Problems in Classifying Mild Cognitive Impairment (MCI): One or Multiple Syndromes?

Designing an effective semantic fluency test for early MCI diagnosis with machine learning

Semantic fluency tests are one of the key tests used in batteries for the early detection of Mild Cognitive Impairment (MCI) as the impairment in speech and semantic memory are among the first symptoms, attracting the attention of a large number of studies. Several new semantic categories and variables capable of providing complementary information of clinical interest have been proposed to increase their effectiveness. However, this also extends the time required to complete all tests and get the overall diagnosis. Therefore, there is a need to reduce the number of tests in the batteries and thus the time spent on them while maintaining or increasing their effectiveness. This study used machine learning methods to determine the smallest and most efficient combination of semantic categories and variables to achieve this goal. We utilized a database containing 423 assessments from 141 subjects, with each subject having undergone three assessments spaced approximately one year apart. Subjects were categorized into three diagnostic groups: Healthy (if diagnosed as healthy in all three assessments), stable MCI (consistently diagnosed as MCI), and heterogeneous MCI (when exhibiting alternations between healthy and MCI diagnoses across assessments). We obtained that the most efficient combination to distinguish between these categories of semantic fluency tests included the animals and clothes semantic categories with the variables corrects, switching, clustering, and total clusters. This combination is ideal for scenarios that require a balance between time efficiency and diagnosis capability, such as population-based screenings.

Effect of combined physical-cognitive training on the functional and cognitive capacity of older people with mild cognitive impairment: a randomized controlled trial

BACKGROUND

The increase in population aging highlights the growing prevalence of mild cognitive impairment, prompting the adoption of interventions that combine physical exercise and cognitive training to improve health and cognitive performance in older adults. The aim of this study was to analyze the efficacy of a combined program on physical and cognitive health in older people with cognitive impairment.

METHODS

A 12-week randomized controlled clinical trial involving 95 participants (aged 72.12 ± 4.25 years), 47 individuals participated in a control group (CG) that only underwent cognitive stimulation, while 48 individuals were in an experimental group (EG) that participated in a combined program. Balance was measured using the Tinetti scale, upper body strength was assessed with the arm curl test, lower body strength was evaluated with the 30-s chair stand test, flexibility was tested using the back scratch test and chair sit-and-reach test, physical function was measured with the Timed Up and Go test, cognitive function was assessed using the Mini Mental State Examination, cognitive impairment was evaluated with the Montreal Cognitive Assessment, verbal fluency was tested with the Isaac test, and executive functions were assessed using the Trail Making Test.

RESULTS

The results of the study show significant improvements in both physical and cognitive aspects, such as balance, gait, upper and lower body strength, flexibility, physical function, cognitive function, cognitive impairment, verbal fluency, and executive functions in the group that carried out the intervention compared to the control group.

CONCLUSION

A combined program for older individuals with mild cognitive impairment leads to enhancements in physical and cognitive health. These improvements underscore the importance of integrating physical exercise with cognitive training as an effective strategy for enhancing overall health and quality of life in older adults.

TRIAL REGISTRATION

NCT05503641.

Longitudinal trajectory effects of different MCI subtypes on general cognitive and daily functions in a population-based cohort of older adults

OBJECTIVES

To identify different mild cognitive impairment (MCI) phenotypes based on substantial relative impairment in specific cognitive domains and then characterize the complex process of general cognitive and daily functions over time in older adults with these MCI subtypes.

METHODS

A total of 1020 participants with MCI at baseline from the Alzheimer's Disease Neuroimaging Initiative (ADNI) were recruited. MCI subtypes were obtained based on neuropsychological tests in five cognitive domains: memory (M), visuospatial function (V), language (L), processing speed (P), and executive function (E). General cognitive function and daily function were measured by the Mini-Mental State Examination (MMSE) and the Functional Assessment Questionnaire (FAQ), respectively. Linear mixed models were fitted to curve their trajectories across different MCI subtypes.

RESULTS

Considering visuospatial function, subtypes were MO (memory impaired only), M&V (memory and visuospatial function impaired) and M&nV (memory impaired and visuospatial function non-impaired). Similar subtypes and naming rules were obtained based on language, executive function, and processing speed. Further, depending on the number of relative impaired cognitive domains M&S and M&M were obtained. Participants with MO had the highest prevalence in the sample (53.4 %), followed by M&nV (31.1 %). Participants with M&V had the highest mean age (74.69 years) at baseline and the greatest dementia conversion rate (53.2 %). The MMSE and FAQ score trajectories changed most slowly in participants with MO while fastest in those with M&V. Obvious different trajectories of both MMSE and FAQ scores were observed across different subtypes based on visuospatial function and executive function.

CONCLUSION

Compared to MO, individuals with multi-dimensional cognitive impairment have worse general cognitive and daily functions, especially for those with M&V.

Analysis of Convergent Validity of Performance-Based Activities of Daily Living Assessed by PA-IADL Test in Relation to Traditional (Standard) Cognitive Assessment to Identify Older Adults with Mild Cognitive Impairment

Difficulty in performing instrumental activities of daily living (IADLs) is currently considered an important indicator of cognitive impairment in the elderly. A non-experimental case-control investigation was conducted to assess the convergent validity of the PA-IADL with traditional (standard) cognitive assessment tests in its ability to identify adults with mild cognitive impairment. The analysis of the data was carried out by means of various multivariate statistical tests, and the sequence in its execution led to the conclusion that 8 of the 12 Tasks that make up the PA-IADL allow for the identification of people with mild cognitive impairment (MCI) to the same extent as traditional cognitive assessment tests and regardless of age. Age was found to be a moderating variable in the performance of the eight tasks; however, the results allow us to hypothesize that people with MCI experience a significant decline when it happens but thereafter, the deterioration that occurs does so at the same rate as the deterioration experienced by healthy people. They also allow us to hypothesize that the difference in the cognitive skills required by the eight functional tasks, and therefore also in the cognitive skills required by the traditional (standard) tests of a person with MCI compared to a person of the same age without MCI (Healthy), is approximately 10 years. These hypotheses have remarkable relevance and should be tested via longitudinal research. In the meantime, the results highlight the importance of the IADL assessment for the diagnosis of MCI as a complement to the standard cognitive assessment.

A common spectrum underlying brain disorders across lifespan revealed by deep learning on brain networks

Brain disorders in the early and late life of humans potentially share pathological alterations in brain functions. However, the key neuroimaging evidence remains unrevealed for elucidating such commonness and the relationships among these disorders. To explore this puzzle, we build a restricted single-branch deep learning model, using multi-site functional magnetic resonance imaging data (N = 4,410, 6 sites), for classifying 5 different early- and late-life brain disorders from healthy controls (cognitively unimpaired). Our model achieves 62.6 ± 1.9% overall classification accuracy and thus supports us in detecting a set of commonly affected functional subnetworks, including default mode, executive control, visual, and limbic networks. In the deep-layer representation of data, we observe young and aging patients with disorders are continuously distributed, which is in line with the clinical concept of the "spectrum of disorders." The relationships among brain disorders from the revealed spectrum promote the understanding of disorder comorbidities and time associations in the lifespan.

Time-Based and Event-Based Prospective Memory in Mild Cognitive Impairment and Alzheimer's Disease Patients: A Systematic Review and Meta-analysis

Prospective memory (PM) is the ability to remember to perform planned actions in a future moment and it is of fundamental importance for an independent and autonomous lifestyle from development to late adulthood. Deficits in episodic memory and executive functions, which are involved in PM are characteristic features of mild cognitive impairment (MCI) and Alzheimer's disease (AD). Considering that the number of older adults is drastically increasing over the next decades, it is of great interest to understand how PM decline in healthy older adults and patients with different degree of cognitive decline. The present meta-analysis included 46 studies investigating PM performance in AD patients (17 studies) and people with MCI (24 studies); 5 studies included both clinical conditions in the same article. The 46 studies contributed a total of 63 independent samples and 129 effect sizes from 4668 participants (2115 patients and 2553 controls). Unlike previous reviews of the literature, our results with a larger and updated sample of studies confirmed lower PM abilities in AD compared to MCI and controls, although we did not observe conclusive differences between event-based and time-based PM in patients. Surprisingly, PM deficits shown by MCI and AD patients have decreased across years, in parallel to a reduction of the evidence of publication bias and an increase in the number of observations per task. We propose the use of more reliable research designs as one plausible explanation for the reduction of PM impairments.

Dissociating memory and executive function impairment through temporal features in a word list verbal learning task

The Rey Auditory Verbal Learning Test (RAVLT) is an established verbal learning test commonly used to quantify memory impairments due to Alzheimer's Disease (AD) both at a clinical dementia stage or prodromal stage of mild cognitive impairment (MCI). Focal memory impairment-as quantified e.g. by the RAVLT-at an MCI stage is referred to as amnestic MCI (aMCI) and is often regarded as the cognitive phenotype of prodromal AD. However, recent findings suggest that not only learning and memory but also other cognitive domains, especially executive functions (EF) and processing speed (PS), influence verbal learning performance. This research investigates whether additional temporal features extracted from audio recordings from a participant's RAVLT response can better dissociate memory and EF in such tasks and eventually help to better describe MCI subtypes. 675 age-matched participants from the H70 Swedish birth cohort were included in this analysis; 68 participants were classified as MCI (33 aMCI and 35 due to executive impairment). RAVLT performances were recorded and temporal features extracted. Novel temporal features were correlated with established neuropsychological tests measuring EF and PS. Lastly, the downstream diagnostic potential of temporal features was estimated using group differences and a machine learning (ML) classification scenario. Temporal features correlated moderately with measures of EF and PS. Performance of an ML classifier could be improved by adding temporal features to traditional counts. We conclude that RAVLT temporal features are in general related to EF and that they might be capable of dissociating memory and EF in a word list learning task.

Openness and age influence cognitive progression: a longitudinal study

BACKGROUND

Some psychological and personality characteristics of individuals seem to determine behavioral patterns that are associated with better health throughout life and, consequently, prevent the progression of early cognitive changes to dementia.

OBJECTIVE

To identify which individuals have modified cognitive ratings after 24 months of follow-up and correlating with personality traits.

METHODS

One hundred and two volunteers were evaluated clinically and for personality characteristics and neuropsychological testing. Of these, 25 subjects were classified as cognitively normal (CN), 25 as subjective cognitive decline (SCD), 28 as nonamnestic mild cognitive impairment (naMCI), and 24 as amnestic mild cognitive impairment (amMCI) at baseline. Follow-up occurred over 2 years from the initial assessment, and the cognitive categories of the participants were re-analyzed every 6 months to observe differences in their classification.

RESULTS

Out of the 102 subjects, 65 remained at follow-up. The sample followed-up longitudinally was composed predominantly of women (65%), white (74%), with a mean age of 78 (±7.5) years old and 12 (±4.8) years of schooling. Throughout the process, 23% of CN, 15% of SDC, and 27% of naMCI individuals worsened cognitively. Amnestic with mild cognitive impairment volunteers remained stable or improved. Individuals with older age show more significant cognitive deterioration, and those with very low or high rates of the openness personality trait are associated with cognitive decline utilizing the Fisher exact test, probably because the open extremes influence choices, stress management, and behavioral maintenance.

CONCLUSION

The factors most associated with cognitive change in this group of older adults were age and the intensity of the openness aspects of personality.

A promising tool to explore functional impairment in neurodegeneration: A systematic review of near-infrared spectroscopy in dementia

This systematic review aimed to evaluate previous studies which used near-infrared spectroscopy (NIRS) in dementia given its suitability as a diagnostic and investigative tool in this population. From 800 identified records which used NIRS in dementia and prodromal stages, 88 studies were evaluated which employed a range of tasks testing memory (29), word retrieval (24), motor (8) and visuo-spatial function (4), and which explored the resting state (32). Across these domains, dementia exhibited blunted haemodynamic responses, often localised to frontal regions of interest, and a lack of task-appropriate frontal lateralisation. Prodromal stages, such as mild cognitive impairment, revealed mixed results. Reduced cognitive performance accompanied by either diminished functional responses or hyperactivity was identified, the latter suggesting a compensatory response not present at the dementia stage. Despite clear evidence of alterations in brain oxygenation in dementia and prodromal stages, a consensus as to the nature of these changes is difficult to reach. This is likely partially due to the lack of standardisation in optical techniques and processing methods for the application of NIRS to dementia. Further studies are required exploring more naturalistic settings and a wider range of dementia subtypes.

The role of semantic assessment in the differential diagnosis between late-life depression and Alzheimer's disease or amnestic mild cognitive impairment: systematic review and meta-analysis

OBJECT

The cognitive complaints encountered in late-life depression (LLD) make it difficult to distinguish from amnestic mild cognitive impairment (aMCI) and Alzheimer's disease (AD) based on an analysis of neurocognitive disorders. The hypothesis of the early impairment of semantic memory in AD and aMCI is considered a potential differential cognitive clue, but the absence of this impairment has not yet been confirmed in  LLD.

METHOD

Based on the PRISMA method, we systematically seek neuropsychological assessments of individuals with LLD, the present study included 31 studies representing 3291 controls and 2820 people with LLD. Wherever possible, studies that tested simultaneously groups with LLD, AD (or aMCI) were also included. The results of the group of neuropsychological tasks relying on semantic memory were analyzed in two groups of tasks with high- or low-executive demand. The mean average effect of LLD was calculated and compared to the incremental effect of aMCI or AD on the scores. Linear regressions including education, age, and severity and type of depression were run to seek their power of prediction for the mean average effects.

RESULTS

LLD has a medium effect on scores at semantic and phonemic fluency and naming and a small average effect on the low-executive demand tasks. Differences in education is a predictor of the effect of LLD on phonemic fluency and naming but not on semantic fluency or on low-executive demand tasks. Except for semantic fluency, aMCI did not demonstrate an incremental effect on the scores compared to LLD, while AD did, for all the tasks except phonemic fluency.

CONCLUSION

Assessment of semantic memory can be a discriminating clue for the distinction between depression and Alzheimer's disease but some methodological variables are highly influential to the scores, especially education. However, high-executive semantic tasks alone do not allow us to clearly distinguish LLD from AD or aMCI, as both pathologies seem to have a largely dialectical influential relationship, but low-executive semantic tasks appear as more sensible to this pathological distinction.

Acquisition and consolidation of verbal learning and episodic memory as predictors of the conversion from mild cognitive impairment to probable Alzheimer's disease

Verbal episodic memory tests assess memory performance using total learning scores. The analysis of inter-trial indices such as gained (GA) and lost (LA) access can provide additional information on the acquisition and consolidation processes. The main objetive was to determine whether the GA and LA indices, derived from a word-list verbal episodic memory test are useful for predicting cognitive impairment in aging. 60 older people aged was divided into 3 groups: cognitively healthy, stable Mild Cognitive Impairment (MCI) and MCI converting to probable Alzheimer's disease (MCI-conv). The results showed that GA and LA measures are independent from the traditional measures -total score of correct answers-. Logistic regression showed that these values are predictive of the conversion over time and could be a cognitive marker of conversion from MCI to AD. This suggests that the GA index, which shows acquisition processes in word-list tests, may be a marker of cognitive impairment.

Accelerated long-term forgetting in neurodegenerative disorders: A systematic review of the literature

Accelerated Long-term Forgetting (ALF) is a memory deficit characterised by normal retention up to relatively short intervals (e.g., minutes, hours) with increased forgetting over longer periods (e.g., days, weeks). ALF is often underestimated due to a lack of common memory assessments beyond 30-60 min. The purpose of this review was to provide an overview of ALF occurrence in neurodegenerative disorders, evaluating whether it can be considered a cognitive deficit useful for diagnosing and monitoring patients. We included 19 experimental studies that investigated ALF in neurodegenerative disorders. Most papers were focused on Alzheimer's disease (AD) dementia and related forms of cognitive decline (Mild Cognitive Impairment, Subjective Cognitive decline, Pre-symptomatic subjects at risk of AD dementia). The major finding of the present work concerns the presence of ALF in very early forms of cognitive decline related to AD. These findings, supporting the hypothesis that ALF is a subtle and undetected hallmark of pre-clinical AD, highlights the importance of investigating forgetting over a longer period and devising standardised measures to be included in clinical practice.

Effects of cognitive interventions on quality of life among adults with mild cognitive impairment: A systematic review and meta-analysis of randomised controlled trials

BACKGROUND

There is considerable research exploring the impact of cognitive interventions on cognition in people with mild cognitive impairment (MCI). However, the impact on quality of life (QOL) is not routinely reported. As QOL is a key predictor of health outcomes, it is important to determine the evidence supporting cognitive interventions for improving QOL in people with MCI.

OBJECTIVE

To evaluate the evidence on the effectiveness of cognitive interventions for improving QOL among people with MCI.

DESIGN

Systematic review and meta-analysis.

METHODS

A systematic database search was conducted from inception to December 11, 2021, using four databases. Quality assessment was conducted, and data on the characteristics of the studies and the effects on QOL were extracted. Subgroup analyses and meta-regression were conducted to elucidate the effects of potential moderator variables on QOL measures.

RESULTS

Of the 1550 records initially identified, 17 studies met the criteria for the final meta-analysis. The findings revealed that cognitive interventions produced moderate gains in overall QOL compared to the control group at the posttest (standardized mean difference (SMD): 0.53, 95% confidence interval (CI): [0.23, 0.84]), but no statistically significant differences were found at the end of follow-up (SMD: 0.40, 95% CI: [-0.15,0.94]). Furthermore, the effects of cognitive interventions were moderated by intervention duration, session duration, and study location. However, intervention types, session frequency, intervention components, control condition, total number of sessions, types of QOL measures, and responders to QOL-AD had no statistically significant effects on QOL outcome.

CONCLUSIONS

Cognitive interventions have positive effects on QOL among adults with MCI. However, the high heterogeneity of the included studies calls for more well-designed cognitive intervention trials to examine the association between QOL and relevant moderators.

OUP accepted manuscript

Subcortical ischemic vascular disease could induce subcortical vascular cognitive impairments (SVCIs), such as amnestic mild cognitive impairment (aMCI) and non-amnestic MCI (naMCI), or sometimes no cognitive impairment (NCI). Previous SVCI studies focused on focal structural lesions such as lacunes and microbleeds, while the functional connectivity networks (FCNs) from functional magnetic resonance imaging are drawing increasing attentions. Considering remarkable variations in structural lesion sizes, we expect that seeking abnormalities in the multiscale hierarchy of brain FCNs could be more informative to differentiate SVCI patients with varied outcomes (NCI, aMCI, and naMCI). Driven by this hypothesis, we first build FCNs based on the atlases at multiple spatial scales for group comparisons and found distributed FCN differences across different spatial scales. We then verify that combining multiscale features in a prediction model could improve differentiation accuracy among NCI, aMCI, and naMCI. Furthermore, we propose a graph convolutional network to integrate the naturally emerged multiscale features based on the brain network hierarchy, which significantly outperforms all other competing methods. In addition, the predictive features derived from our method consistently emphasize the limbic network in identifying aMCI across the different scales. The proposed analysis provides a better understanding of SVCI and may benefit its clinical diagnosis.

Discovery of a Metabolic Signature Predisposing High Risk Patients with Mild Cognitive Impairment to Converting to Alzheimer's Disease

Assessing dementia conversion in patients with mild cognitive impairment (MCI) remains challenging owing to pathological heterogeneity. While many MCI patients ultimately proceed to Alzheimer’s disease (AD), a subset of patients remain stable for various times. Our aim was to characterize the plasma metabolites of nineteen MCI patients proceeding to AD (P-MCI) and twenty-nine stable MCI (S-MCI) patients by untargeted metabolomics profiling. Alterations in the plasma metabolites between the P-MCI and S-MCI groups, as well as between the P-MCI and AD groups, were compared over the observation period. With the help of machine learning-based stratification, a 20-metabolite signature panel was identified that was associated with the presence and progression of AD. Furthermore, when the metabolic signature panel was used for classification of the three patient groups, this gave an accuracy of 73.5% using the panel. Moreover, when specifically classifying the P-MCI and S-MCI subjects, a fivefold cross-validation accuracy of 80.3% was obtained using the random forest model. Importantly, indole-3-propionic acid, a bacteria-generated metabolite from tryptophan, was identified as a predictor of AD progression, suggesting a role for gut microbiota in AD pathophysiology. Our study establishes a metabolite panel to assist in the stratification of MCI patients and to predict conversion to AD.

Mild Cognitive Impairment Detection Using Machine Learning Models Trained on Data Collected from Serious Games

Mild cognitive impairment (MCI) is an indicative precursor of Alzheimer’s disease and its early detection is critical to restrain further cognitive deterioration through preventive measures. In this context, the capacity of serious games combined with machine learning for MCI detection is examined. In particular, a custom methodology is proposed, which consists of a series of steps to train and evaluate classification models that could discriminate healthy from cognitive impaired individuals on the basis of game performance and other subjective data. Such data were collected during a pilot evaluation study of a gaming platform, called COGNIPLAT, with 10 seniors. An exploratory analysis of the data is performed to assess feature selection, model overfitting, optimization techniques and classification performance using several machine learning algorithms and standard evaluation metrics. A production level model is also trained to deal with the issue of data leakage while delivering a high detection performance (92.14% accuracy, 93.4% sensitivity and 90% specificity) based on the Gaussian Naive Bayes classifier. This preliminary study provides initial evidence that serious games combined with machine learning methods could potentially serve as a complementary or an alternative tool to the traditional cognitive screening processes.

Prospective and retrospective timing in mild cognitive impairment and Alzheimer's disease patients: A systematic review and meta-analysis

Performance on timing tasks changes with age. Whether these changes reflect a real "clock" problem due to aging or a secondary effect of the reduced cognitive resources of older adults is still an unsettled question. Research on processing of time in aged populations marked by severe mnemonic and/or attentional deficits, such as patients with Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI), may help elucidate the role of cognitive resources in age-related temporal distortions. To this end, we conducted a systematic review and meta-analysis of timing studies in AD and MCI patients; both prospective and retrospective timing tasks were considered and analysed separately. As concerns prospective timing, a first random-effect model showed a medium overall effect of neurodegeneration on timing performance. When considering the role of moderator variables(i.e., neurodegenerative condition, type of measure, participants' age and years of education, interval length, and type of timing task), mean score appeared to be a less sensitive measure than accuracy and variability, and the observed temporal impairment was smaller in older samples. In addition, AD patients only exhibited medium-to-high impairment on prospective timing tasks, whereas MCI patients did not significantly differ from controls. However, assuming a mean age of 70 years old and absolute error as dependent variable, a second fitted meta-regression model predicted a significant outcome also for MCI patients. Concerning retrospective timing, a significant but small effect of neurodegeneration was observed for retrospective judgments. None of the moderators, however, explained between-studies variability. Collectively, our findings highlight a clear deficit in prospective timing for AD patients and underscore several issues that future work should carefully consider to better investigate the effect of MCI on prospective temporal judgements. Results from retrospective timing also point to a possible impairment of retrospective judgments in neurodegenerative conditions, albeit more studies are needed to substantiate this finding.

Effect of education on cognitive performance in patients with mild cognitive impairment

This study aims to investigate if education (as a cognitive reserve proxy) modifies the profile of cognitive performance. We hypothesize that participants with higher education can remain functional (due to a better executive performance), despite a more severe memory impairment, compared with lower education individuals. One hundred and sixty-six mild cognitive impairment (MCI) individuals with at least one comprehensive neuropsychological evaluation were included in a retrospective, cross-sectional study and divided into two groups (Low Education-LE [1-4 years] and Medium-to-High Education-MHE [> 4 years]). A total of 22 neuropsychological measures were analyzed. Age-adjusted results were subject to simple regression analyses to determine the variance explained by education. Average scores and proportions of low performances were subject to group comparison. The results showed similar cognitive decline patterns between individuals with LE and MHE, with no significant difference in each cognitive domain. However, MHE revealed a steeper decline in certain cognitive domains, such as sustained attention and episodic memory, compared with the LE. Moreover, MHE showed a trend to higher proportion of tests affected when compared to LE. These suggest that individuals with higher education may remain in a MCI stage despite a more widespread cognitive impairment, reflecting a higher cognitive reserve.

Integrative Base Ontology for the Research Analysis of Alzheimer's Disease-Related Mild Cognitive Impairment

Early detection of mild cognitive impairment (MCI) has become a priority in Alzheimer's disease (AD) research, as it is a transitional phase between normal aging and dementia. However, information on MCI and AD is scattered across different formats and standards generated by different technologies, making it difficult to work with them manually. Ontologies have emerged as a solution to this problem due to their capacity for homogenization and consensus in the representation and reuse of data. In this context, an ontology that integrates the four main domains of neurodegenerative diseases, diagnostic tests, cognitive functions, and brain areas will be of great use in research. Here, we introduce the first approach to this ontology, the Neurocognitive Integrated Ontology (NIO), which integrates the knowledge regarding neuropsychological tests (NT), AD, cognitive functions, and brain areas. This ontology enables interoperability and facilitates access to data by integrating dispersed knowledge across different disciplines, rendering it useful for other research groups. To ensure the stability and reusability of NIO, the ontology was developed following the ontology-building life cycle, integrating and expanding terms from four different reference ontologies. The usefulness of this ontology was validated through use-case scenarios.

Prediction of transition from mild cognitive impairment to Alzheimer's disease based on a logistic regression-artificial neural network-decision tree model

AIM

To develop a logistic regression model, artificial neural network (ANN) model and decision tree (DT) model for the progression of mild cognitive impairment (MCI) to Alzheimer's disease (AD) to compare the performance of the three models.

METHODS

A total of 425 patients with MCI were screened from the original cohort. The actual follow up included 361 patients, with AD as the outcome variable. Three kinds of prediction models were developed: a logistic regression model, ANN model and DT model. The performance of all three models was measured with accuracy, sensitivity, positive predictive value and area under the receiver operating characteristic curve.

RESULTS

A total of 121 patients with MCI developed AD, and the average conversion rate was 9.49% per year. The ANN model had higher accuracy (89.52 ± 0.36%), area under the receiver operating characteristic curve (92.08 ± 0.12), sensitivity (82.11 ± 0.42%) and positive predictive value (75.26 ± 0.86%) than the other two models. The first five important predictors of the ANN model were, in order, ADL score, age, urine AD-associated neuronal thread protein, alcohol consumption and smoking. For the DT model, they were age, activities of daily living score, family history of dementia, urine AD-associated neuronal thread protein and alcohol consumption. For the logistic regression model, they were age, sex, activities of daily living score, alcohol consumption and smoking.

CONCLUSION

The logistic regression, ANN and DT models performed well at predicting the transition from MCI to AD with ideal stability. However, the ANN model had the best predictive value. Increased age, activities of daily living score, urine AD-associated neuronal thread protein, alcohol consumption, smoking and sex were important factors. Geriatr Gerontol Int 2021; 21: 43-47.

Digital Biomarkers for the Early Detection of Mild Cognitive Impairment: Artificial Intelligence Meets Virtual Reality

Elderly people affected by Mild Cognitive Impairment (MCI) usually report a perceived decline in cognitive functions that deeply impacts their quality of life. This subtle waning, although it cannot be diagnosable as dementia, is noted by caregivers on the basis of their relative’s behaviors. Crucially, if this condition is also not detected in time by clinicians, it can easily turn into dementia. Thus, early detection of MCI is strongly needed. Classical neuropsychological measures – underlying a categorical model of diagnosis - could be integrated with a dimensional assessment approach involving Virtual Reality (VR) and Artificial Intelligence (AI). VR can be used to create highly ecologically controlled simulations resembling the daily life contexts in which patients’ daily instrumental activities (IADL) usually take place. Clinicians can record patients’ kinematics, particularly gait, while performing IADL (Digital Biomarkers). Then, Artificial Intelligence employs Machine Learning (ML) to analyze them in combination with clinical and neuropsychological data. This integrated computational approach would enable the creation of a predictive model to identify specific patterns of cognitive and motor impairment in MCI. Therefore, this new dimensional cognitive-behavioral assessment would reveal elderly people’s neural alterations and impaired cognitive functions, typical of MCI and dementia, even in early stages for more time-sensitive interventions.

Machine Learning Analysis of Digital Clock Drawing Test Performance for Differential Classification of Mild Cognitive Impairment Subtypes Versus Alzheimer's Disease

OBJECTIVE

To determine how well machine learning algorithms can classify mild cognitive impairment (MCI) subtypes and Alzheimer's disease (AD) using features obtained from the digital Clock Drawing Test (dCDT).

METHODS

dCDT protocols were administered to 163 patients diagnosed with AD(n = 59), amnestic MCI (aMCI; n = 26), combined mixed/dysexecutive MCI (mixed/dys MCI; n = 43), and patients without MCI (non-MCI; n = 35) using standard clock drawing command and copy procedures, that is, draw the face of the clock, put in all of the numbers, and set the hands for "10 after 11." A digital pen and custom software recorded patient's drawings. Three hundred and fifty features were evaluated for maximum information/minimum redundancy. The best subset of features was used to train classification models to determine diagnostic accuracy.

RESULTS

Neural network employing information theoretic feature selection approaches achieved the best 2-group classification results with 10-fold cross validation accuracies at or above 83%, that is, AD versus non-MCI = 91.42%; AD versus aMCI = 91.49%; AD versus mixed/dys MCI = 84.05%; aMCI versus mixed/dys MCI = 84.11%; aMCI versus non-MCI = 83.44%; and mixed/dys MCI versus non-MCI = 85.42%. A follow-up two-group non-MCI versus all MCI patients analysis yielded comparable results (83.69%). Two-group classification analyses were achieved with 25-125 dCDT features depending on group classification. Three- and four-group analyses yielded lower but still promising levels of classification accuracy.

CONCLUSION

Early identification of emergent neurodegenerative illness is criterial for better disease management. Applying machine learning to standard neuropsychological tests promises to be an effective first line screening method for classification of non-MCI and MCI subtypes.

Individual and combined effects of a cognitive task, light finger touch, and vision on standing balance in older adults with mild cognitive impairment

BACKGROUND

Postural instability and balance dysfunction have been identified in older adults with mild cognitive impairment (MCI). Performing a secondary task while standing can additionally jeopardize their balance.

AIMS

The purpose of the exploratory study was to investigate the individual and combined effects of a cognitive task, light finger touch and vision on postural sway in older adults with MCI as compared to healthy older adults.

METHODS

Five individuals with MCI and ten age-matched control subjects stood on the force platform with and without the performance of a cognitive task (counting backward from a randomly chosen three-digit number), with and without light finger touch contact applied to an external stable structure, and with eyes open or closed. The center of pressure (COP) excursion, range, velocity in antero-posterior and medial-lateral directions and sway area were calculated.

RESULTS

Participants demonstrated significantly larger postural sway when vision was not available (p < 0.05), smaller postural sway when using a finger touch contact (p < 0.05) and increased postural sway during the performance of the cognitive task (p < 0.05). When finger touch and a cognitive task were performed simultaneously, body sway decreased as compared to just standing in healthy older adults but not in individuals with MCI (p < 0.05).

CONCLUSIONS

The results help to better understand the individual and combined effects of vision, light touch and a cognitive task in postural control of individuals with MCI. The study outcome also provides a basis for future studies of balance control in patients with cognitive impairments.

Longitudinal Patterns of the Tip-of-the-Tongue Phenomenon in People With Subjective Cognitive Complaints and Mild Cognitive Impairment

Background

The Tip-of-the-Tongue (ToTs) state is considered a universal phenomenon and is a frequent cognitive complaint in old age. Previous cross-sectional studies have found that ToT measures successfully discriminate between cognitively unimpaired adults and adults with Mild Cognitive Impairment (MCI). The aim of this study was to identify longitudinal patterns of ToTs in individuals with subjective complaints and with MCI regarding progress of their cognitive status.

Method

The study included 193 participants with subjective cognitive complaints (SCC) and 56 participants with MCI who completed a baseline and two follow-up assessments, with an interval of about 18 months between each assessment. Participants were classified into three groups by considering cognitive stability or deterioration from the baseline diagnosis: SCC-stable, MCI-stable and MCI-worsened. Participants performed a ToT task involving recognition and naming of famous people depicted in 50 photographs. Generalized Linear Mixed Models (GLMM) were used to model longitudinal changes in familiarity, feeling of knowing, semantic access, phonological access and verbal fluency.

Results

Phonological access differentiated MCI patients, stable and worsened, from adults with SCCs at all evaluation times. Phonological access declined over time in the three groups, without significant interactions between groups and time.

Discussion

This study provides the first longitudinal evidence of differences in ToT measures for adults with MCI. The findings indicate that phonological access measures successfully differentiated between the diagnostic groups. However, slopes remain irrespective of the diagnostic group and progression toward more advance stages of cognitive impairment.

Role of a single session of ball throwing exercise on postural control in older adults with mild cognitive impairment

PURPOSE

The purpose of the study was to investigate the role of training in improvement of balance control in older adults with mild cognitive impairment.

METHODS

Older adults (mean age 78) with mild cognitive impairment (MCI) and cognitively intact older adults (mean age 72) were exposed to self-initiated perturbations while performing bilateral shoulder flexion task before and after a single training session consisting of throwing a medicine ball. EMG activity of six trunk and lower limb muscles was recorded. Muscle onsets, integrals of EMG, and muscle co-contraction (C) and reciprocal (R) activation indices were calculated and analyzed during the anticipatory and compensatory phases of postural control.

RESULTS

Anticipatory postural adjustments (APAs) were observed in both groups.  Individuals with MCI, as compared to controls, had higher level of co-contraction of muscles. The training resulted in enhancement of the generation of APAs in individuals with MCI seen as earlier onset of leg and trunk muscle activity prior to the bilateral arm flexion task. While smaller co-contraction of muscles post-training was seen in both the groups, the effect of a single training session was significant in control subjects only.

CONCLUSIONS

The outcome of the exploratory study suggests that perturbation-based training could be used to improve balance control in older adults with and without mild cognitive impairment.

Can mild cognitive impairment be stabilized by showering brain mitochondria with laser photons?

There is now substantial evidence that cerebral blood flow (CBF) declines with age. From age 20 to 60, CBF is estimated to dip about 16% and continues to drop at a rate of 0.4%/year. This CBF dip will slowly reduce oxygen/glucose delivery to brain thus lowering ATP energy production needed by brain cells to perform normal activities. Reduced ATP production from mitochondrial loss or damage in the wear-and-tear of aging worsens when vascular risk factors (VRF) to Alzheimer's disease develop that can accelerate both age-decline CBF and mitochondrial deficiency to a level where mild cognitive impairment (MCI) develops. To date, no pharmacological or any other treatment has been successful in reversing, stabilizing or delaying MCI. For the first time in medical interventions, a non-pharmacological, non-invasive, well-tolerated, easy to perform, free of significant side effects and cost-effective treatment may achieve what virtually all AD treatments in the past have been unable to accomplish. This intervention uses transcranial infrared brain stimulation (TIBS), a form of photobiomodulation (PBM). PBM is a bioenergetic non-ionizing, therapeutic approach using low level light emission from laser or light emitting diodes. PBM has been used in a number of neurological conditions including Parkinson's disease, depression, traumatic brain injury, and stroke with diverse reported benefits. This brief review examines the impact of reduced energy supply stemming from chronic brain hypoperfusion in the aging brain. In this context, the use of TIBS is planned in a randomized, placebo-controlled study of MCI patients to be done at our University Clinic. This article is part of the special issue entitled 'The Quest for Disease-Modifying Therapies for Neurodegenerative Disorders'.

Using an Overlapping Time Interval Strategy to Study Diagnostic Instability in Mild Cognitive Impairment Subtypes

(1) Background: Mild cognitive impairment (MCI) is a diagnostic label in which stability is typically low. The aim of this study was to examine temporal changes in the diagnosis of MCI subtypes by using an overlapping-time strategy; (2) Methods: The study included 435 participants aged over 50 years with subjective cognitive complaints and who completed at least one follow-up evaluation. The probability of transition was estimated using Bayesian odds ratios; (3) Results: Within the different time intervals, the controls with subjective cognitive complaints represented the largest proportion of participants, followed by sda-MCI at baseline and in the first five intervals of the follow-up, but not in the last eight intervals. The odds ratios indicated higher odds of conversion to dementia in sda-MCI and mda-MCI groups relative to na-MCI (e.g., interval 9–15 months—sda-MCI OR = 9 and mda-MCI OR = 3.36; interval 27–33—sda-MCI OR = 16 and mda-MCI = 5.06; interval 42–48—sda-MCI OR = 8.16 and mda-MCI = 3.45; interval 45–51—sda-MCI OR = 3.31 and mda-MCI = 1); (4) Conclusions: Notable patterns of instability consistent with the current literature were observed. The limitations of a prospective approach in the study of MCI transitions are discussed.

Lack of Temporal Impairment in Patients With Mild Cognitive Impairment

In the present study, we investigate possible temporal impairment in patients with mild cognitive impairment (MCI) and the amount of temporal distortions caused by the presentation of emotional facial expressions (anger, shame, and neutral) in MCI patients and controls. Twelve older adults with MCI and 14 healthy older adults were enrolled in the present study. All participants underwent a complete neuropsychological evaluation. We used three timing tasks to tap temporal abilities, namely time bisection (standard intervals lasting 400 and 1600 ms), finger-tapping (free and 1 s), and simple reaction-time tasks. The stimuli used in the time bisection task were facial emotional stimuli expressing anger or shame to investigate a possible contribution of emotional information as previously observed in healthy adults. MCI patients showed temporal abilities comparable to controls. We observed an effect of facial emotional stimuli on time perception when data were analyzed in terms of proportion of long responses, and this result was mainly driven by the temporal overestimation when a facial expression of anger was presented in controls. Results seem to suggest that the severity of the cognitive dysfunction accounts more for subjective temporal impairment than a compromised internal clock.

Potential Fluid Biomarkers for the Diagnosis of Mild Cognitive Impairment

Mild cognitive impairment (MCI) is characterized by a level of cognitive impairment that is lower than normal for a person’s age, but a higher function than that that observed in a demented person. MCI represents a transitional state between normal aging and dementia disorders, especially Alzheimer’s disease (AD). Much effort has been made towards determining the prognosis of a person with MCI who will convert to AD. It is now clear that cerebrospinal fluid (CSF) levels of Aβ40, Aβ42, total tau and phosphorylated tau are useful for predicting the risk of progression from MCI to AD. This review highlights the advantages of the current blood-based biomarkers in MCI, and discusses some of these challenges, with an emphasis on recent studies to provide an overview of the current state of MCI.

Psychometric validation of Fuld Object Memory Evaluation in older adults with cognitive impairments

OBJECTIVES

Mild cognitive impairment (MCI) refers to an early but abnormal state of cognitive impairment with minimal functional impairment. The present study aimed to evaluate the validity of Fuld Object Memory Evaluation (FOME) as a measure of episodic memory function.

METHOD

The study sample included 204 Chinese older adults with cognitive impairments. The participants completed five recall trials and a delayed trial in FOME, neurocognitive measures on digit spans and trail making, and daily functioning. Discriminative power of FOME to differentiate between MCI and dementia was inspected via receiver operating characteristic curve analysis.

RESULTS

FOME showed good test-retest reliability and convergent validity with digit spans and trail making. Controlling for gender, age, and education, lower levels of FOME total retrieval, verbal fluency, and daily functioning significantly predicted a higher likelihood of dementia compared to MCI. The optimal cut-off scores for total retrieval, verbal fluency, and daily functioning to differentiate dementia were 37/38 (77% sensitivity and 83% specificity), 28/29 (85% sensitivity and 72% specificity), and 14/15 (92% sensitivity and 78% specificity), respectively, in the younger subgroup. The corresponding figures were 34/35 (69% sensitivity and 76% specificity) and 27/28 (92% sensitivity and 62% specificity), and 11/12 (74% sensitivity and 80% specificity), respectively, in the older subgroup.

CONCLUSION

The findings support the FOME as a valid assessment tool of episodic memory function in older Chinese adults. The combined use of FOME and daily functioning is recommended to distinguish persons with dementia from MCI.

Language Performance of Individuals at Risk for Mild Cognitive Impairment

Purpose Evidence exists that changes in language performance may be an early indicator of mild cognitive impairment (MCI), often a harbinger of dementing disease. The purpose of this study was the evaluation of language performance in individuals at risk for MCI by virtue of age and self-concern and its relation to performance on tests of memory, visuospatial function, and mental status. Method Eighty-three individuals 55 years or older were administered the Arizona Battery for Communication Disorders of Dementia ( Bayles & Tomoeda, 1993 ), a standardized battery with normative data from 86 healthy older adults (HOAs) and 86 individuals with Alzheimer's dementia, the most common dementing disease. A performance criterion of 1-1.5 SDs below the mean of HOAs defined MCI, as recommended in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition. We hypothesized that (a) the majority of at-risk participants would score 1 SD or more below the mean of HOAs on 1 or more subtests and (b) language performance tests would present a greater challenge than memory, mental status, and visuospatial construction tests. Results Both hypotheses were confirmed. Sixty-two participants (74.6%) met the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, criteria on at least 1 subtest. Moreover, language subtests were those most likely to elicit a performance 1 SD or more below the mean of HOAs. Conclusions Language performance deficits can appear early before impairment in episodic memory, visuospatial construction ability, or mental status in individuals at risk for MCI. Speech-language pathologists are uniquely qualified to identify subtle changes in language, and standardized language tests with normative data should be used when testing for MCI.

The instruments used by the Italian centres for cognitive disorders and dementia to diagnose mild cognitive impairment (MCI)

AIMS

The purpose of this study was to examine the tools used in Italy to diagnose mild cognitive impairment (MCI).

METHODS

In collaboration with the Luigi Amaducci Research Consortium, the Italian Network of Alzheimer Evaluation Units prepared a questionnaire to describe how MCI is diagnosed in the Italian Centres for cognitive disorders and dementia (CCDD).

RESULTS

Most of the ninety-two CCDDs participating in the survey were located in hospitals (54.7%); large percentages were coordinated by neurologists (50.8%) and geriatricians (44.6%). Almost all (98.5%) used the Mini Mental State Examination to diagnose MCI; the Clock Drawing Test was also frequently used (83.9%). Other neuropsychological, imaging and biomarker tests were utilized less frequently and a wide diversity in the instruments used was noted.

CONCLUSIONS

According to the results, diagnoses of MCI are based on a multitude of instruments, with major differences in the clinical assessment of geriatricians and neurologists. Standardized testing protocols, validated instruments and cut-off points need to be identified and adopted by the CCDDs for assessing MCI.