Accuracy of Machine Learning Using the Montreal Cognitive Assessment for the Diagnosis of Cognitive Impairment in Parkinson’s Disease

Background: Cognitive impairment is prevalent in Parkinson's disease (PD), affecting 15–20% of patients at diagnosis. α-synuclein expression and genetic polymorphisms of Apolipoprotein E (ApoE) have been associated with the presence of cognitive impairment in PD although data have been inconsistent.Objectives: To determine the prevalence of cognitive impairment in patients with PD using Montreal Cognitive Assessment (MoCA), Comprehensive Trail Making Test (CTMT) and Parkinson's disease-cognitive rating scale (PDCRS), and its association with plasma α-synuclein and ApoE genetic polymorphisms.Methods: This was across-sectional study involving 46 PD patients. Patients were evaluated using Montreal cognitive assessment test (MoCA), and detailed neuropsychological tests. The Parkinson's disease cognitive rating scale (PDCRS) was used for cognitive function and comprehensive trail making test (CTMT) for executive function. Blood was drawn for plasma α-synuclein measurements and ApoE genetic analysis. ApoE polymorphism was detected using MutaGELAPoE from ImmunDiagnostik. Plasma α-synuclein was detected using the ELISA Technique (USCN Life Science Inc.) according to the standard protocol.Results: Based on MoCA, 26 (56.5%) patients had mild cognitive impairment (PD-MCI) and 20 (43.5%) had normal cognition (PD-NC). Based on the PDCRS, 18 (39.1%) had normal cognition (PDCRS-NC), 17 (37%) had mild cognitive impairment (PDCRS-MCI), and 11 (23.9%) had dementia (PDCRS-PDD). In the PDCRS-MCI group, 5 (25%) patients were from PD-NC group and all PDCRS-PDD patients were from PD-MCI group. CTMT scores were significantly different between patients with MCI and normal cognition on MoCA (p = 0.003). Twenty one patients (72.4%) with executive dysfunction were from the PD-MCI group; 17 (77.3%) with severe executive dysfunction and 4 (57.1%) had mild to moderate executive dysfunction. There were no differences in the plasma α-synuclein concentration between the presence or types of cognitive impairment based on MoCA, PDCRS, and CTMT. TheApoEe4 allele carrier frequency was significantly higher in patients with executive dysfunction (p = 0.014).Conclusion: MCI was prevalent in our PD population. PDCRS appeared to be more discriminatory in detecting MCI and PDD than MoCA. Plasma α-synuclein level was not associated with presence nor type of cognitive impairment, but the ApoEe4 allele carrier status was significantly associated with executive dysfunction in PD.

The impact of Parkinson’s disease (PD) dementia is substantial and has major functional and socioeconomic consequences. Early prediction of future cognitive impairment would help target future interventions. The Montreal Cognitive Assessment (MoCA), the Mini-Mental State Examination (MMSE), and fluency tests were administered to 486 patients with PD within 3.5 years of diagnosis, and the results were compared with those from 141 controls correcting for age, sex, and educational years. Eighteen-month longitudinal assessments were performed in 155 patients with PD. The proportion of patients classified with normal cognition, mild cognitive impairment (MCI), and dementia varied considerably, depending on the MoCA and MMSE thresholds used. With the MoCA total score at screening threshold, 47.7%, 40.5%, and 11.7% of patients with PD were classified with normal cognition, MCI, and dementia, respectively; by comparison, 78.7% and 21.3% of controls had normal cognition and MCI, respectively. Cognitive impairment was predicted by lower education, increased age, male sex, and quantitative motor and non-motor (smell, depression, and anxiety) measures. Longitudinal data from 155 patients with PD over 18 months showed significant reductions in MoCA scores, but not in MMSE scores, with 21.3% of patients moving from normal cognition to MCI and 4.5% moving from MCI to dementia, although 13.5% moved from MCI to normal; however, none of the patients with dementia changed their classification. The MoCA may be more sensitive than the MMSE in detecting early baseline and longitudinal cognitive impairment in PD, because it identified 25.8% of those who experienced significant cognitive decline over 18 months. Cognitive decline was associated with worse motor and non-motor features, suggesting that this reflects a faster progressive phenotype.

An important proportion of patients with Parkinson’s Disease (PD) present signs of cognitive impairment, although this is heterogeneous. In an attempt to classify this, the dual syndrome hypothesis distinguishes between two profiles: one defined by attentional and executive problems with damage in anterior cerebral regions, and another with mnesic and visuospatial alterations, with damage in posterior cerebral regions. The Montreal Cognitive Assessment (MoCA) is one of the recommended screening tools, and one of the most used, to assess cognitive impairment in PD. However, its ability to specifically identify these two profiles of cognitive impairment has not been studied. The aim of this study was, therefore, to analyze the capacity of the MoCA to detect cognitive impairment, and also to identify anterior and posterior profiles defined by the dual syndrome hypothesis. For this purpose, 59 patients with idiopathic PD were studied with the MoCA and a neuropsychological battery of tests covering all cognitive domains. Results of logistic regression analysis with ROC (Receiver Operating Characteristic) curves showed that MoCA detected cognitive impairment and identified patients with a profile of anterior/attentional and executive deficit, with acceptable sensibility and specificity. However, it did not identify patients with a posterior/mnesic-visuospatial impairment. We discuss the reasons for the lack of sensitivity of MoCA in this profile, and other possible implications of these results with regards the usefulness of this tool to assess cognitive impairment in PD.

Cognitive impairment (CI) is common in Parkinson's disease (PD) and an important cause of disability. Screening facilitates early detection of CI and has implications for management. Preclinical disability is when patients have functional limitations but maintain independence through compensatory measures. The objective of this study was to investigate the relationship between scores on the Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA) with levels of PD severity and disability. PD patients (n = 2,234) in a large observational study were stratified by disease severity, based on Total Unified Parkinson's Disease Rating Scale (Total UPDRS) and Hoehn and Yahr (HY) stage. Using MMSE (n = 1,184) or MoCA (n = 1,050) and basic (ADL) and instrumental activities of daily living (IADL) scales for disability, linear regression analysis examined associations between cognitive status and disability. Cognition and disability were highly correlated, with the strongest correlation between IADL and MoCA. Only 16.0% of mean MMSE scores were below threshold for CI (28) and only in advanced PD (Total UPDRS 60+, HY≥3). MoCA scores fell below CI threshold (26) in 66.2% of the sample and earlier in disease (Total UPDRS 30+, HY≥2), corresponding with impairments in ADLs. In a large clinical dataset, a small fraction of MMSE scores fell below cutoff for CI, reinforcing that MMSE is an insensitive screening tool in PD. MoCA scores indicated CI earlier in disease and coincided with disability. This study shows that MoCA, but not MMSE is sensitive to the emergence of early cognitive impairment in PD and correlates with the concomitant onset of disability.

Objective The Montreal Cognitive Assessment (MoCA) is recommended for general cognitive evaluation in Parkinson’s disease (PD) patients. However, age- and education-adjusted cutoffs specifically for PD have not been developed or systematically validated across PD cohorts with diverse education levels.Methods In this retrospective analysis, we utilized data from 1,293 Korean patients with PD whose cognitive diagnoses were determined through comprehensive neuropsychological assessments. Age- and education-adjusted cutoffs were formulated based on 1,202 patients with PD. To identify the optimal machine learning model, clinical parameters and MoCA domain scores from 416 patients with PD were used. Comparative analyses between machine learning methods and different cutoff criteria were conducted on an additional 91 consecutive patients with PD.Results The cutoffs for cognitive impairment decrease with increasing age within the same education level. Similarly, lower education levels within the same age group correspond to lower cutoffs. For individuals aged 60–80 years, cutoffs were set as follows: 25 or 24 years for those with more than 12 years of education, 23 or 22 years for 10–12 years, and 21 or 20 years for 7–9 years. Comparisons between age- and education-adjusted cutoffs and the machine learning method showed comparable accuracies. The cutoff method resulted in a higher sensitivity (0.8627), whereas machine learning yielded higher specificity (0.8250).Conclusion Both the age- and education-adjusted cutoff methods and machine learning methods demonstrated high effectiveness in detecting cognitive impairment in PD patients. This study highlights the necessity of tailored cutoffs and suggests the potential of machine learning to improve cognitive assessment in PD patients.

Little is known about the impact of the dopamine system on development of cognitive impairment (CI) in Parkinson disease (PD). We used data from a multi-site, international, prospective cohort study to explore the impact of dopamine system-related biomarkers on CI in PD. PD participants were assessed annually from disease onset out to 7 years, and CI determined by applying cut-offs to four measures: (1) Montreal Cognitive Assessment; (2) detailed neuropsychological test battery; (3) Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) cognition score; and (4) site investigator diagnosis of CI (mild cognitive impairment or dementia). The dopamine system was assessed by serial Iodine-123 Ioflupane dopamine transporter (DAT) imaging, genotyping, and levodopa equivalent daily dose (LEDD) recorded at each assessment. Multivariate longitudinal analyses, with adjustment for multiple comparisons, determined the association between dopamine system-related biomarkers and CI, including persistent impairment. Demographic and clinical variables associated with CI were higher age, male sex, lower education, non-White race, higher depression and anxiety scores and higher MDS-UPDRS motor score. For the dopamine system, lower baseline mean striatum dopamine transporter values (P range 0.003-0.005) and higher LEDD over time (P range <0.001-0.01) were significantly associated with increased risk for CI. Our results provide preliminary evidence that alterations in the dopamine system predict development of clinically-relevant, cognitive impairment in Parkinson's disease. If replicated and determined to be causative, they demonstrate that the dopamine system is instrumental to cognitive health status throughout the disease course. Parkinson's Progression Markers Initiative is registered with ClinicalTrials.gov (NCT01141023).

Brain iron accumulation has been proposed as one of the pathomechanisms in Parkinson's disease (PD). This study aimed to examine the whole-brain pattern of iron accumulation associated with cognitive impairment in patients with PD using voxel-based quantitative susceptibility mapping analysis. We enrolled 24 patients with PD and mild cognitive impairment, 22 patients with PD and normal cognition, and 20 age-matched healthy controls in this cross-sectional study. All participants underwent global cognitive and physical assessments and brain MRI. Using a combined method of voxel-based morphometry and quantitative susceptibility mapping, we compared the voxel-wise magnetic susceptibility of the whole brain between the groups and analyzed its correlation with the cognitive and behavioral data. The PD and mild cognitive impairment group had lower Montreal Cognitive Assessment (MoCA) score than the PD and normal cognition and healthy control groups. There were no gray matter volumetric differences between the groups. In contrast, the voxel-based quantitative susceptibility mapping analysis showed that the PD and mild cognitive impairment group had significantly higher quantitative susceptibility mapping values in the cuneus, precuneus, caudate head, fusiform gyrus, and orbitofrontal cortex than did the PD and normal cognition group. These quantitative susceptibility mapping values were negatively correlated with the MoCA scores in the PD patients (cuneus: r = -0.510, P < .001; caudate head: r = -0.458, P = 0.002). This study suggests that cognitive impairment in PD is associated with cerebral iron burden and highlights the potential of quantitative susceptibility mapping as an auxiliary biomarker for early evaluation of cognitive decline in patients with PD. © 2019 International Parkinson and Movement Disorder Society.

Background: The Montreal Cognitive Assessment (MoCA) has been recommended as a cognitive screening tool for clinical practice and research in Parkinson’s disease (PD), yet no normative data have been published for MoCA in PD without dementia.Methods: We undertook a pooled secondary analysis of data from two studies (one cross-sectional design and one clinical trial) conducted in the East of England region. All participants were aged 18 years or over, met UK Brain Bank criteria for PD and did not have clinical dementia. Cognitive status was assessed using MoCA at baseline in both studies. The influences of age, gender, disease duration, medication load (LEDD) and mood (HADS) on cognition were examined using regression analysis.Results: Data from 101 people with PD without dementia were available (mean age 71 years, 66% men). Median (IQR) MoCA was 25(22, 27). Age was found as the only predictor of MoCA in this sample. People aged over 71 had poorer MoCA (Beta=0.6 (95%CI 0.44, 0.82)) and an increased odds of MoCA <26 (Beta=0.29 (95%CI 0.12, 0.70)) as well as poorer scores on several MoCA sub-domains.Conclusion: We present the normative data for MoCA in people with PD without clinical dementia. Age appeared to be the only associated factor for lower level of cognition, suggestive of Mild cognitive impairment in PD (PD-MCI) in PD without clinical diagnosis of dementia.

Mild cognitive impairment is one of the non-motor symptoms in Parkinson's disease (PD) and multiple system atrophy (MSA). Few studies have previously been conducted on the correlation between serum uric acid (SUA) and lipid levels and mild cognitive impairment in PD and MSA. Participants included 149 patients with PD and 99 patients with MSA. The Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA) were used to evaluate cognitive function. Evaluations were conducted on SUA and lipid levels, which included triglyceride, low-density lipoprotein cholesterol (LDL-C), high-density lipoprotein cholesterol (HDL-C) and total cholesterol (TC). Patients with PD and MSA diagnosed with mild cognitive impairment demonstrated multiple cognitive domain impairment when compared with patients with normal cognition. Attentional impairment was more pronounced in patients with MSA when compared with PD (p = 0.001). In PD, the risk of mild cognitive impairment was lower in the highest quartiles and secondary quartile of SUA than in the lowest quartiles (odds ratio [OR] = 0.281, 95% confidence intervals [CI]: 0.097-0.810, p = 0.019; and OR = 0.317, 95% CI: 0.110-0.911, p = 0.033). In MSA, the risk of mild cognitive impairment was lower in the third and highest quartile of SUA than in the lowest quartile (OR = 0.233, 95% CI: 0.063-0.868, p = 0.030; and OR = 0.218, 95% CI: 0.058-0.816, p = 0.024). In patients with PD, the MoCA scores were negatively correlated with TC levels (r = -0.226, p = 0.006) and positively correlated with SUA levels (r = 0.206, p = 0.012). In MSA, the MoCA scores were positively correlated with SUA levels (r = 0.353, p = 0.001). Lower SUA levels and higher TC levels are a possible risk factor for the risk and severity of mild cognitive impairment in PD. Lower SUA levels are a possible risk factor for the risk and severity of mild cognitive impairment in MSA.

BackgroundInsulin resistance (IR) is proved be involved in the pathophysiology of Parkinson’s disease (PD). As an effective surrogate marker of IR, the correlation between the triglyceride-glucose (TyG) index and PD remains unclear. This cross-sectional study aimed to explore the association between the TyG index and cognitive impairment in PD (PDCI).MethodsPatients with sporadic PD were consecutively enrolled between May 2022 and October 2023. The cognitive function was evaluated using the Montreal Cognitive Assessment (MoCA). The Spearman correlation analysis was used to evaluate the correlation between TyG index and MoCA score, Unified-Parkinson Disease Rating Scale (UPDRS) III and peripheral blood oxidative stress markers, respectively. Logistic regression analysis was performed to explore the correlation between TyG and PDCI and dementia in PD (PDD).ResultsA total of 78 patients were enrolled, of whom 50 (64.1%) were diagnosed with PDCI [26 with mild cognitive impairment (MCI) and 24 with PDD]. The TyG index in patients with dementia and MCI were higher than those with normal cognition (9.32 ± 0.43 vs. 8.90 ± 0.47 vs. 8.51 ± 0.46, P < 0.001). The Spearman correlation analysis demonstrated that TyG was negatively correlated with MoCA (r = −0.704, P < 0.001) and superoxide dismutase (r = −0.244, P = 0.031), but positively correlated with UPDRS III (r = 0.246, P = 0.030). Multivariate logistic regression analysis showed that TyG was independently associated with PDCI regardless of whether it was used as a continuous variable (OR = 6.177, 95% CI = 1.590–24.000) or a tertile variable (OR = 5.478, 95% CI = 1.030–29.132). This association persisted after excluding patients with diabetes. The receiver operating characteristic (ROC) analysis suggested that the area under the curve (AUC) of TyG for predicting PDCI was 0.805 (95% CI = 0.707–0.903, P < 0.001).ConclusionElevated TyG levels were associated with an increased likelihood of PDCI in patients with PD.

Correlation between serum 25(OH)D and cognitive impairment in Parkinson's disease

Recognition of early cognitive impairment in Parkinsons disease (PD) is important since it represents a risk factor for developing Parkinson's disease dementia and psychosis. The Mini- Mental State Examination (MMSE) remains the most commonly used screening instrument for global cognition, even though it has not been specifically validated for use in PD subjects. More recently, the Montreal Cognitive Assessment (MoCA) test has been recommended as a better screening tool in PD. Most of these studies have been done in countries with a highly-educated population. The objective of the study is to compare the performance between the MMSE and the MoCA to screen for mild cognitive impairment in subjects with Parkinson's disease and a low education background. The MMSE and MoCA were applied to 128 subjects using a cut-off score of 26 points for cognitive impairment. Fifty-five percent were classified with cognitive impairment according to the MoCA. Forty-one percent of subjects with a normal MMSE were classified with cognitive impairment by MoCA. Results from our analysis could be directly applied to other populations with a high proportion of poorly educated subjects.

Objective To investigate the risk factors of Parkinson＇s disease（PD）with mild cognitive impairment and mode of cerebral glucose metabolism. Methods One hundred and one non-dementia PD patients were assessed with Montreal Cognitive Assessment（MoCA）and divided into the PD with mild cognitive impairment （PD-MCI）group and the PD non-cognitive impairment（PD-NC）group. The demographic details, clinical features,Unified Pakinson＇s Disease Rating Scale（UPDRS）, Hohen-Yahr rank and Hamilton Depression Scale（HAMD）were compared between the two groups. Patients in Hohen-Yahr stage 1 underwent positron emission tomography（PET）with 18F-fluorodeoxyglucose（18F-FDG）to show glucose metabolism. Results Seventy-seven（74. 3%）PD patients had mild cognitive impairment PD-MCI group had higher score in UPDRS 1st（mentation ,behavior and mood）,2nd （activity of daily living）and 3rd（motor examination）subscale（2.48 ± 1.51,10. 71 ± 4. 88,22.31 ± 12.70）than PD-NC group（1.65 ± 1.29,8.15 ±2. 20,15.92 ±7.56,P 〈0.05）respectively. The FDG metabolism ratio of frontal cortex,parietal cortex and occipital cortex decreased more significantly in PD-MCI than in PD-NC（P 〈 0.05）.Conclusions The risk factors of mild cognitive impairment in PD include moter dysfunction, clinical stage and depression. The metabolic dysfunction of cortex may be the mechanism of mild cognitive impairment in PD. Key words: Parkinson＇s disease; Cognitive impairment; Positron emission tomography

Which figure copy test is more sensitive for cognitive impairment in Parkinson's disease: Wire cube or interlocking pentagons?

Background/Objectives: Cognitive impairment (CI) in Parkinson's disease (PD) is a major burden and significantly affects patients' quality of life. Previous studies found that older age at onset and presence of the akinetic-rigid (AR) subtype are associated with an increased likelihood of CI in PD. The present study aimed to assess factors that are related to the development of CI in PD. Methods: Eighty-three PD patients were consecutively recruited. Demographic information, clinical details, Montreal cognitive assessment (MoCA), Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS), walking speed, and instrumental activity of daily living (IADL) were assessed. Resting motor threshold (rMT), was also assessed for subgroup of patients with versus without cognitive impairment. Results: According to the MoCA cut-off score of 26, 45 had PD without CI (PD-NCI) (54.22%) and 38 cases (45.78%) had PD with CI (PD-CI). The age and age at onset were significantly older in the PD-CI group (p = 0.006 and 0.018, respectively). The patients were reclassified into AR and tremor-dominant (TR) phenotype. PD-CI patients were more likely to have the AR (81.6%). Walking speed, MDS-UPDRS score, and IADL scores were significantly worse in PD-CI than in PD-NCI. Stepwise linear regression analysis of risk factors associated CI revealed that higher MDS-UPDRS scores, later age of onset, and higher rMT values were considered risk factors for developing CI. Conclusions: Higher UPDRS score, later age of onset, and higher rMT values were considered as risk factors associated CI in PD patients and provide valuable insights for further investigation and potential clinical considerations.