Using Variational Autoencoder to Develop and Validate a Compact, Deep Representation of Digital Clock Drawing Test for Classifying Dementia

The Clock Drawing Test (CDT) is an inexpensive tool to screen for dementia. In this study, we examined if a semi-supervised deep learning (DL) system using Variational Autoencoder (VAE) can extract atypical clock features from a large dataset of unannotated CDTs (n=13,580) and use them to classify dementia (n=18) from non-dementia (n=20) peers. The classification model built with VAE latent space features adequately classified dementia from non-dementia (0.78 Area Under Receiver Operating Characteristics (AUROC)). The VAE-identified atypical clock features were then reviewed by domain experts and compared with existing literature on clock drawing errors. This study shows that a semi-supervised deep learning (DL) analysis of the CDT can extract important clock drawing anomalies that are predictive of dementia.

Theracurmin supplementation may be a therapeutic option for older patients with alzheimer’s disease: a 6-month retrospective follow-up study

Background: Alzheimer’s Disease (AD) is still a great global challenge and agents with various mechanisms represent a promising therapeutic opportunity. Theracurmin, a very highly absorbable curcumin formulation, was shown to improve memory and attention in non-demented people. Objective: To investigate the effect of Theracurmin on disease course in elderly patients with mild cognitive impairment (MCI) and AD. Methods: This follow-up study was performed retrospectively on 93 patients with MCI or AD. All patients underwent comprehensive geriatric assessment, including Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MOCA), clock-drawing test, activities of daily living (ADL), at baseline and end of the 6th-month. 19 patients with AD and 17 with MCI were treated with Theracurmin 180 mg/day per oral. Results: MMSE, MOCA and instrumental ADL scores decreased in AD patients that were not treated with Theracurmin (p<0.001, p=0.011, and p=0.004, respectively), whereas these scores remained stable in those treated with Theracurmin. This stabilization in the instrumental ADL was also observed in MCI patients treated with Theracurmin. During the follow-up, three of MCI patients who did not receive Theracurmin progressed to AD, whereas only one patient progressed in those who received it. Conclusion: Theracurmin seems to be a therapeutic option for elderly patients with AD and MCI via providing stabilization of the disease course by preventing progressive loss in cognitive functions and ADLs.

Impact of post-stroke cognitive dysfunction on driving ability

The paper aims to present the current views on the impact of post-stroke cognitive deficits on driving ability, and diagnostic assessment practices in this area. Firstly, the neuropsychological consequences of stroke are briefly presented. This part focuses specifically on visuospatial and executive dysfunctions. Among those dysfunctions, unilateral neglect, especially as it is frequently associated with anosognosia, may have the greatest impact on driving ability, leading to an increased accident risk. Then, different approaches to assessing fitness to drive after stroke are presented, including on-road testing, testing with the use of simulator, and clinical assessment focusing on cognition. The role of cognitive assessment in predicting fitness to drive is described in more detail. The Clock Drawing Test is the most appropriate screening measure in this context, as it engages both visuospatial and executive functions. The Trail Making Test is the most popular working memory test in the context of drivers’ assessment, as it requires visual search and psychomotor speed. The Rey Complex Figure Test is another commonly used test. It requires visuospatial and executive functions, and may also serve as a measure of visuospatial memory. Finally, the legal aspects of the assessments are discussed with reference to the practices used in Great Britain, Belgium, Sweden, and Germany. In Poland, there are no detailed standards for post-stroke fitness-to-drive assessment.

Extended Application of Digital Clock Drawing Test in the Evaluation of Alzheimer’s Disease Based on Artificial intelligence and the Neural Basis

Introduction: This study aimed to build the supervised learning model to predict the state of cognitive impairment, Alzheimer’s Disease (AD) and cognitive domains including memory, language, action, and visuospatial based on Digital Clock Drawing Test (dCDT) precisely. Methods: 207 normal controls, 242 Mild Cognitive Impairment (MCI) patients, 87 dementia patients, including 53 AD patients, were selected from Shanghai Tongji Hospital. The electromagnetic tablets were used to collect the trajectory points of dCDT. By combining dynamic process and static results, different types of features were extracted, and the prediction models were built based on the feature selection approaches and machine learning methods. Results: The optimal AUC of cognitive impairment’s screening, AD’s screening and differentiation are 0.782, 0.919 and 0.818, respectively. In addition, the cognitive state of the domains with the best prediction result based on the features of dCDT is action with the optimal AUC 0.794, while the other three cognitive domains got the prediction results between 0.744-0.755. Discussion: By extracting dCDT features, cognitive impairment and AD patients can be identified early. Through dCDT feature extraction, a prediction model of single cognitive domain damage can be established.

Clock drawing test: comparison between the Pfizer and the Shulman systems

ABSTRACT Cognitive decline can be screened by the clock drawing test (CDT), which has several versions. Objective: This survey aimed to analyze the correlation between two simple methods for scoring the CDT. Methods: This cross-sectional study was nested in the Elo-Creati cohort from Passo Fundo, Brazil and comprised 404 subjects. Two raters underwent previous training and scored the subjects’ CDT according to both the Pfizer and Shulman systems. The inter-observer and intra-observer concordance within each method was analyzed with the Spearman’s rank correlation coefficient, as well as the concordance of the scores between the two methods. Age and scholarity were also correlated with the scores. Results: Most of the participants were women (93.8%) and Caucasian (84.6%), with a mean age of 66.9 (±7.8) years and a scholarity of 10.9 years (±5.6). There was significant inter-observer (Pfizer: r=0.739, p£0.001; Shulman: r=0.727, p£0.001) and intra-observer correlation (Pfizer: rater 1, r=0.628, p≤0.001; rater 2, r=0.821, p≤0.001; Shulman: rater 1, r=0.843, p≤0.001; rater 2: r=0.819; p≤0.001). Intra-observer correlation was also observed comparing Pfizer and Shulman methods (rater 1: r=0.744; p≤0.001; rater 2: r=0.702; p≤0.001). There was weak correlation of the scores with scholarity (Pfizer: r=0.283, p£0.001; Shulman: r=0.244, p£0.001) and age (Pfizer: r=-0.174, p£0.001; Shulman: r=-0.170, p£0.001). More participants were classified with decreased cognition through the Pfizer system (rater 1: 44.3 vs. 26.5%; rater 2: 42.1 vs. 16.3%; p≤0.001). Conclusions: For this population, our results suggest that the Pfizer system of scoring CDT is more suitable for screening cognitive decline.

Longitudinal Association of Executive Function and Balance in Community-Dwelling Older Adults

Declines in Executive Function (EF) are associated with balance in community-dwelling older adults with Mild Cognitive Impairment (MCI). While this has been examined in cross-sectional studies, no longitudinal studies describe change over time. The purpose of this study was to examine how performance on the components of the Short Physical Performance Battery (SPPB) are associated with EF in community-dwelling older adults who transition into MCI. This secondary data analysis employed eight years of data from the National Health and Aging Trends Study dataset (2011 – 2018) with 1,225 participants in all eight waves (balanced). EF was measured with the Clock Drawing Test and SPPB balance tests included side-by-side, semi-tandem, full tandem, and single leg stance with eyes open or closed. Longitudinal ordered logistic regression was used to examine associations between each balance measure and EF while controlling for comorbidity, function, depression, gender, age, and ethnicity. EF was significantly associated with tandem, semi-tandem, and single leg stance after controlling for covariates. One point increase in SPPB can reduce the risk of EF impairment by 8.2% (Odds Ratio (OR)=0.918, p&lt;0.001). Among SPPB components, semi-tandem (OR=0.468) and side-by-side (OR=0.472) were the strongest predictors of EF impairment. Declines in both EF and balance performance occurred over an eight-year period in adults. This may reflect common neural processes shared between the cognitive and motor areas of the central nervous system. Best practice suggests screening both balance (tandem, semi-tandem, or single leg stance) and EF in the clinical assessment of community-dwelling older adults.

Assessment of cognitive dysfunction using the Montreal Cognitive Assessment test: rate, severity and comparison with the Clock test alone in a population of patients referred for TAVI

Background Although not recommended in routine practice, the detection and quantification of Cognitive Dysfunction (CD) in older patients might have an impact on clinical decisions. We assessed the rate and severity of CD in an unselected population of patients referred for Transcatheter Aortic Valve Implantation (TAVI) using the Montreal Cognitive Assessment (MoCA) and using the Clock Drawing Test (ClockT) alone. Methods The MoCA was performed before TAVI by an experienced operator. The ClockT was scored out of 10 points according to the Rouleau rating scale. CD was defined according to the MoCA score: No CD if score ≥26, mild CD if score 18–25, moderate if 10–17 and severe if &lt;10. Inter-observer reliability of scoring on the ClockT was estimated with the Bland-Altman method. Agreement between MoCA scores and the ClockT for ruling out and for detecting CD were measured with the Kappa coefficient. Results MoCA was performed in 83 consecutive patients referred for TAVI, median age 85 years. The mean time required for assessment was 11±2 min for the MoCA and 3±2 min for the ClockT. The mean MoCA score was 21±4.5: CD was excluded in 17 (20%) pts, mild CD was found in 50 (60%), moderate in 15 (18%) and severe in one (1%). The median ClockT score was 8 (interquartile 6; 9), with excellent inter-observer concordance (Kappa= 0.84). Overall, 51% of the variance of the MoCA score was explained by the ClockT alone according to multiple regression. A ClockT &lt;7 detected a group with significantly lower MoCA score, compared to pts with higher ClockT scores (figure). Conclusion Among patients referred for TAVI, CD can be excluded using the MoCA test in 20%, while moderate or severe CD is observed in 18%. The ClockT alone is faster to implement, reliable to interpret and enabled detection of patients with moderate CD when Rouleau scoring was &lt;7. Funding Acknowledgement Type of funding sources: None.