Toward a Multimodal Computer-Aided Diagnostic Tool for Alzheimer’s Disease Conversion

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder. It is one of the leading sources of morbidity and mortality in the aging population AD cardinal symptoms include memory and executive function impairment that profoundly alters a patient’s ability to perform activities of daily living. People with mild cognitive impairment (MCI) exhibit many of the early clinical symptoms of patients with AD and have a high chance of converting to AD in their lifetime. Diagnostic criteria rely on clinical assessment and brain magnetic resonance imaging (MRI). Many groups are working to help automate this process to improve the clinical workflow. Current computational approaches are focused on predicting whether or not a subject with MCI will convert to AD in the future. To our knowledge, limited attention has been given to the development of automated computer-assisted diagnosis (CAD) systems able to provide an AD conversion diagnosis in MCI patient cohorts followed longitudinally. This is important as these CAD systems could be used by primary care providers to monitor patients with MCI. The method outlined in this paper addresses this gap and presents a computationally efficient pre-processing and prediction pipeline, and is designed for recognizing patterns associated with AD conversion. We propose a new approach that leverages longitudinal data that can be easily acquired in a clinical setting (e.g., T1-weighted magnetic resonance images, cognitive tests, and demographic information) to identify the AD conversion point in MCI subjects with AUC = 84.7. In contrast, cognitive tests and demographics alone achieved AUC = 80.6, a statistically significant difference (n = 669, p < 0.05). We designed a convolutional neural network that is computationally efficient and requires only linear registration between imaging time points. The model architecture combines Attention and Inception architectures while utilizing both cross-sectional and longitudinal imaging and clinical information. Additionally, the top brain regions and clinical features that drove the model’s decision were investigated. These included the thalamus, caudate, planum temporale, and the Rey Auditory Verbal Learning Test. We believe our method could be easily translated into the healthcare setting as an objective AD diagnostic tool for patients with MCI.

Developing guidelines for the translation and cultural adaptation of the Montreal Cognitive Assessment: scoping review and qualitative synthesis

Background Ethnic minorities in countries such as the UK are at increased risk of dementia or minor cognitive impairment. Despite this, cognitive tests used to provide a timely diagnosis for these conditions demonstrate performance bias in these groups, because of cultural context. They require adaptation that accounts for language and culture beyond translation. The Montreal Cognitive Assessment (MoCA) is one such test that has been adapted for multiple cultures. Aims We followed previously used methodology for culturally adapting cognitive tests to develop guidelines for translating and culturally adapting the MoCA. Method We conducted a scoping review of publications on different versions of the MoCA. We extracted their translation and cultural adaptation procedures. We also distributed questionnaires to adaptors of the MoCA for data on the procedures they undertook to culturally adapt their respective versions. Results Our scoping review found 52 publications and highlighted seven steps for translating the MoCA. We received 17 responses from adaptors on their cultural adaptation procedures, with rationale justifying them. We combined data from the scoping review and the adaptors’ feedback to form the guidelines that state how each question of the MoCA has been previously adapted for different cultural contexts and the reasoning behind it. Conclusions This paper details our development of cultural adaptation guidelines for the MoCA that future adaptors can use to adapt the MoCA for their own languages or cultures. It also replicates methods previously used and demonstrates how these methods can be used for the cultural adaptation of other cognitive tests.

Constructing and Standardizing Cognitive Test in Artist Competition Rule for Epee Referees

The research aimed at constructing and standardizing a cognitive test in competition rules for epee referees as well as identifying the validity of these tests. The problem of the research lies in the lack of cognitive tests made for fencing referees. The researchers used the descriptive method on (50) referees and the pilot study was conducted on (3) while constructing subjects (47) and standardizing subjects were (45). The test was distributed, collected, and treated using proper statistical operations to conclude that there are differences between referees in their level that proves the validity of this test to measure cognitive knowledge of competition rules.

Temporal clusters of age-related behavioral alterations captured in smartphone touchscreen interactions

Cognitive and behavioral abilities alter across the adult life span. Smartphones engage various cognitive functions and the corresponding touchscreen interactions may help resolve if and how the behavior is systematically structured by aging. Here, in a sample spanning the adult lifespan (16 to 86 years, N = 598, accumulating 355 million interactions) we analyzed a range of interaction intervals - from a few milliseconds to a minute. We used probability distributions to cluster the interactions according to their next inter-touch interval dynamics to discover systematic age-related changes at the distinct temporal clusters. There were age-related behavioral losses at the clusters occupying short intervals (~ 100 ms, R2 ~ 0.8) but gains at the long intervals (~ 4 s, R2 ~ 0.4). These correlates were independent of the years of experience on the phone or the choice of fingers used on the screen. We found further evidence for a compartmentalized influence of aging, as individuals simultaneously demonstrated both accelerated and decelerated aging at distant temporal clusters. In contrast to these strong correlations, cognitive tests probing sensorimotor, working memory, and executive processes revealed rather weak age-related decline. Contrary to the common notion of a simple behavioral decline with age based on conventional cognitive tests, we show that real-world behavior does not simply decline and the nature of aging systematically varies according to the underlying temporal dynamics. Of all the imaginable factors determining smartphone interactions in the real world, age-sensitive cognitive and behavioral processes can dominatingly dictate smartphone temporal dynamics.

Evaluation of the Therapeutic Potential of Oral Phycocyanin-Rich Spirulina Extract in Neuropsychiatric Disorders.

Aim: Spirulina is a microalga that is widely used as a food supplement and is regarded as having performance enhancing and health promoting properties. We conducted a preliminary evaluation of the possible antidepressant, anti-anxiety, pro-socialization and cognition-enhancing effects of Spirulina in mouse models Methods: Sixty male BalbC mice aged 3 weeks were administered phycocyanin-rich Spirulina extract [PRSE, 545 mg/kg], fluoxetine [20 mg/kg] or water orally for 5 weeks. During the last 2 weeks of the experiment a series of behavioral-cognitive tests was performed to evaluate motor activity, antidepressant and anti-anxiety effects, socialization and cognitive effects. Effects of PRSE and fluoxetine were compared to those of water. Results: There was a significant effect of PRSE in the activity domain, manifesting as an increase in velocity in the open field [p=0.0007 vs. water]. Fluoxetine significantly enhanced immobility in the tail suspension test and the forced swim test reflecting the known antidepressant effect of this compound, but not PRSE. There were no significant effects of PRSE in tests of anxiety, socialization or cognition. Conclusions: The most striking observation in this study was that PRSE significantly enhanced activity in the open field test. Further studies are indicated to confirm and extend this finding and investigate possible mechanisms of action. The results of the current study do not support sporadic reports of possible antidepressant or cognition-enhancing effects of PRSE. Nevertheless, additional studies are indicated using depression models rather than naïve mice, alternative mouse strains, using additional cognitive tests, and administering higher PRSE doses.

Identifying Mild Cognitive Impairment by Using Human–Robot Interactions

Background: Mild cognitive impairment (MCI), which is common in older adults, is a risk factor for dementia. Rapidly growing health care demand associated with global population aging has spurred the development of new digital tools for the assessment of cognitive performance in older adults. Objective: To overcome methodological drawbacks of previous studies (e.g., use of potentially imprecise screening tools that fail to include patients with MCI), this study investigated the feasibility of assessing multiple cognitive functions in older adults with and without MCI by using a social robot. Methods: This study included 33 older adults with or without MCI and 33 healthy young adults. We examined the utility of five robotic cognitive tests focused on language, episodic memory, prospective memory, and aspects of executive function to classify age-associated cognitive changes versus MCI. Standardized neuropsychological tests were collected to validate robotic test performance. Results: The assessment was well received by all participants. Robotic tests assessing delayed episodic memory, prospective memory, and aspects of executive function were optimal for differentiating between older adults with and without MCI, whereas the global cognitive test (i.e., Mini-Mental State Examination) failed to capture such subtle cognitive differences among older adults. Furthermore, robot-administered tests demonstrated sound ability to predict the results of standardized cognitive tests, even after adjustment for demographic variables and global cognitive status. Conclusion: Overall, our results suggest the human–robot interaction approach is feasible for MCI identification. Incorporating additional cognitive test measures might improve the stability and reliability of such robot-assisted MCI diagnoses.

Chronic kidney disease biomarkers, cognitive impairment and incident dementia in an older healthy cohort

Background: Chronic kidney disease is a risk factor for cognitive impairment (CI),but reports of individual associations of estimated glomerular filtration rate (eGFR) and albuminuria with CI and incident dementia in healthier older longitudinal populations are lacking. Our goal was to estimate these associations in a large cohort of older healthy persons. Methods: In a longitudinal cohort study of older persons without prior cardiovascular disease, we estimated the associations between baseline eGFR (in mL/min per 1.73 m2) and albuminuria, measured as urine albumin-to-creatinine ratio (UACR, in mg/mmol) and cognitive test scores, declines in cognitive test scores and incident dementia, using adjusted linear and linear mixed models. Cox proportional hazards regression models assessed the association between baseline kidney function and incident CI no dementia (CIND) or dementia at a median of 4.7 years. Results: At baseline, among 18,131 participants, median age was 74 years, eGFR 74 (IQR 63, 84), UACR 0.8 (IQR 0.5, 1.5; (7.1 (4.4- 13.3 mg/g and 56% were female. Baseline eGFR was not associated with performance on any cognitive tests in cross-sectional analysis, nor incident CIND or dementia over median follow-up of 4.7 years. However, baseline UACR ≥ 3 (≥ 26.6 mg/g) was significantly associated with lower baseline scores and larger declines on the Modified Mini Mental State Exam, verbal memory and processing speed tests, and with incident CIND [(hazard ratio, HR, 1.19; 95% confidence interval, CI,1.07 - 1.33)] and dementia (HR 1.32;1.06 - 1.66). Conclusion: Mild albuminuria was associated with worse baseline cognitive function, cognitive decline, and increased risk for incident CIND and dementia. Screening global cognitive tests for older persons with UACR ≥ 3 mg/mmol could identify those at elevated risk of cognitive decline and dementia.

Voice Biomarkers as Possible Indicators of Cognitive Aging

There is emerging evidence that measures of voice prosody are related to diagnoses of Alzheimer’s Disease and Related Disorders. The goal of this study was to examine whether voice prosody measures (pitch, pulse, voice breaks, jitter, shimmer, and amplitude) are also related to individual differences in normal cognitive aging. Data are from the Midlife in the United States Wave 2 (M2) and Wave 3 (M3) for 2693 participants (ages 42-92 at M3) who completed the M2 and M3 Brief Test of Adult Cognition by Telephone (BTACT) and had M3 voice recordings. Voice variables were measured from cognitive interviews using three cognitive tests and averaged to create a composite for each voice variable. Voice prosody was related to age, sex, education, and health, which were included as covariates. Older adults, men, and those with more health conditions had higher jitter and shimmer. Older adults, women, and those with higher education and better health had more voice breaks. Hierarchical regression models, controlling for the covariates, examined the voice composites as predictors of each cognitive measure at M3 and change over 9 years from M2 to M3. As hypothesized, higher jitter predicted lower performance and greater decline on memory, category fluency, and attention. Contrary to predictions, a lower number of voice breaks predicted worse performance and greater declines on all cognitive tests. The results suggest that voice biomarkers are related to cognitive performance and decline, and they may offer a promising approach for identifying early signs of cognitive impairment or dementia.