Objective estimation of m-CTSIB balance test scores using wearable sensors and machine learning.

Accurate balance assessment is important in healthcare for identifying and managing conditions affecting stability and coordination. It plays a key role in preventing falls, understanding movement disorders, and designing appropriate therapeutic interventions across various age groups and medical conditions. However, traditional balance assessment methods often suffer from subjectivity, lack of comprehensive balance assessments and remote assessment capabilities, and reliance on specialized equipment and expert analysis. In response to these challenges, our study introduces an innovative approach for estimating scores on the Modified Clinical Test of Sensory Interaction on Balance (m-CTSIB). Utilizing wearable sensors and advanced machine learning algorithms, we offer an objective, accessible, and efficient method for balance assessment. We collected comprehensive movement data from 34 participants under four different sensory conditions using an array of inertial measurement unit (IMU) sensors coupled with a specialized system to evaluate ground truth m-CTSIB balance scores for our analysis. This data was then preprocessed, and an extensive array of features was extracted for analysis. To estimate the m-CTSIB scores, we applied Multiple Linear Regression (MLR), Support Vector Regression (SVR), and XGBOOST algorithms. Our subject-wise Leave-One-Out and 5-Fold cross-validation analysis demonstrated high accuracy and a strong correlation with ground truth balance scores, validating the effectiveness and reliability of our approach. Key insights were gained regarding the significance of specific movements, feature selection, and sensor placement in balance estimation. Notably, the XGBOOST model, utilizing the lumbar sensor data, achieved outstanding results in both methods, with Leave-One-Out cross-validation showing a correlation of 0.96 and a Mean Absolute Error (MAE) of 0.23 and 5-fold cross-validation showing comparable results with a correlation of 0.92 and an MAE of 0.23, confirming the model's consistent performance. This finding underlines the potential of our method to revolutionize balance assessment practices, particularly in settings where traditional methods are impractical or inaccessible.

The Healthy Brain Initiative (HBI): A prospective cohort study protocol.

BACKGROUND: The Health Brain Initiative (HBI), established by University of Miami's Comprehensive Center for Brain Health (CCBH), follows racially/ethnically diverse older adults without dementia living in South Florida. With dementia prevention and brain health promotion as an overarching goal, HBI will advance scientific knowledge by developing novel assessments and non-invasive biomarkers of Alzheimer's disease and related dementias (ADRD), examining additive effects of sociodemographic, lifestyle, neurological and biobehavioral measures, and employing innovative, methodologically advanced modeling methods to characterize ADRD risk and resilience factors and transition of brain aging. METHODS: HBI is a longitudinal, observational cohort study that will follow 500 deeply-phenotyped participants annually to collect, analyze, and store clinical, cognitive, behavioral, functional, genetic, and neuroimaging data and biospecimens. Participants are ≥50 years old; have no, subjective, or mild cognitive impairment; have a study partner; and are eligible to undergo magnetic resonance imaging (MRI). Recruitment is community-based including advertisements, word-of-mouth, community events, and physician referrals. At baseline, following informed consent, participants complete detailed web-based surveys (e.g., demographics, health history, risk and resilience factors), followed by two half-day visits which include neurological exams, cognitive and functional assessments, an overnight sleep study, and biospecimen collection. Structural and functional MRI is completed by all participants and a subset also consent to amyloid PET imaging. Annual follow-up visits repeat the same data and biospecimen collection as baseline, except that MRIs are conducted every other year after baseline. ETHICS AND EXPECTED IMPACT: HBI has been approved by the University of Miami Miller School of Medicine Institutional Review Board. Participants provide informed consent at baseline and are re-consented as needed with protocol changes. Data collected by HBI will lead to breakthroughs in developing new diagnostics and therapeutics, creating comprehensive diagnostic evaluations, and providing the evidence base for precision medicine approaches to dementia prevention with individualized treatment plans.

The Healthy Brain Initiative (HBI): A prospective cohort study protocol.

Background: The Health Brain Initiative (HBI), established by University of Miami's Comprehensive Center for Brain Health (CCBH), follows racially/ethnically diverse older adults without dementia living in South Florida. With dementia prevention and brain health promotion as an overarching goal, HBI will advance scientific knowledge by developing novel assessments and non-invasive biomarkers of Alzheimer's disease and related dementias (ADRD), examining additive effects of sociodemographic, lifestyle, neurological and biobehavioral measures, and employing innovative, methodologically advanced modeling methods to characterize ADRD risk and resilience factors and transition of brain aging. Methods: HBI is a longitudinal, observational cohort study that will follow 500 deeply-phenotyped participants annually to collect, analyze, and store clinical, cognitive, behavioral, functional, genetic, and neuroimaging data and biospecimens. Participants are ≥50 years old; have no, subjective, or mild cognitive impairment; have a study partner; and are eligible to undergo magnetic resonance imaging (MRI). Recruitment is community-based including advertisements, word-of-mouth, community events, and physician referrals. At baseline, following informed consent, participants complete detailed web-based surveys (e.g., demographics, health history, risk and resilience factors), followed by two half-day visits which include neurological exams, cognitive and functional assessments, an overnight sleep study, and biospecimen collection. Structural and functional MRI is completed by all participants and a subset also consent to amyloid PET imaging. Annual follow-up visits repeat the same data and biospecimen collection as baseline, except that MRIs are conducted every other year after baseline. Ethics and expected impact: HBI has been approved by the University of Miami Miller School of Medicine Institutional Review Board. Participants provide informed consent at baseline and are re-consented as needed with protocol changes. Data collected by HBI will lead to breakthroughs in developing new diagnostics and therapeutics, create comprehensive diagnostic evaluations, and provide the evidence base for precision medicine approaches to dementia prevention with individualized treatment plans.

The Resilience Index: A Quantifiable Measure of Brain Health and Risk of Cognitive Impairment and Dementia.

BACKGROUND: There is increasing interest in lifestyle modification and integrative medicine approaches to treat and/or prevent mild cognitive impairment (MCI) and Alzheimer's disease and related dementias (ADRD). OBJECTIVE: To address the need for a quantifiable measure of brain health, we created the Resilience Index (RI). METHODS: This cross-sectional study analyzed 241 participants undergoing a comprehensive evaluation including the Clinical Dementia Rating and neuropsychological testing. Six lifestyle factors including physical activity, cognitive activity, social engagements, dietary patterns, mindfulness, and cognitive reserve were combined to derive the RI (possible range of scores: 1-378). Psychometric properties were determined. RESULTS: The participants (39 controls, 75 MCI, 127 ADRD) had a mean age of 74.6±9.5 years and a mean education of 15.8±2.6 years. The mean RI score was 138.2±35.6. The RI provided estimates of resilience across participant characteristics, cognitive staging, and ADRD etiologies. The RI showed moderate-to-strong correlations with clinical and cognitive measures and very good discrimination (AUC: 0.836; 95% CI: 0.774-0.897) between individuals with and without cognitive impairment (diagnostic odds ratio = 8.9). Individuals with high RI scores (> 143) had better cognitive, functional, and behavioral ratings than individuals with low RI scores. Within group analyses supported that controls, MCI, and mild ADRD cases with high RI had better cognitive, functional, and global outcomes than those with low RI. CONCLUSION: The RI is a brief, easy to administer, score and interpret assessment of brain health that incorporates six modifiable protective factors. Results from the RI could provide clinicians and researchers with a guide to develop personalized prevention plans to support brain health.

Characterization of dementia with Lewy bodies (DLB) and mild cognitive impairment using the Lewy body dementia module (LBD-MOD).

INTRODUCTION: The National Institute on Aging Alzheimer's Disease Research Center program added the Lewy body dementia module (LBD-MOD) to the Uniform Data Set to facilitate LBD characterization and distinguish dementia with Lewy bodies (DLB) from Alzheimer's disease (AD). We tested the performance of the LBD-MOD. METHODS: The LBD-MOD was completed in a single-site study in 342 participants: 53 controls, 78 AD, and 110 DLB; 79 mild cognitive impairment due to AD (MCI-AD); and 22 MCI-DLB. RESULTS: DLB differed from AD in extrapyramidal symptoms, hallucinations, apathy, autonomic features, REM sleep behaviors, daytime sleepiness, cognitive fluctuations, timed attention tasks, and visual perception. MCI-DLB differed from MCI-AD in extrapyramidal features, mood, autonomic features, fluctuations, timed attention tasks, and visual perception. Descriptive data on LBD-MOD measures are provided for reference. DISCUSSION: The LBD-MOD provided excellent characterization of core and supportive features to differentiate DLB from AD and healthy controls while also characterizing features of MCI-DLB.

Detection of Mild Cognitive Impairment and Alzheimer's Disease using Dual-task Gait Assessments and Machine Learning.

OBJECTIVE: Early detection of mild cognitive impairment (MCI) and Alzheimer's disease (AD) can increase access to treatment and assist in advance care planning. However, the development of a diagnostic system that d7oes not heavily depend on cognitive testing is a major challenge. We describe a diagnostic algorithm based solely on gait and machine learning to detect MCI and AD from healthy. METHODS: We collected "single-tasking" gait (walking) and "dual-tasking" gait (walking with cognitive tasks) from 32 healthy, 26 MCI, and 20 AD participants using a computerized walkway. Each participant was assessed with the Montreal Cognitive Assessment (MoCA). A set of gait features (e.g., mean, variance and asymmetry) were extracted. Significant features for three classifications of MCI/healthy, AD/healthy, and AD/MCI were identified. A support vector machine model in a one-vs.-one manner was trained for each classification, and the majority vote of the three models was assigned as healthy, MCI, or AD. RESULTS: The average classification accuracy of 5-fold cross-validation using only the gait features was 78% (77% F1-score), which was plausible when compared with the MoCA score with 83% accuracy (84% F1-score). The performance of healthy vs. MCI or AD was 86% (88% F1-score), which was comparable to 88% accuracy (90% F1-score) with MoCA. CONCLUSION: Our results indicate the potential of machine learning and gait assessments as objective cognitive screening and diagnostic tools. SIGNIFICANCE: Gait-based cognitive screening can be easily adapted into clinical settings and may lead to early identification of cognitive impairment, so that early intervention strategies can be initiated.

Dual-Task Gait Assessment and Machine Learning for Early-detection of Cognitive Decline.

Alzheimer's disease (AD) affects approximately 30 million people worldwide, and this number is predicted to triple by 2050 unless further discoveries facilitate the early detection and prevention of the disease. Computerized walkways for simultaneous assessment of motor-cognitive performance, known as a dual-task assessment, has been used to associate changes in gait characteristics to mild cognitive impairment (MCI) with early-stage disease. However, to our best knowledge, there is no validated method to detect MCI using the collective analysis of these gait characteristics. In this paper, we develop a machine learning approach to analyze the gait data from the dual-task assessment in order to detect subjects with cognitive impairment from healthy individuals. We collected dual-task gait data from a computerized walkway of a total of 92 subjects with 31 healthy control (HC) and 61 MCI. Using support vector machine (SVM) and gradient tree boosting, we developed a classifier to differentiate MCI from HC subjects and compared the results with a paper-based questionnaire assessment that has been commonly used in clinical practice. SVM provided the highest accuracy of 77.17% with 81.97% sensitivity and 67.74% specificity. Our results indicate the potential of machine learning + dual-task assessment to enable early diagnosis of cognitive decline before it advances to dementia and AD, so that early intervention or prevention strategies can be initiated.

The Quick Physical Activity Rating (QPAR) scale: A brief assessment of physical activity in older adults with and without cognitive impairment.

INTRODUCTION: Alzheimer's disease and related dementias (ADRD) currently affect over 5.7 million Americans and over 35 million people worldwide. At the same time, over 31 million older adults are physically inactive with impaired physical performance interfering with activities of daily living. Low physical activity is a risk factor for ADRD. We examined the utility of a new measure, the Quick Physical Activities Rating (QPAR) as an informant-rated instrument to quantify the dosage of physical activities in healthy controls, MCI and ADRD compared with Gold Standard assessments of objective measures of physical performance, fitness, and functionality. METHODS: This study analyzed 390 consecutive patient-caregiver dyads who underwent a comprehensive evaluation including the Clinical Dementia Rating (CDR), mood, neuropsychological testing, caregiver ratings of patient behavior and function, and a comprehensive physical performance and gait assessment. The QPAR was completed prior to the office visit and was not considered in the clinical evaluation, physical performance assessment, staging or diagnosis of the patient. Psychometric properties including item variability and distribution, floor and ceiling effects, strength of association, known-groups performance, and internal consistency were determined. RESULTS: The patients had a mean age of 75.3±9.2 years, 15.7±2.8 years of education and were 46.9% female. The patients had a mean CDR-SB of 4.8±4.7 and a mean MoCA score of 18.6±7.1 and covered a range of healthy controls (CDR 0 = 54), MCI or very mild dementia (CDR 0.5 = 161), mild dementia (CDR 1 = 92), moderate dementia (CDR 2 = 64), and severe dementia (CDR 3 = 29). The mean QPAR score was 20.2±18.9 (range 0-132) covering a wide range of physical activity. The QPAR internal consistency (Cronbach alpha) was very good at 0.747. The QPAR was correlated with measures of physical performance (dexterity, grip strength, gait, mobility), physical functionality rating scales, measures of activities of daily living and comorbidities, the UPDRS, and frailty ratings (all p < .001). The QPAR report of physical activities was able to discriminate between individuals with impaired physical functionality (32.2±23.9 vs 15.2±13.8, p < .001), falls risk (28.4±21.6 vs. 14.5±13.2, p < .001), and the presence of frailty (28.1±22.7 vs. 11.8±9.4, p < .001). The QPAR showed strong psychometric properties and excellent data quality, and worked equally well across different patient ages, sexes, informant relationships, and in individuals with and without cognitive impairment. DISCUSSION: The QPAR is a brief detection tool that captures informant reports of physical activities and differentiates individuals with normal physical functionality from those individuals with impaired physical functionality. The QPAR correlated with Gold Standard assessments of strength and sarcopenia, activities of daily living, gait and mobility, fitness, health related quality of life, frailty, global physical performance, and provided good discrimination between states of physical functionality, falls risk, and frailty. The QPAR performed well in comparison to standardized scales of objective physical performance, but in a brief fashion that could facilitate its use in clinical care and research.

Feasibility of Conducting Nonpharmacological Interventions to Manage Dementia Symptoms in Community-Dwelling Older Adults: A Cluster Randomized Controlled Trial.

This study assessed the feasibility of conducting 3 nonpharmacological interventions with older adults in dementia, exploring the effects of chair yoga (CY), compared to music intervention (MI) and chair-based exercise (CBE) in this population. Using a cluster randomized controlled trial (RCT), 3 community sites were randomly assigned 1:1:1 to CY, MI, or CBE. Participants attended twice-weekly 45-minute sessions for 12 weeks. Thirty-one participants were enrolled; 27 safely completed the interventions and final data collection (retention rate of 87%). Linear mixed modeling was performed to examine baseline and longitudinal group differences. The CY group improved significantly in quality of life compared to the MI group (CY mean = 35.6, standard deviation [SD] = 3.8; MI mean = 29.9, SD = 5.3, P = .010). However, no significant group differences were observed in physical function, behavioral, or psychological symptoms (eg, for mini-PPT: slopetime = 0.01, standard error [SE] = 0.3, P = .984 in the CBE group; slopetime = -0.1, SE = 0.3, P = .869 in the MI group; slopetime = -0.3, SE = 0.3, P = .361 in the CY group) over the 12-week intervention period. Overall, this pilot study is notable as the first cluster RCT of a range of nonpharmacological interventions to examine the feasibility of such interventions in older adults, most with moderate-to-severe dementia. Future clinical trials should be conducted to examine the effects of nonpharmacological interventions for older adults with dementia on health outcomes.

Tardive dyskinesia: motor system impairments, cognition and everyday functioning.

The recent approval of treatments for tardive dyskinesia (TD) has rekindled interest in this chronic and previously recalcitrant condition. A large proportion of patients with chronic mental illness suffer from various degrees of TD. Even the newer antipsychotics constitute a liability for TD, and their liberal prescription might lead to emergence of new TD in patient populations previously less exposed to antipsychotics, such as those with depression, bipolar disorder, autism, or even attention deficit hyperactivity disorder. The association of TD with activity limitations remains poorly understood. We review potential new avenues of assessing the functional sequelae of TD, such as the performance of instrumental activities of daily living, residential status, and employment outcomes. We identify several mediating aspects, including physical performance measures and cognition, that may represent links between TD and everyday performance, as well as potential treatment targets.