial performance, however a more cautious response strategy may be related to visual hallucinations in Lewy body disease. Interestingly, MCI-LB patients showed no impairment in information processing ability, suggesting that, when perceptual encoding was successful, patients were able to normally process information, potentially explaining the variability of hallucination incidence.

Is the Random Forest Algorithm Suitable for Predicting Parkinson's Disease with Mild Cognitive Impairment out of Parkinson's Disease with Normal Cognition?

Because it is possible to delay the progression of dementia if it is detected and treated in an early stage, identifying mild cognitive impairment (MCI) is an important primary goal of dementia treatment. The objectives of this study were to develop a random forest-based Parkinson's disease with mild cognitive impairment (PD-MCI) prediction model considering health behaviors, environmental factors, medical history, physical functions, depression, and cognitive functions using the Parkinson's Dementia Clinical Epidemiology Data (a national survey conducted by the Korea Centers for Disease Control and Prevention) and to compare the prediction accuracy of our model with those of decision tree and multiple logistic regression models. We analyzed 96 subjects (PD-MCI = 45; Parkinson's disease with normal cognition (PD-NC) = 51 subjects). The prediction accuracy of the model was calculated using the overall accuracy, sensitivity, and specificity. Based on the random forest analysis, the major risk factors of PD-MCI were, in descending order of magnitude, Clinical Dementia Rating (CDR) sum of boxes, Untitled Parkinson's Disease Rating (UPDRS) motor score, the Korean Mini Mental State Examination (K-MMSE) total score, and the K- Korean Montreal Cognitive Assessment (K-MoCA) total score. The random forest method achieved a higher sensitivity than the decision tree model. Thus, it is advisable to develop a protocol to easily identify early stage PDD based on the PD-MCI prediction model developed in this study, in order to establish individualized monitoring to track high-risk groups.