Search

BackgroundThe combined analysis of imaging and functional modalities is supposed to improve diagnostics of neurodegenerative diseases with advanced data science techniques.ObjectiveTo get an insight into normal and accelerated brain aging by developing the machine learning models that predict individual performance in neuropsychological and cognitive tests from brain MRI. With these models we endeavor to look for patterns of brain structure-function association (SFA) indicative of mild cognitive impairment (MCI) and Alzheimer's dementia.Materials and methodsWe explored the age-related variability of cognitive and neuropsychological test scores in normal and accelerated aging and constructed regression models predicting functional performance in cognitive tests from brain radiomics data. The models were trained on the three study cohorts from ADNI dataset—cognitively normal individuals, patients with MCI or dementia—separately. We also looked for significant correlations between cortical parcellation volumes and test scores in the cohorts to investigate neuroanatomical differences in relation to cognitive status. Finally, we worked out an approach for the classification of the examinees according to the pattern of structure-function associations into the cohorts of the cognitively normal elderly and patients with MCI or dementia.ResultsIn the healthy population, the global cognitive functioning slightly changes with age. It also remains stable across the disease course in the majority of cases. In healthy adults and patients with MCI or dementia, the trendlines of performance in digit symbol substitution test and trail making test converge at the approximated point of 100 years of age. According to the SFA pattern, we distinguish three cohorts: the cognitively normal elderly, patients with MCI, and dementia. The highest accuracy is achieved with the model trained to predict the mini-mental state examination score from voxel-based morphometry data. The application of the majority voting technique to models predicting results in cognitive tests improved the classification performance up to 91.95% true positive rate for healthy participants, 86.21%—for MCI and 80.18%—for dementia cases.ConclusionThe machine learning model, when trained on the cases of this of that group, describes a disease-specific SFA pattern. The pattern serves as a “stamp” of the disease reflected by the model.

BackgroundThe human brain structure undergoes considerable changes throughout life. Cognitive function can be affected either negatively or positively. It is challenging to segregate normal brain aging from the accelerated one.ObjectiveTo work out a descriptive model of brain structural and functional changes in normal aging.Materials and MethodsBy using voxel-based morphometry and lesion segmentation along with linear statistics and machine learning (ML), we analyzed the structural changes in the major brain compartments and modeled the dynamics of neurofunctional performance throughout life. We studied sex differences in lifelong dynamics of brain volumetric data with Mann-Whitney U-test. We tested the hypothesis that performance in some cognitive domains might decline as a linear function of age while other domains might have a non-linear dependence on it. We compared the volumetric changes in the major brain compartments with the dynamics of psychophysiological performance in 4 age groups. Then, we tested linear models of structural and functional decline for significant differences between the slopes in age groups with the T-test.ResultsWhite matter hyperintensities (WMH) are not the major structural determinant of the brain normal aging. They should be viewed as signs of a disease. There is a sex difference in the speed and/or in the onset of the gray matter atrophy. It either starts earlier or goes faster in males. Marked sex difference in the proportion of total cerebrospinal fluid (CSF) and intraventricular CSF (iCSF) justifies that elderly men are more prone to age-related brain atrophy than women of the same age.ConclusionThe article gives an overview and description of the conceptual structural changes in the brain compartments. The obtained data justify distinct patterns of age-related changes in the cognitive functions. Cross-life slowing of decision-making may follow the linear tendency of enlargement of the interhemispheric fissure because the center of task switching and inhibitory control is allocated within the medial wall of the frontal cortex, and its atrophy accounts for the expansion of the fissure. Free online tool at https://med-predict.com illustrates the tests and study results.

Background: Neuroscience lacks a reliable method of screening the early stages of dementia.Objective: To improve the diagnostics of age-related cognitive functions by developing insight into the proportionality of age-related changes in cognitive subdomains.Materials and Methods: We composed a battery of psychophysiological tests and collected an open-access psychophysiological outcomes of brain atrophy (POBA) dataset by testing individuals without dementia. To extend the utility of machine learning (ML) classification in cognitive studies, we proposed estimates of the disproportional changes in cognitive functions: an index of simple reaction time to decision-making time (ISD), ISD with the accuracy performance (ISDA), and an index of performance in simple and complex visual-motor reaction with account for accuracy (ISCA). Studying the distribution of the values of the indices over age allowed us to verify whether diverse cognitive functions decline equally throughout life or there is a divergence in age-related cognitive changes.Results: Unsupervised ML clustering shows that the optimal number of homogeneous age groups is four. The sample is segregated into the following age-groups: Adolescents ∈ [0, 20), Young adults ∈ [20, 40), Midlife adults ∈ [40, 60) and Older adults ≥60 year of age. For ISD, ISDA, and ISCA values, only the median of the Adolescents group is different from that of the other three age-groups sharing a similar distribution pattern (p > 0.01). After neurodevelopment and maturation, the indices preserve almost constant values with a slight trend toward functional decline. The reaction to a moving object (RMO) test results (RMO_mean) follow another tendency. The Midlife adults group's median significantly differs from the remaining three age subsamples (p < 0.01). No general trend in age-related changes of this dependent variable is observed. For all the data (ISD, ISDA, ISCA, and RMO_mean), Levene's test reveals no significant changes of the variances in age-groups (p > 0.05). Homoscedasticity also supports our assumption about a linear dependency between the observed features and age.Conclusion: In healthy brain aging, there are proportional age-related changes in the time estimates of information processing speed and inhibitory control in task switching. Future studies should test patients with dementia to determine whether the changes of the aforementioned indicators follow different patterns.

Background: Neuronal reactions and cognitive processes slow down during aging. The onset, rate, and extent of changes vary considerably from individual to individual. Assessing the changes throughout the lifespan is a challenging task. No existing test covers all domains, and batteries of tests are administered. The best strategy is to study each functional domain separately by applying different behavioral tasks whereby the tests reflect the conceptual structure of cognition. Such an approach has limitations that are described in the article.Objective: Our aim was to improve the diagnosis of early cognitive decline. We estimated the onset of cognitive decline in a healthy population, using behavioral tests, and predicted the age group of an individual. The comparison between the predicted (“cognitive”) and chronological age will contribute to the early diagnosis of accelerated aging.Materials and Methods: We used publicly available datasets (POBA, SSCT) and Pearson correlation coefficients to assess the relationship between age and tests results, Kruskal-Wallis test to compare distribution, clustering methods to find an onset of cognitive decline, feature selection to enhance performance of the clustering algorithms, and classification methods to predict an age group from cognitive tests results.Results: The major results of the psychophysiological tests followed a U-shape function across the lifespan, which reflected the known inverted function of white matter volume changes. Optimal values were observed in those aged over 35 years, with a period of stability and accelerated decline after 55–60 years of age. The shape of the age-related variance of the performance of major cognitive tests was linear, which followed the trend of lifespan gray matter volume changes starting from adolescence. There was no significant sex difference in lifelong dynamics of major tests estimates. The performance of the classification model for identifying subject age groups was high.Conclusions: ML models can be designed and utilized as computer-aided detectors of neurocognitive decline. Our study demonstrated great promise for the utility of classification models to predict age-related changes. These findings encourage further explorations combining several tests from the cognitive and psychophysiological test battery to derive the most reliable set of tests toward the development of a highly-accurate ML model.

Background: The current study examines the relationship between speed and accuracy of performance in a reaction time setting and explores the informative value of the inverse efficiency score (IES) regarding the possibility to reflect age-related cognitive changes.Objectives: To study the characteristics of speed and accuracy while performing psychophysiological tests throughout the lifespan; to examine the speed-accuracy ratio in age groups and to apply IES to discriminative visual-motor reaction task; and to figure out the predictive potential of psychophysiological tests to identify IES values.Methods: We utilize nonparametric statistical tests, regression analysis, and supervised machine learning methods.Results and Conclusion: The examinees under 20 and over 60 years of age share one tendency regarding the speed-accuracy ratio without speed-accuracy trade-off. Both at the time of active developmental changes in adolescence and during ongoing atrophic changes in elderly there is a tendency toward a rise of the number of mistakes while slowing the reaction. In the age range from 20 to 60 the relationship between the speed and accuracy is opposite and speed-accuracy trade-off is present. In our battery, complex visual-motor reaction is the only test with the significant negative association between reaction time and error rate in the subcohort of young and midlife adults taken together. On average, women perform more slowly and accurately than men in the speed-accuracy task, however most of the gender-related differences are insignificant. Using results of other psychophysiological tests, we predicted IES values for the visual-motor reaction with high accuracy (R2 = 0.77 ± 0.08; mean absolute error / IES range = 3.37%). The regression model shows the best performance in the cognitively preserved population groups of young and middle-aged adults (20–60 years). Because of the individual rate of neurodevelopment in youth and cognitive decline in the elderly, the regression model for these subcohorts has a low predictive performance. IES accounts for different cognitive subdomains and may reflect their disproportional changes throughout the lifespan. This encourages us to proceed to explore the combination of executive functioning and psychophysiological test results utilizing machine learning models. The latter can be designed as a reliable computer-aided detector of cognitive changes at early stages.