Differentiation Of Mild Cognitive Impairment Research Articles

Early detection of mild cognitive impairment due to Alzheimer’s disease using combinations of an online cognitive assessment and blood biomarkers

AbstractBackgroundAccessible measurements to a large screening and early differentiation of mild cognitive impairment due to Alzheimer’s disease (MCI‐AD) from healthy elderly is increasing urgent with the prevalence of Alzheimer’s disease (AD) expanded.Methodan online cognitive assessment (Memtrax) and MoCA were performed, on 99 clinically diagnosed cognitively normal (CON) and 101 MCI‐AD participants. The plasma levels of phosphorylated tau (p‐tau)181 and neurofilament light (NfL) and amyloid beta (Aβ)42/40 were measured using Simoa assay. The relevance between Memtrax and blood biomarkers were conducted by Spearman correlation analysis. Discrimination models were built using assorted machine learning approaches combining Memtrax with blood biomarkers, and model performance was measured using Area Under the Receiver Operating Characteristic Curve (AUC).ResultThe AUC of Memtrax and MoCA in differentiating MCI‐AD from CON was similar. Memtrax has a strong correlation with phosphorylated tau (p‐tau)181 and neurofilament light (NfL), while less related to amyloid beta (Aβ)42/40. Combining Memtrax and blood biomarkers, the AUC of best model reach to 0.975 (95% CI: 0.950‐0.999).ConclusionThe combination of Memtrax and blood biomarkers is promising to the large screening and early detection in MCI‐AD.

A pilot study for a practical screening tool for dementia: validation of 5-minute cognitive test in a geriatric population.

The aim of this study is to validate the Turkish version of the 5-minute cognitive test (FCT) in a geriatric population. In total, 61 participants aged ≥65 years with normal cognitive functions, mild cognitive impairment (MCI), and early stage dementia were included. The FCT was compared to the standardised Mini Mental State Examination (MMSE) and the Qmci-TR (quick mild cognitive impairment) test. Test reliability for the FCT was strong (Cronbach's α = 0.747). We demonstrated a strong correlation of FCT scores with MMSE and Qmci-TR scores (respectively, r = 0.730, P < 0.001, r = 0.723, P < 0.001). The fact that the scores obtained in the dementia group were significantly lower also showed that the test can be used reliably in the differentiation of MCI and early dementia (P < 0.001). The FCT is a brief, reliable, and valid cognitive screening test for screening dementia at early stages in a Turkish geriatric population.

A Convolutional Neural Network Using Multimodal Retinal Imaging for Differentiation of Mild Cognitive Impairment from Normal Cognition

To develop a machine learning tool capable of differentiating eyes of subjects with normal cognition from those with mild cognitive impairment (MCI) using OCT and OCT angiography (OCTA). Evaluation of a diagnostic technology. Subjects with normal cognition were compared to subjects with MCI. A multimodal convolutional neural network (CNN) was built to predict likelihood of MCI from ganglion cell-inner plexiform layer (GC-IPL) thickness maps, OCTA images, and quantitative data including patient characteristics. Area under the receiver operating characteristic curve (AUC) and summaries of the confusion matrix (sensitivity and specificity) were used as performance metrics for the prediction outputs of the CNN. Images from 236 eyes of 129 cognitively normal subjects and 154 eyes of 80 MCI subjects were used for training, validating, and testing the CNN. When applied to the independent test set using inputs including GC-IPL thickness maps, OCTA images, and quantitative OCT and OCTA data, the AUC value for the CNN was 0.809 (95% confidence interval [CI]: 0.681-0.937). This model achieved a sensitivity of 79% and specificity of 83%. The AUC value for GC-IPL thickness maps alone was 0.681 (95% CI: 0.529-0.832), for OCTA images alone was 0.625 (95% CI: 0.466-0.784) and for both GC-IPL maps and OCTA images was 0.693 (95% CI: 0.543-0.843). Models using quantitative data alone were also tested, with a model using quantitative data derived from images, 0.960 (95% CI: 0.902-1.00), outperforming a model using demographic data alone, 0.580 (95% CI: 0.417-0.742). This novel CNN was able to identify an MCI diagnosis using an independent test set comprised of OCT and OCTA images and quantitative data. The GC-IPL thickness maps provided more useful decision support than the OCTA images. The addition of quantitative data inputs also provided significant decision support to the CNN to identify individuals with MCI. Quantitative imaging metrics provided superior decision support than demographic data. Proprietary or commercial disclosure may be found after the references.

Explainable Optimized LightGBM Based Differentiation of Mild Cognitive Impairment Using MR Radiomic Features.

In this study, an explainable Bayesian Optimized (BO) LightGBM model is employed to differentiate the Corpus Callosal (CC) image features of Healthy Controls (HC) and Mild Cognitive Impairment (MCI). For this, Magnetic Resonance (MR) brain images obtained from a public database are pre-processed and CC is segmented using spatial fuzzy clustering-based level set. Radiomic features are extracted from the segmented CC, which are further fed to BO-LightGBM classifier. SHapley Additive exPlanations (SHAP) technique is used to evaluate the interpretability of the model. The results indicate that radiomics based BO-LightGBM is able to differentiate MCI from HC. An area under curve of 0.83 is achieved by the model. SHAP values suggest that out of 56 radiomic features, texture descriptors possess the highest discriminative power in MCI diagnosis. The performance of adopted approach indicates that radiomics based BO-LightGBM aid in the automated diagnosis of early Alzheimer's Disease stages.

Differentiation of mild cognitive impairment (MCI) progression to Alzheimer's disease (AD) vs dementia with Lewy bodies (DLB): Is this possible neuropsychologically?

Differentiation of mild cognitive impairment (MCI) progression to Alzheimer's disease (AD) vs dementia with Lewy bodies (DLB): Is this possible neuropsychologically?

Reconsidering the overdiagnosis of mild cognitive impairment for dementia prevention among adults aged ≥80 years.

A diagnosis at the stage of mild cognitive impairment (MCI) is encouraged to promote dementia prevention since intensive intervention during the mild stage is thought to be effective for dementia prevention. Many adults aged ≥80 years hope to prevent dementia; however, several issues should be considered regarding the diagnosis of MCI. First, the diagnosis of MCI is not clear-cut in actual medical practice, with the differentiation of MCI from normal states and mild dementia being blurred. Second, although MCI due to Alzheimer's disease can be differentiated from MCI without pathological changes, interventions specific to MCI due to Alzheimer's disease have not been developed. Third, the diagnosis of MCI can cause self-stigma, leading to psychological effects such as depression and anxiety for both the patients and their families, which can be risk factors for developing dementia for patients. In addition, medical resources are limited and diagnosing MCI is costly in medical human resources. Considering these issues, diagnosing MCI to promote dementia prevention should be viewed from the perspective of the individual patient's interests, especially for those aged ≥80 years. The final decision regarding receiving a diagnosis or not should be the patient's; therefore, it is necessary to increase patients' health literacy, which requires medical professionals to provide them with appropriate evidence-based information. At the same time, it is important to provide psychological support to people who have been diagnosed.

Effective differentiation of mild cognitive impairment by functional brain graph analysis and computerized testing.

Community-dwelling African American elders are twice as likely to develop mild cognitive impairment (MCI) or Alzheimer’s disease and related dementias than older white Americans and therefore represent a significant at-risk group in need of early monitoring. More extensive imaging or cerebrospinal fluid studies represent significant barriers due to cost and burden. We combined functional connectivity and graph theoretical measures, derived from resting-state electroencephalography (EEG) recordings, with computerized cognitive testing to identify differences between persons with MCI and healthy controls based on a sample of community-dwelling African American elders. We found a significant decrease in functional connectivity and a less integrated graph topology in persons with MCI. A combination of functional connectivity, topological and cognition measurements is powerful for prediction of MCI and combined measures are clearly more effective for prediction than using a single approach. Specifically, by combining cognition features with functional connectivity and topological features the prediction improved compared with the classification using features from single cognitive or EEG domains, with an accuracy of 86.5%, compared with the accuracy of 77.5% of the best single approach. Community-dwelling African American elders find EEG and computerized testing acceptable and results are promising in terms of differentiating between healthy controls and persons with MCI living in the community.

Differentiation of mild cognitive impairment using an entorhinal cortex-based test of virtual reality navigation.

The entorhinal cortex is one of the first regions to exhibit neurodegeneration in Alzheimer's disease, and as such identification of entorhinal cortex dysfunction may aid detection of the disease in its earliest stages. Extensive evidence demonstrates that the entorhinal cortex is critically implicated in navigation underpinned by the firing of spatially modulated neurons. This study tested the hypothesis that entorhinal-based navigation is impaired in pre-dementia Alzheimer's disease. Forty-five patients with mild cognitive impairment (26 with CSF Alzheimer's disease biomarker data: 12 biomarker-positive and 14 biomarker-negative) and 41 healthy control participants undertook an immersive virtual reality path integration test, as a measure of entorhinal-based navigation. Behavioural performance was correlated with MRI measures of entorhinal cortex volume, and the classification accuracy of the path integration task was compared with a battery of cognitive tests considered sensitive and specific for early Alzheimer's disease. Biomarker-positive patients exhibited larger errors in the navigation task than biomarker-negative patients, whose performance did not significantly differ from controls participants. Path-integration performance correlated with Alzheimer's disease molecular pathology, with levels of CSF amyloid-β and total tau contributing independently to distance error. Path integration errors were negatively correlated with the volumes of the total entorhinal cortex and of its posteromedial subdivision. The path integration task demonstrated higher diagnostic sensitivity and specificity for differentiating biomarker positive versus negative patients (area under the curve = 0.90) than was achieved by the best of the cognitive tests (area under the curve = 0.57). This study demonstrates that an entorhinal cortex-based virtual reality navigation task can differentiate patients with mild cognitive impairment at low and high risk of developing dementia, with classification accuracy superior to reference cognitive tests considered to be highly sensitive to early Alzheimer's disease. This study provides evidence that navigation tasks may aid early diagnosis of Alzheimer's disease, and the basis of this in animal cellular and behavioural studies provides the opportunity to answer the unmet need for translatable outcome measures for comparing treatment effect across preclinical and clinical trial phases of future anti-Alzheimer's drugs.

Multi-modal discriminative dictionary learning for Alzheimer's disease and mild cognitive impairment

Background and objectiveThe differentiation of mild cognitive impairment (MCI), which is the prodromal stage of Alzheimer's disease (AD), from normal control (NC) is important as the recent research emphasis on early pre-clinical stage for possible disease abnormality identification, intervention and even possible prevention. MethodsThe current study puts forward a multi-modal supervised within-class-similarity discriminative dictionary learning algorithm (SCDDL) we introduced previously for distinguishing MCI from NC. The proposed new algorithm was based on weighted combination and named as multi-modality SCDDL (mSCDDL). Structural magnetic resonance imaging (sMRI), fluorodeoxyglucose (FDG) positron emission tomography (PET) and florbetapir PET data of 113 AD patients, 110 MCI patients and 117 NC subjects from the Alzheimer's disease Neuroimaging Initiative database were adopted for classification between MCI and NC, as well as between AD and NC. ResultsAdopting mSCDDL, the classification accuracy achieved 98.5% for AD vs. NC and 82.8% for MCI vs. NC, which were superior to or comparable with the results of some other state-of-the-art approaches as reported in recent multi-modality publications. ConclusionsThe mSCDDL procedure was a promising tool in assisting early diseases diagnosis using neuroimaging data.

Dual Tasking for the Differentiation between Depression and Mild Cognitive Impairment.

Differentiation of mild cognitive impairment from depression in elderly adults is a clinically relevant issue which is not sufficiently solved. Gait and dual task (DT) parameters may have the potential to complement current diagnostic work-up, as both dementia and depression are associated with changes of gait and DT parameters. Methods: Seven hundred and four participants of the TREND study (Tübinger evaluation of Risk factors for Early detection of NeuroDegeneration) aged 50–80 years were assessed using the Consortium to Establish a Registry for Alzheimer's Disease Plus test battery for testing cognition and Beck's Depression Inventory for evaluation of depression. Based on these results, four groups were defined: acute depressed (N = 53), cognitively mildly impaired (N = 97), acute depressed, and cognitively mildly impaired (N = 15), and controls (N = 536). Participants underwent a 20 m walk and checking boxes task under single (ST) and DT conditions. ST and DT performance and dual task costs (DTC) were calculated. Due to the typical age of increasing incidence of depressive and also cognitive symptoms, the 7th decade was calculated separately. Results: ST speeds of gait and checking boxes, DT walking speed, and walking DTC were significantly different between groups. Healthy controls were the fastest in all paradigms and cognitively mildly impaired had higher DTC than depressed individuals. Additionally, we constructed a multivariate predictive model differentiating the groups on a single-subject level. Conclusion: DT parameters are simply and comfortably measureable, and DTC can easily be determined. The combination of these parameters allows a differentiation of depressed and cognitively mildly impaired elderly adults.

A Method to Differentiate Mild Cognitive Impairment and Alzheimer in MR Images using Eigen Value Descriptors.

Automated analysis and differentiation of mild cognitive impairment and Alzheimer's condition using MR images is clinically significant in dementic disorder. Alzheimer's Disease (AD) is a fatal and common form of dementia that progressively affects the patients. Shape descriptors could better differentiate the morphological alterations of brain structures and aid in the development of prospective disease modifying therapies. Ventricle enlargement is considered as a significant biomarker in the AD diagnosis. In this work, a method has been proposed to differentiate MCI from the healthy normal and AD subjects using Laplace-Beltrami (LB) eigen value shape descriptors. Prior to this, Reaction Diffusion (RD) level set is used to segment the ventricles in MR images and the results are validated against the Ground Truth (GT). LB eigen values are infinite series of spectrum that describes the intrinsic geometry of objects. Most significant LB shape descriptors are identified and their performance is analysed using linear Support Vector Machine (SVM) classifier. Results show that, the RD level set is able to segment the ventricles. The segmented ventricles are found to have high correlation with GT. The eigen values in the LB spectrum could show distinction in the feature space better than the geometric features. High accuracy is observed in the classification results of linear SVM. The proposed automated system is able to distinctly separate the MCI from normal and AD subjects. Thus this pipeline of work seems to be clinically significant in the automated analysis of dementic subjects.

Diagnostic differentiation of mild cognitive impairment due to Alzheimer's disease using a hippocampus-dependent test of spatial memory.

The hippocampus is one of the earliest brain regions affected in Alzheimer's disease (AD) and tests of hippocampal function have the potential to detect AD in its earliest stages. Given that the hippocampus is critically involved in allocentric spatial memory, this study applied a short test of spatial memory, the 4 Mountains Test (4MT), to determine whether test performance can differentiate mild cognitive impairment (MCI) patients with and without CSF biomarker evidence of underlying AD and whether the test can distinguish patients with MCI and mild AD dementia when applied in different cultural settings. Healthy controls (HC), patients with MCI, and mild AD dementia were recruited from study sites in UK and Italy. Study numbers were: HC (UK 20, Italy 10), MCI (UK 21, Italy 14), and AD (UK 11, Italy 9). Nineteen UK MCI patients were grouped into CSF biomarker-positive (MCI+, n = 10) and biomarker-negative (MCI-, n = 9) subgroups. Behavioral data were correlated with hippocampal volume and cortical thickness of the precuneus and posterior cingulate gyrus. Spatial memory was impaired in both UK and Italy MCI and AD patients. Test performance additionally differentiated between MCI+ and MCI- subgroups (P = 0.001). A 4MT score of ≤8/15 was associated with 100% sensitivity and 90% specificity for detection of early AD (MCI+ and mild AD dementia) in the UK population, and with 100% sensitivity and 50% specificity for detection of MCI and AD in the Italy sample. 4MT performance correlated with hippocampal volume in the UK population and cortical thickness of the precuneus in both study populations. In conclusion, performance on a hippocampus-sensitive test of spatial memory differentiates MCI due to AD with high diagnostic sensitivity and specificity. The observation that similar diagnostic sensitivity was obtained in two separate study populations, allied to the scalability and usability of the test in community memory clinics, supports future application of the 4MT in the diagnosis of pre-dementia due to AD.

P-1023 - A chinese version of montreal cognitive assessment as a brief screening tool for mild cognitive impairment: a population-based study

The sensitivity and specificity of a Chinese version of Montreal Cognitive Assessment (MoCA-CV) for Screening mild cognitive impairment (MCI) were examined. MoCA-CV and MMSE together with a battery of neuropsychological tests were administered to 1056 elders who were recruited from three regions of Beijing (i.e. new town, old town, rural areas). Twenty-six participants were diagnosed with dementia, 118 were MCI by psychiatrists and neurologists, and 875 were considered to be cognitively normal based on independent neuropsychological tested. Using the recommended cut-off score of 26, the MoCA-CV had an excellent sensitivity of 90.4% to detect MCI from controls, while the specificity was relatively poor (32.0%). Using a lower cut-off score of 22, the MoCA-CV exhibited the optimal balanced sensitivity of 68.7% and specificity of 65.2%. Among all the seven cognitive sub-domains, delayed recall performed the best differentiation of MCI from normal controls. Item analysis showed the internal consistency was relatively low in both naming and sentence repetition tasks which related with the characteristics of Chinese language and culture. Region differences were not significant when such confounding demographic variables as age, gender and education were controlled. The MoCA-CV is a brief and effective screening tool for detecting MCI. However, presumably due to linguistic and culture issues and the lower education level of Chinese elders, the MoCA-CV did not show better screening capability than MMSE as expected. Some items may need further adaptation to accommodate the language, culture and education characteristics of Chinese participants.

Quantitative EEG in progressing vs stable mild cognitive impairment (MCI): results of a 1‐year follow‐up study

The study objective is to evaluate the use of qEEG data for the cross-sectional differentiation of mild cognitive impairment (MCI) from mild Alzheimer's disease (AD) and in the longitudinal prediction of cognitive decline in MCI. Eighty-eight subjects with MCI and 42 subjects with mild probable AD were enrolled. Baseline EEGs were recorded using a 32-channel system with electrode positioning according to the international 10-20 system. Digitalized EEG data were further studied by quantitative spectral analysis. Study subjects were followed up for 1 year and reassessed psychometrically. An increase of the total ADAS-cog score of >or= 4 points was regarded as a significant cognitive decline. Using this cut-off, MCI subjects were sub-grouped into stable MCI (s-MCI) and progressing MCI (p-MCI). AD subjects and p-MCI subjects were differentiated from s-MCI subjects by a reduction of alpha power over posterior leads. Reduction of alpha power and mean frequency were significantly correlated with poorer cognitive performance in psychometric tests. Baseline values of alpha power over posterior leads had the highest positive predictive power for MCI and AD (69-80%) and predicted cognitive decline in MCI within a 1-year follow up. qEEG revealed decreased alpha activity in progressing MCI and mild AD prior to an increase of slow wave activity, which typically occurs in advancing AD. This finding may reflect an affection of thalamo-cortical relay activity and cortical connectivity in the early disease course of AD. Reduced alpha activity in MCI subjects at baseline may have prognostic value regarding future cognitive decline.

Using duration of memory loss to improve differentiation of mild cognitive impairment from normal cognition

Using duration of memory loss to improve differentiation of mild cognitive impairment from normal cognition

0780 Differentiation of mild cognitive impairment and Alzheimer's disease with Bulgarian version of CERAD

0780 Differentiation of mild cognitive impairment and Alzheimer's disease with Bulgarian version of CERAD