Prediction of Decline in Global Cognitive Function Using Machine Learning with Feature Ranking of Gait and Physical Fitness Outcomes in Older Adults.
Ontology highlight
ABSTRACT:
SUBMITTER: Noh B
PROVIDER: S-EPMC8582857 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:This study aimed to identify classifier variables by considering both gait and physical fitness for identifying adults aged over 75 years and global cognitive function declines in older adults. The participants included 735 adults aged 65-89 years who were asked to walk at three different speeds (slower, preferred, and faster) while wearing inertial measurement units embedded in shoe-type data loggers and to perform nine physical fitness tests. The variability in the stance phase as well as the strength, balance, and functional endurance showed a strong dependence on the age being over 75 years. The cognitive function was evaluated by the Mini-Mental State Examination; a longer stance phase at a slower walking speed and decreased grip strength and five times sit-to-stand were associated with cognitive function. These findings may be useful for determining the decline in physical performance of older adults. A longer stance phase and decreased grip strength and five times sit-to-stand may be factors that help distinguish declines in cognitive function from normal age-related declines.
| S-EPMC7369886 | biostudies-literature
Project description:ObjectiveTo determine the extent to which the regional brain volumes associated with slow gait speed can inform subsequent cognitive decline in older adults from the Rush Memory and Aging Project.ApproachWe utilized deformation-based morphometry (DBM) in a whole-brain exploratory approach to identify the regional brain volumes associated with gait speed assessed over a short distance during an in-home assessment. We created deformation scores to summarize the gait-associated regions and entered the scores into a series of longitudinal mixed effects models to determine the extent to which deformation predicted change in cognition over time, controlling for associations between gait and cognition.ResultsIn 438 older adults (81 ± 7; 76% female), DBM revealed that slower gait speed was associated with smaller volumes across frontal white matter, temporal grey matter, and subcortical areas and larger volumes in the ventricles during the same testing cycle. When a subset was followed over multiple (5 ± 2) years, slower gait speed was also associated with annual declines in global cognition, executive functioning, and memory abilities. Several of the gait-related brain structures were associated with these declines in cognition; however, larger ventricles and smaller medial temporal lobe volumes proved most robust and attenuated the association between slow gait and cognitive decline.ConclusionRegional brain volumes in the ventricles and temporal lobe associated with both slow gait speed and faster cognitive decline have potential to improve risk stratification for cognitive decline in older adults.
| S-EPMC10582745 | biostudies-literature
Project description:Autism spectrum disorder is the most used umbrella term for a myriad of neuro-degenerative/developmental conditions typified by inappropriate social behavior, lack of communication/comprehension skills, and restricted mental and emotional maturity. The intriguing factor of this disorder is attributed to the fact that it can be detected only by close monitoring of developmental milestones after childbirth. Moreover, the exact causes for the occurrence of this neurodevelopmental condition are still unknown. Besides, autism is prevalent across individuals irrespective of ethnicity, genetic/familial history, and economic/educational background. Although research suggests that autism is genetic in nature and early detection of this disorder can greatly enhance the independent lifestyle and societal adaptability of affected individuals, there is still a great dearth of information to support the statement of proven facts and figures. This research work places emphasis on the application of automated machine learning incorporated with feature ranking techniques to generate significant feature signatures for the early detection of autism. Publicly available datasets based on the Q-chat scores of individuals across diverse age groups-toddlers, children, adolescents, and adults have been employed in this study. A machine learning framework based on automated hyperparameter optimization is proposed in this work to rank the potential nonclinical markers for autism. Moreover, this study aimed at ranking the AutoML models based on Mathew's correlation coefficient and balanced accuracy via which nonclinical markers were identified from these datasets. Besides, the feature signatures and their significance in distinguishing between classes are being reported for the first time in autism detection. The proposed framework yielded ∼90% MCC and ∼95% balanced accuracy across all four age groups of autism datasets. Deep learning approaches have yielded a maximum of 92.7% accuracy on the same datasets but are limited in their ability to extract significant markers, have not reported on MCC for unbalanced data, and cannot adapt automatically to new data entries. However, AutoML approaches are more flexible, easier to implement, and provide automated optimization, thereby yielding the highest accuracy with minimal user intervention.
| S-EPMC9833925 | biostudies-literature
Project description:BackgroundSeveral studies have reported the association between gait and global cognitive function; however, there is no study explaining the age-specific gait characteristics of older women and association between those characteristics and global cognitive function by age-specific differences and gait speed modification. The aim of this study was to examine age-specific differences in gait characteristics and global cognitive function in older women as well as identify gait domains strongly associated with global cognitive function in older women based on gait speed modification.MethodsOne hundred sixty-four female participants aged 65-85 years were examined. Participants were assessed for global cognitive function through the mini-mental state examination. They also performed three trials of the overground walking test along a straight 20 m walkway. Inertial measurement unit sensors with shoe-type data loggers on both the left and right outsoles were used to measure gait characteristics.ResultsThe pace at all speeds and the variability and phase at faster speeds were altered in women aged >75 years (all pace domain parameters, p < 0.05); variability and phase highly depended on age (all p < 0.05). Variability at slower speeds (β = -0.568 and p = 0.006) and the phase at the preferred (β = -0.471 and p = 0.005) and faster speeds (β = -0.494 and p = 0.005) were associated with global cognitive function in women aged >75 years.DiscussionThe variability and phase domains at faster speeds were considered to identify gait changes that accompany aging. In addition, the decreases in global cognitive function are associated with increased variability and phase domains caused by changes in gait speed in older women.ConclusionOur results are considered useful for understanding age-related gait characteristics with global cognitive function in old women.
| S-EPMC7081786 | biostudies-literature
Project description:Preserving attention abilities is of great concern to older adults who are motivated to maintain their quality of life. Both cognitive and physical fitness interventions have been utilized in intervention studies to assess maintenance and enhancement of attention abilities in seniors, and a coupling of these approaches is a compelling strategy to buttress both cognitive and physical health in a time- and resource-effective manner. With this perspective, we created a closed-loop, motion-capture video game (Body-Brain Trainer: BBT) that adapts a player's cognitive and physical demands in an integrated approach, thus creating a personalized and cohesive experience across both domains. Older adults who engaged in two months of BBT improved on both physical fitness (measures of blood pressure and balance) and attention (behavioral and neural metrics of attention on a continuous performance task) outcome measures beyond that of an expectancy matched, active, placebo control group, with maintenance of improved attention performance evidenced 1 year later. Following training, the BBT group's improvement on the attention outcome measure exceeded performance levels attained by an untrained group of 20-year olds, and showed age-equilibration of a neural signature of attention shown to decline with age: midline frontal theta power. These findings highlight the potential benefits of an integrated, cognitive-physical, closed-loop training platform as a powerful tool for both cognitive and physical enhancement in older adults.
| S-EPMC9427998 | biostudies-literature
Project description:BackgroundThe longitudinal rates of cognitive decline among aging populations are heterogeneous. Few studies have investigated the possibility of implementing prognostic models to predict cognitive changes with the combination of categorical and continuous data from multiple domains.ObjectiveImplement a multivariate robust model to predict longitudinal cognitive changes over 12 years among older adults and to identify the most significant predictors of cognitive changes using machine learning techniques.MethodIn total, data of 2733 participants aged 50-85 years from the English Longitudinal Study of Ageing are included. Two categories of cognitive changes were determined including minor cognitive decliners (2361 participants, 86.4%) and major cognitive decliners (372 participants, 13.6%) over 12 years from wave 2 (2004-2005) to wave 8 (2016-2017). Machine learning methods were used to implement the predictive models and to identify the predictors of cognitive decline using 43 baseline features from seven domains including sociodemographic, social engagement, health, physical functioning, psychological, health-related behaviors, and baseline cognitive tests.ResultsThe model predicted future major cognitive decliners from those with the minor cognitive decline with a relatively high performance. The overall AUC, sensitivity, and specificity of prediction were 72.84%, 78.23%, and 67.41%, respectively. Furthermore, the top 7 ranked features with an important role in predicting major vs minor cognitive decliners included age, employment status, socioeconomic status, self-rated memory changes, immediate word recall, the feeling of loneliness, and vigorous physical activity. In contrast, the five least important baseline features consisted of smoking, instrumental activities of daily living, eye disease, life satisfaction, and cardiovascular disease.ConclusionThe present study indicated the possibility of identifying individuals at high risk of future major cognitive decline as well as potential risk/protective factors of cognitive decline among older adults. The findings could assist in improving the effective interventions to delay cognitive decline among aging populations.
| S-EPMC9983884 | biostudies-literature
Project description:Ageing is associated with declines in cognitive functions and physical fitness (PF). Physical exercise training and physical activity (PA) have been shown to have positive effects on cognitive functions and brain plasticity. This study aims to establish a practical equation for evaluating cognitive functions using PF parameters in healthy older adults. One-hundred and two older subjects were physically and clinically evaluated. Participants performed the Short Physical Performance Battery (SPPB) and handgrip test (HG); general cognitive functions were examined using the Mini Mental State Examination (MMSE). For all of them, a multiple regression analysis was used to predict MMSE from age, SPPB and HG variables. The new equation was cross validated to determine its prediction accuracy. Considering that SPPB and MMSE reference score are not different between genders, only one equation was developed for females and males. Age, SPPB and HG correlated significantly (p<0.01) with the MMSE score. The developed equation was MMSE = 19.479 + (1.548 x SPPB)-(0.130 x age) (R2 = 0.72 and root mean square errors of 3.6). The results of PF are useful for exercise specialists to achieve the best physical exercise training and PA in older adults. In conclusion, this study showed for the first time that our new equation can be used to predict subjects' cognitive functions based on SPPB results and subject age. We suggest its use when patients' cognitive functions or more appropriate clinical tests cannot be pursued.
| S-EPMC7205244 | biostudies-literature
Project description:BackgroundOlder adults with mild cognitive impairment (MCI) have slower gait speed and poor gait performance under dual-task conditions. However, gait kinematic and kinetic characteristics in older adults with MCI or subjective cognitive decline (SCD) remain unknown. This study was designed to explore the difference in gait kinematics and kinetics during level walking among older people with MCI, SCD, and normal cognition (NC).MethodsThis cross-sectional study recruited 181 participants from July to December 2019; only 82 met the inclusion criteria and consented to participate and only 79 completed gait analysis. Kinematic and kinetic data were obtained using three-dimensional motion capture system during level walking, and joint movements of the lower limbs in the sagittal plane were analyzed by Visual 3D software. Differences in gait kinematics and kinetics among the groups were analyzed using multivariate analysis of covariance (MANCOVA) with Bonferroni post-hoc analysis. After adjusting for multiple comparisons, the significance level was p < 0.002 for MANCOVA and p < 0.0008 for post-hoc analysis.ResultsTwenty-two participants were MCI [mean ± standard deviation (SD) age, 71.23 ± 6.65 years], 33 were SCD (age, 72.73 ± 5.25 years), and 24 were NC (age, 71.96 ± 5.30 years). MANCOVA adjusted for age, gender, body mass index (BMI), gait speed, years of education, diabetes mellitus, and Geriatric Depression Scale (GDS) revealed a significant multivariate effect of group in knee peak extension angle (F = 8.77, p < 0.0001) and knee heel strike angle (F = 8.07, p = 0.001) on the right side. Post-hoc comparisons with Bonferroni correction showed a significant increase of 5.91° in knee peak extension angle (p < 0.0001) and a noticeable decrease of 6.21°in knee heel strike angle (p = 0.001) in MCI compared with NC on the right side. However, no significant intergroup difference was found in gait kinetics, including dorsiflexion, plantar flexion, knee flexion, knee extension, hip flexion, and hip extension(p > 0.002).ConclusionAn increase of right knee peak extension angle and a decrease of right knee heel strike angle during level walking were found among older adults with MCI compared to those with NC.
| S-EPMC8368728 | biostudies-literature
Project description:ImportancePhysical activity is associated with the risk for cognitive decline, but much of the evidence in this domain comes from studies with short follow-ups, which is prone to reverse causation bias.ObjectiveTo examine how length of follow-up, baseline age, physical activity amount, and study quality modify the longitudinal associations of physical activity with cognition.Data sourcesObservational studies of adults with a prospective follow-up of at least 1 year, a valid baseline cognitive measure or midlife cohort, and an estimate of the association of baseline physical activity and follow-up cognition were sought from PsycInfo, Scopus, CINAHL, Web of Science, SPORTDiscus, and PubMed, with the final search conducted on November 2, 2022.Study selectionTwo independent researchers screened titles with abstracts and full-text reports.Data extraction and synthesisTwo reviewers independently assessed study quality and extracted data. Pooled estimates of association were calculated with random-effects meta-analyses. An extensive set of moderators, funnel plots, and scatter plots of physical activity amount were examined. This study is reported following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guideline.Main outcomes and measuresPooled estimates of the associations between physical activity and global cognition, as well as specific cognitive domains, were examined.ResultsA total of 104 studies with 341 471 participants were assessed. Analysis of binary outcomes included 45 studies with 102 452 individuals, analysis of follow-up global cognition included 14 studies with 41 045 individuals, and analysis of change in global cognition included 25 studies with 67 463 individuals. Physical activity was associated with a decreased incidence of cognitive impairment or decline after correction for funnel plot asymmetry (pooled risk ratio, 0.97; 95% CI, 0.97-0.99), but there was no significant association in follow-ups longer than 10 years. Physical activity was associated with follow-up global cognition (standardized regression coefficient, 0.03; 95% CI, 0.02-0.03) and change in global cognition (standardized regression coefficient, 0.01; 95% CI, 0.01 to 0.02) from trim-and-fill analyses, with no clear dose-response or moderation by follow-up length, baseline age, study quality or adjustment for baseline cognition. The specific cognitive domains associated with physical activity were episodic memory (standardized regression coefficient, 0.03; 95% CI, 0.02-0.04) and verbal fluency (standardized regression coefficient, 0.05; 95% CI, 0.03-0.08).Conclusions and relevanceIn this meta-analysis of the association of physical activity with cognitive decline, physical activity was associated with better late-life cognition, but the association was weak. However, even a weak association is important from a population health perspective.
| S-EPMC10835510 | biostudies-literature
Project description:IntroductionThere is a large interindividual variability in cognitive functioning with increasing age due to biological and lifestyle factors. One of the most important lifestyle factors is the level of physical fitness (PF). The link between PF and brain activity is widely accepted but the specificity of cognitive functions affected by physical fitness across the adult lifespan is less understood. The present study aims to clarify whether PF is basically related to cognition and general intelligence in healthy adults, and whether higher levels of PF are associated with better performance in the same or different cognitive functions at different ages.MethodsA sample of 490 participants (20-70 years) was analyzed to examine this relationship. Later, the sample was split half into the young to middle-aged group (YM; 20-45 years; n = 254), and the middleaged to older group (MO; 46-70 years; n = 236). PF was measured by a quotient of maximum power in a bicycle ergometry test PWC-130 divided by body weight (W/kg), which was supported by a self-reported level of PF. Cognitive performance was evaluated by standardized neuropsychological test batteries.ResultsRegression models showed a relationship between PF and general intelligence (g-factor) and its subcomponents extracted using structural equation modeling (SEM) in the entire sample. This association was moderated by age, which also moderated some specific cognitive domains such as attention, logical reasoning, and interference processing. After splitting the sample into two age groups, a significant relationship was found between cognitive status, as assessed by the Mini Mental State Examination (MMSE), and PF in both age groups. However, apart from cognitive failures in daily life (CFQ), no other association between PF and specific cognitive functions was found in the YM group. In contrast, several positive associations were observed in the MO group, such as with selective attention, verbal memory, working memory, logical reasoning, and interference processing.DiscussionThese findings show that middle-aged to older adults benefit more from PF than younger to middle-aged adults. The results are discussed in terms of the neurobiological mechanisms underlying the cognitive effects of PF across the lifespan.Clinical trial registrationhttps://clinicaltrials.gov/ct2/show/NCT05155397, identifier NCT05155397.
| S-EPMC10312084 | biostudies-literature