Screening For Cognitive Impairment Research Articles

Atrial Fibrillation and Dementia: A Report From the AF-SCREEN International Collaboration

Growing evidence suggests a consistent association between atrial fibrillation (AF) and cognitive impairment and dementia that is independent of clinical stroke. This report from the AF-SCREEN International Collaboration summarizes the evidence linking AF to cognitive impairment and dementia. It provides guidance on the investigation and management of dementia in patients with AF on the basis of best available evidence. The document also addresses suspected pathophysiologic mechanisms and identifies knowledge gaps for future research. Whereas AF and dementia share numerous risk factors, the association appears to be independent of these variables. Nevertheless, the evidence remains inconclusive regarding a direct causal effect. Several pathophysiologic mechanisms have been proposed, some of which are potentially amenable to early intervention, including cerebral microinfarction, AF-related cerebral hypoperfusion, inflammation, microhemorrhage, brain atrophy, and systemic atherosclerotic vascular disease. The mitigating role of oral anticoagulation in specific subgroups (eg, low stroke risk, short duration or silent AF, after successful AF ablation, or atrial cardiopathy) and the effect of rhythm versus rate control strategies remain unknown. Likewise, screening for AF (in cognitively normal or cognitively impaired patients) and screening for cognitive impairment in patients with AF are debated. The pathophysiology of dementia and therapeutic strategies to reduce cognitive impairment warrant further investigation in individuals with AF. Cognition should be evaluated in future AF studies and integrated with patient-specific outcome priorities and patient preferences. Further large-scale prospective studies and randomized trials are needed to establish whether AF is a risk factor for cognitive impairment, to investigate strategies to prevent dementia, and to determine whether screening for unknown AF followed by targeted therapy might prevent or reduce cognitive impairment and dementia.

Fully automated discrimination of Alzheimer's disease using resting-state electroencephalography signals.

The Alzheimer's disease (AD) population increases worldwide, placing a heavy burden on the economy and society. Presently, there is no cure for AD. Developing a convenient method of screening for AD and mild cognitive impairment (MCI) could enable early intervention, thus slowing down the progress of the disease and enabling better overall disease management. In the current study, resting-state electroencephalography (EEG) data were acquired from 113 normal cognition (NC) subjects, 116 amnestic MCI patients, and 72 probable AD patients. After preprocessing by an automatic algorithm, features including spectral power, complexity, and functional connectivity were extracted, and machine-learning classifiers were built to differentiate among the 3 groups. The classification performance was evaluated from multiple perspectives, including accuracy, specificity, sensitivity, area under the curve (AUC) with 95% confidence intervals, and compared to the empirical chance level by permutation tests. The analysis of variance results (P<0.05 with false discovery rate correction) confirmed the tendency to slow brain activity, reduced complexity, and connectivity with AD progress. By combining the features, the ability of the machine-learning classifiers, especially the ensemble trees, to differentiate among the 3 groups, was significantly better than that of the empirical chance level of the permutation test. The AUC of the classifier with the best performance was 80.08% for AD vs. NC, 70.82% for AD vs. MCI, and 63.95% for MCI vs. NC. The current study presented a fully automatic procedure that could significantly distinguish NC, MCI, and AD subjects via resting-state EEG signals. The study was based on a large data set with evidence-based medical diagnosis and provided further evidence that resting-state EEG data could assist in the discrimination of AD patients.

Automated analysis of facial emotions in subjects with cognitive impairment.

Differences in expressing facial emotions are broadly observed in people with cognitive impairment. However, these differences have been difficult to objectively quantify and systematically evaluate among people with cognitive impairment across disease etiologies and severity. Therefore, a computer vision-based deep learning model for facial emotion recognition trained on 400.000 faces was utilized to analyze facial emotions expressed during a passive viewing memory test. In addition, this study was conducted on a large number of individuals (n = 493), including healthy controls and individuals with cognitive impairment due to diverse underlying etiologies and across different disease stages. Diagnoses included subjective cognitive impairment, Mild Cognitive Impairment (MCI) due to AD, MCI due to other etiologies, dementia due to Alzheimer’s diseases (AD), and dementia due to other etiologies (e.g., Vascular Dementia, Frontotemporal Dementia, Lewy Body Dementia, etc.). The Montreal Cognitive Assessment (MoCA) was used to evaluate cognitive performance across all participants. A participant with a score of less than or equal to 24 was considered cognitively impaired (CI). Compared to cognitively unimpaired (CU) participants, CI participants expressed significantly less positive emotions, more negative emotions, and higher facial expressiveness during the test. In addition, classification analysis revealed that facial emotions expressed during the test allowed effective differentiation of CI from CU participants, largely independent of sex, race, age, education level, mood, and eye movements (derived from an eye-tracking-based digital biomarker for cognitive impairment). No screening methods reliably differentiated the underlying etiology of the cognitive impairment. The findings provide quantitative and comprehensive evidence that the expression of facial emotions is significantly different in people with cognitive impairment, and suggests this may be a useful tool for passive screening of cognitive impairment.

Predictive Sentence Context Reduces Listening Effort in Older Adults With and Without Hearing Loss and With High and Low Working Memory Capacity.

Listening effort is needed to understand speech that is degraded by hearing loss, a noisy environment, or both. This in turn reduces cognitive spare capacity, the amount of cognitive resources available for allocation to concurrent tasks. Predictive sentence context enables older listeners to perceive speech more accurately, but how does contextual information affect older adults' listening effort? The current study examines the impacts of sentence context and cognitive (memory) load on sequential dual-task behavioral performance in older adults. To assess whether effects of context and memory load differ as a function of older listeners' hearing status, baseline working memory capacity, or both, effects were compared across separate groups of participants with and without hearing loss and with high and low working memory capacity. Participants were older adults (age 60-84 years; n = 63) who passed a screen for cognitive impairment. A median split classified participants into groups with high and low working memory capacity. On each trial, participants listened to spoken sentences in noise and reported sentence-final words that were either predictable or unpredictable based on sentence context, and also recalled short (low-load) or long (high-load) sequences of digits that were presented visually before each spoken sentence. Speech intelligibility was quantified as word identification accuracy, and measures of listening effort included digit recall accuracy, and response time to words and digits. Correlations of context benefit in each dependent measure with working memory and vocabulary were also examined. Across all participant groups, accuracy and response time for both word identification and digit recall were facilitated by predictive context, indicating that in addition to an improvement in intelligibility, listening effort was also reduced when sentence-final words were predictable. Effects of predictability on all listening effort measures were observed whether or not trials with an incorrect word identification response were excluded, indicating that the effects of predictability on listening effort did not depend on speech intelligibility. In addition, although cognitive load did not affect word identification accuracy, response time for word identification and digit recall, as well as accuracy for digit recall, were impaired under the high-load condition, indicating that cognitive load reduced the amount of cognitive resources available for speech processing. Context benefit in speech intelligibility was positively correlated with vocabulary. However, context benefit was not related to working memory capacity. Predictive sentence context reduces listening effort in cognitively healthy older adults resulting in greater cognitive spare capacity available for other mental tasks, irrespective of the presence or absence of hearing loss and baseline working memory capacity.

The audio recorded cognitive screen for brief screening of cognitive impairment in patients with psychosis: A pilot study

Introduction. Disorders of cognitive functioning in patients with psychosis can manifest in different domains. The disorders vary depending on the severity, from mild to severe, and on the severity of symptoms within the underlying disease. The aim of this study was to examine the possibility of using the Audio Recorded Cognitive Screen in patients with schizophrenia. Material and Methods. The study included a total of 61 subjects divided into two groups: 31 subjects with schizophrenia and 30 healthy controls. All subjects completed the Audio Recorded Cognitive Screen to assess the cognitive status in five domains of cognitive functioning. Results. The Audio Recorded Cognitive Screen showed a good reliability index (? = 0.85). Multivariate analysis of variance confirmed the differences between the two groups in all examined cognitive domains (F (6.53) = 26.719, p &lt; .001). The partial eta squared results were as follows: object naming 0.159; immediate recall 0.531; delayed recall 0.585; visuospatial functions 0.334; attention 0.644; and verbal fluency 0.590. These results indicated significant differences between the two groups. Conclusion. The Audio Recorded Cognitive Screen is a feasible tool for the detection of neurocognitive impairment in individuals with schizophrenia. However, it is necessary to conduct further research in larger samples and use additional assessment instruments in this population.

Early Screening of Mild Cognitive Impairment Through Hand Movement Analysis in Virtual Reality Based on Machine Learning: Screening of MCI Through Hand Movement in VR

Early Screening of Mild Cognitive Impairment Through Hand Movement Analysis in Virtual Reality Based on Machine Learning: Screening of MCI Through Hand Movement in VR

FORENSIC HANDWRITING ANALYSIS ENABLES THE DETECTION OF DEMENTIA CASES

In many cases, legal psychological expertise includes the evaluation of the cognitive state of a person. In particular, that relates to the cognitive impairment due to dementia. Alzheimer's disease (AD) is the most common form of dementia. There are multiple biomarkers and neurological diagnostic procedures, however, they are often not applicable in the legal context. Handwriting analysis is a potential method for early detection of the onset of the disease. It allows the investigation of current specimens as well as documents from the past, which is especially important for forensic. In the article we present an instrument for screening of possible AD (AD-HS) by handwriting. It includes 40 handwriting and 2 linguistic markers. Their cumulative assessment allows the evaluation of a quantitative AD Indicator (ADI), which reflects the severity level of impairment. The presented validation study includes 48 persons with the AD diagnosis and the control group of 182 handwriting specimens from the database of the HSDetect system for handwriting analysis. The mean value for ADI in the control group equals 0.26 and the 95% level lies at 0.46. All participants have higher ADI value with an average value of 0.46. Besides, the correlation between ADI and the severity of AD was 0.64. That is, AD-HS allows the evaluation of AD severity. The presented approach provides a practical instrument for forensics and criminal expertise. Further refinement of AD-HS and the extension of the experiment data will allow even more reliable screening of cognitive impairment through handwriting. Keywords: forensic psychological examination, Alzheimer's disease, indicator of Alzheimer's disease, cognitive impairment in handwriting, dementia.

Patient, Family Caregiver, and Provider Perceptions on Self-Assessment Screening for Cognitive Impairment in Primary Care: Findings From a Qualitative Study.

The purpose of this study was to evaluate patient, family, and provider perspectives on routine cognitive screening of older adults in primary care using a novel self-assessment tool for detection of early cognitive impairment (CI). We conducted four virtual focus groups with patients aged 65 and older with no CI (n = 18) and family caregivers of patients with CI (n = 5) and interviews with primary care providers (n = 11). Patient and family caregiver participants felt that early detection of CI was important in primary care and may facilitate planning for the future including finances, living arrangements, and advance care planning. Providers reported that they do not use a standardized tool to routinely screen patients for CI yet endorsed the use of a self-assessment CI screening tool. These results suggest that routine screening of older adults using a brief, self-assessment screening tool for CI in primary care may be acceptable to patients, family caregivers, and providers. The findings from this study will inform the development of a brief self-assessment CI screening tool for use in primary care.

Validation of the automated neuropsychological assessment metrics for assessing cognitive impairment in systemic lupus erythematosus.

ObjectiveWe previously demonstrated the utility of the Automated Neuropsychological Assessment Metrics (ANAM) for screening cognitive impairment (CI) in patients with systemic lupus erythematosus (SLE) and developed composite indices for interpreting ANAM results. Our objectives here were to provide further support for the ANAM’s concurrent criterion validity against the American College of Rheumatology neuropsychological battery (ACR-NB), identify the most discriminatory subtests and scores of the ANAM for predicting CI, and provide a new approach to interpret ANAM results using Classification and Regression Tree (CART) analysis.Methods300 adult SLE patients completed an adapted ACR-NB and ANAM on the same day. As per objectives, six models were built using combinations of ANAM subtests and scores and submitted to CART analysis. Area under the curve (AUC) was calculated to evaluate the ANAM’s criterion validity compared to the adapted ACR-NB; the most discriminatory ANAM subtests and scores in each model were selected, and performance of models with the highest AUCs were compared to our previous composite indices; decision trees were generated for models with the highest AUCs.ResultsTwo models had excellent AUCs of 86 and 89%. Eight most discriminatory ANAM subtests and scores were identified. Both models demonstrated higher AUCs against our previous composite indices. An adapted decision tree was created to simplify the interpretation of ANAM results.ConclusionWe provide further validity evidence for the ANAM as a valid CI screening tool in SLE. The decision tree improves interpretation of ANAM results, enhancing clinical utility.

Utility of olfactory identification test for screening of cognitive dysfunction in community-dwelling older adults.

BackgroundThere is a need for a large-scale screening test that can be used to detect dementia in older individuals at an early stage. Olfactory identification deficits have been shown to occur in the early stages of dementia, indicating their usefulness in screening tests. This study investigated the utility of an olfactory identification test as a screening test for mild cognitive dysfunction in community-dwelling older people.MethodsThe subjects were city-dwelling individuals aged over 65 years but under 85 years who had not been diagnosed with dementia or mild cognitive impairment. The Japanese version of the Mild Cognitive Impairment Screen was used to evaluate cognitive function. Based on the results, the subjects were divided into two groups: healthy group and cognitively impaired group. Olfactory identification abilities based on the Japanese version of the University of Pennsylvania Smell Identification Test were compared between the groups.ResultsThere were 182 participants in total: 77 in the healthy group and 105 in the cognitively impaired group. The mean olfactory identification test score of the cognitively impaired group was significantly lower than that of the healthy group. The cognitive impairment test score was significantly correlated with the olfactory identification test score.ConclusionsCross-sectional olfactory identification deficits at baseline in community-dwelling older adults reflected cognitive dysfunction. Assessing olfactory identification ability might be useful as a screening test for mild cognitive dysfunction in community-dwelling older people.

611 Mild cognitive impairment is associated with subclinical left ventricular dysfunction as assessed by global longitudinal strain in hypertensive patients

Abstract Aims Left ventricular global longitudinal strain (GLS) detects subtle systolic abnormalities in various cardiovascular conditions, which represent significant risk factors for cognitive impairment and stroke. Specifically, GLS has emerged as a more precise myocardial function measure than left ventricular ejection fraction (LVEF). This study investigated the relationship of GLS with mild cognitive impairment (MCI) in hypertensive patients. Methods and results From February 2020 to October 2021 were enrolled hypertensive patients without atrial fibrillation and/or cerebrovascular and/or neurodegenerative diseases. Complete demographic, clinical characteristics, laboratory analyses, conventional echocardiographic parameters were collected. Finally, MCI was defined by accurate the Quick Mild Cognitive Impairment (QMCI) Screen corrected for age and education. This score explores spatial and temporal orientation, registration, delayed recall, clock design, logical memory, and verbal fluency in a brief time (5 min—score 0–100); a compliance questionnaire (Morisky medication adherence scale); a questionnaire on nutritional status (MNA). 81 hypertensive patients [66 ± 7.27 years; 9 (11%) female] were included in the study. Concerning echocardiographic evaluation, LVEF was 50.47 ± 9.95% and mean GLS was −16.00 ± 3.66. Mean QMCI corrected for age and education was 56.45 ± 9.37, and MCI was detected in 21 patients (26%). When comparing the patients with MCI (QMCItot &amp;lt;49.4) and without MCI (QMCItot &amp;gt;49.4), a statistically significant difference of GLS values was detected (no MCI: −16.52 ± 3.66 vs. MCI: −14.18 ± 3.23; P = 0.032); on the other hand, the two groups did not differ in LVEF (no MCI: 50.58 ± 9.70 vs. MCI: 48.86 ± 11.93; P = 0.864). Furthermore, excluding patients with FE ≥ 45% from the analysis, a statistically significant linear regression was observed between QMCI (corrected for age and education) and the GLS (P = 0.014) (Figure 1). Conclusions Compromised GLS, but not LV EF, is related to MCI in hypertensive patients who are free of clinical dementia, stroke, and neurodegenerative disease. Moreover, our study demonstrates for the first time the existence of a significant association between the QMCI and GLS; consequently, GLS could be an additional parameter in clinical practice for early recognition of MCI. However, studies on a larger population will be needed to confirm this association.

A Virtual Supermarket Program for the Screening of Mild Cognitive Impairment in Older Adults: Diagnostic Accuracy Study.

BackgroundMild cognitive impairment (MCI) is often a precursor of dementia, and patients with MCI develop dementia at a higher rate than healthy older adults. Early detection of cognitive decline at the MCI stage supports better planning of care and interventions. At present, the use of virtual reality (VR) in screening for MCI in older adults is promising, but there is little evidence regarding the use of virtual supermarkets to screen for MCI.ObjectiveThe objectives of this study are to validate a VR game–based test, namely, the Virtual Supermarket Program (VSP), for differentiating patients with MCI and healthy controls and to identify cutoff scores for different age levels.MethodsSubjects were recruited from several nursing homes and communities in Changchun, China. They were divided into a healthy control group (n=64) and an MCI group (n=62). All subjects were administered the VSP and a series of neuropsychological examinations. The study determined the optimal cutoff, discriminating validity, concurrent validity, and retest reliability of the VSP. We used the area under the receiver operating characteristic curve (AUC) to evaluate the discriminating validity and obtain the optimal cutoff values. Pearson correlation analysis and the intraclass correlation coefficient were used to evaluate the concurrent validity and retest reliability, respectively.ResultsA cutoff score of 46.4 was optimal for the entire sample, yielding a sensitivity of 85.9% and specificity of 79.0% for differentiating individuals with MCI and healthy controls, and the AUC was 0.870 (95% CI 0.799-0.924). The median index of VSP score was 51.1 (range 42.6-60.0). There was a moderate positive correlation between the VSP total score and Mini-Mental State Examination score (r=0.429, P<.001). There was a strong positive correlation between VSP total score and Montreal Cognitive Assessment score (r=0.645, P<.001). The retest reliability of the VSP was feasible (r=0.588, P=.048).ConclusionsThe VSP is interesting and feasible for subjects. It shows high sensitivity and specificity for the identification of MCI in older adults, which makes it a promising screening method. The VSP may be generalized to older adults in other countries, although some cultural adaptation may be necessary.Trial RegistrationChinese Clinical Trial Registry ChiCTR2000040074; https://www.chictr.org.cn/showprojen.aspx?proj=64639

Determining Appropriate Screening Tools and Cutoffs for Cognitive Impairment in the Chinese Elderly

Background: The Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA) are the most commonly used tools for cognitive impairment screening. The present study aimed to investigate the ability of the MOCA and MMSE to differentiate between cognitively normal elderly individuals, MCI patients and dementia patients at different ages and education levels and to establish the optimal cutoff scores of the MoCA and MMSE for MCI and dementia in the Chinese elderly.Methods: A total of 2,954 Chinese elderly individuals, including 1,746 normal controls, 599 MCI patients and 249 dementia patients, were consecutively recruited in the study. The optimal cutoffs for MoCA and MMSE were determined using receiver operating characteristic (ROC) analysis among the different age and education levels in the three groups. Furthermore, comparison of ROC curves were made to evaluate the performances of the two tests.Results: The area under the curve(AUC) of the MoCA (0.82) for detecting MCI was significantly higher than that of the MMSE (0.75) (P < 0.001). When the sample was divided according to age and education level, the AUC of the MoCA (0.84) was higher than those of the MMSE (0.71) for MCI (P < 0.001) in the younger and more highly-educated groups. The optimal cutoff scores of the MoCA for the groups aged ≤ 75 years old and education ≤ 6 years, aged > 75 years old and education ≤ 6 years, aged ≤ 75 years old and education > 6 years, aged > 75 years old and education > 6 years in screening for MCI were identified as 19.5, 15.5, 24.5 and 24.5, respectively, and the optimal cutoff scores for dementia were 18.5, 10.5, 18.5 and 20.5, respectively. For MMSE in the above four groups, the cutoff scores to detect MCI were 26.5, 22.5, 28.5 and 26.5, respectively, and the optimal cutoff scores for dementia were 23.5, 19.5, 23.5 and 23.5, respectively.Conclusion: Compared to MMSE, the MoCA is more suitable for discriminating MCI in younger and more highly educated elderly Chinese individuals. However, the MMSE has advantage over MoCA in screening MCI in individuals with lower education levels and the older groups of Chinese elderly.

Reliability and validity of a quick test of cognitive speed (AQT) in screening for mild cognitive impairment and dementia

BackgroundCognitive disorders are one of the important issues in old age. There are many cognitive tests, but some variables affect their results (e.g., age and education). This study aimed to evaluate the reliability and validity of A Quick Test of Cognitive Speed (AQT) in screening for mild cognitive impairment (MCI) and dementia.MethodsThis is a psychometric properties study. 115 older adults participated in the study and were divided into three groups (46 with MCI, 24 with dementia, and 45 control) based on the diagnosis of two geriatric psychiatrists. Participants were assessed by AQT and Mini-Mental State Examination (MMSE). Data were analyzed using Pearson correlation, independent t-test, and ROC curve by SPSS v.23.ResultsThere was no significant correlation between AQT subscales and age and no significant difference between the AQT subscales in sex, educational levels. The test-retest correlations ranges were 0.84 from 097. Concurrent validity was significant between MMSE and AQT. Its correlation was with Color − 0.78, Form − 0.71, and Color-Form − 0.72. The cut-off point for Color was 43.50 s, Form 52 s, and Color-Form 89 s were based on sensitivity and specificity for differentiating older patients with MCI with controls. The cut-off point for Color was 62.50 s, for Form 111 s, and Color-Form 197.50 s based on sensitivity and specificity measures for differentiating older patients with dementia and MCI.ConclusionThe findings showed that AQT is a suitable tool for screening cognitive function in older adults.

Screening for cognitive impairment in systemic lupus erythematosus: Application of the Montreal Cognitive Assessment (MoCA) in a Greek patient sample

Cognitive impairment (CI) is one of the most frequent neuropsychiatric manifestations of systemic lupus erythematosus (SLE). Given that extensive neuropsychological testing is not always feasible in routine clinical practice, brief cognitive screening tools are desirable. The aim of this study was to evaluate the Montreal Cognitive Assessment (MoCA) as a screening tool for CI in SLE. Consecutive SLE patients followed at a single centre were evaluated using MoCA and an extensive neuropsychological test battery (NPT), including the Digits Forward and Digits Backwards, Rey Auditory Verbal Learning Memory Test, Trail Making Test, Stroop Colour-Word Test, Semantic and Phonetic Verbal Fluency tests and a 25-problem version of the General Adult Mental Ability test. The criterion validity of MoCA was assessed through receiver operating characteristic (ROC) analyses using three different case definitions: i) against normative population data, ii) and iii) against average performance of a comparison group of rheumatoid arthritis (RA) patients, to adjust for possible confounding effects of chronic illness and inflammatory processes on cognitive performance. The effect of patient-related (age, years of education, anxiety, depression, fatigue and pain) and disease-related (activity, damage, age at diagnosis, disease duration, use of glucocorticoid, psychotropic and pain medication) parameters on the MoCA was examined. A total of 71 SLE patients were evaluated. MoCA significantly correlated with all NPT scores and was affected by education level (p < 0.001), but not by other demographic or clinical variables. The optimal cutoff for detecting CI, as defined on the basis of normative population data, was 23/30 points, demonstrating 73% sensitivity and 75% specificity. A cutoff of 22/30 points, using neuropsychological profiles of the RA group as inflammatory disease controls, exhibited higher sensitivity (100%, based on both definitions) and specificity (87% and 90%, depending on the definition). The standard cutoff of 26/30 points displayed excellent sensitivity (91-100%) with significant expenses in specificity (43-45%). The MoCA is an easily applied tool, which appears to be reliable for identifying CI in SLE patients. The standard cutoff score (26/30) ensures excellent sensitivity while lower cutoff scores (22-23/30) may, also, provide higher specificity.

A remote digital tool for diagnosis and monitoring of Alzheimer’s disease

AbstractBackgroundEarly detection and monitoring of mild cognitive impairment (MCI) and Alzheimer’s Disease (AD) patients are key to tackling dementia and providing benefits to patients, caregivers, healthcare providers and society.MethodWe developed the Integrated Cognitive Assessment (ICA); a 5 minute computerised cognitive test employs Artificial Intelligence (AI) to improve its accuracy in detecting cognitive impairment. ICA presents a series of rapidly changing images on a mobile device to measure cognitive impairment via a person's accuracy and response time in categorising those images.We studied the ICA in a total of 230 participants. 95 healthy volunteers, 80 MCI, and 55 mild AD participants completed the ICA, the Montreal Cognitive Assessment (MoCA) and Addenbrooke’s Cognitive Examination (ACE) cognitive tests.ResultThe ICA demonstrated convergent validity with MoCA (r=0.58) and ACE (r=0.62). The ICA AI model was able to detect cognitive impairment with an area under the curve of 81% for MCI patients (MoCA 77%), and 88% for mild AD patients (MoCA 89%). The AI classifier, based on an explainable logistic regression model, demonstrated improved performance with increased training data. Furthermore it showed generalisability in performance from one population to another. The ICA was able to detect cognitive impairment with high accuracy when trained with one cohort and tested in an independent cohort with different cultural and demographic characteristics, a prerequisite for large population deployment.In a monitoring study, 12 healthy participants self‐administered 78 ICA tests remotely over a period of 3 months (936 tests in total). The ICA demonstrated no significant practice effect observed over the duration of the study.ConclusionThe ICA can support clinicians by aiding accurate diagnosis of MCI and AD and is appropriate for large‐scale screening of cognitive impairment. The ICA is unbiased by differences in language, culture and education and has additional advantages over standard of care tests because of its shorter duration, automatic scoring and potential for medical record or research database integration.The pandemic has presented a challenge for face‐face assessments. A digital tool such as the ICA allows us to adapt to these changes by administering assessments remotely and monitoring disease progression.

P.0596 The Brief Neuropsychological Cognitive Examination in cognitive impairment screening in HIV-positive individuals

P.0596 The Brief Neuropsychological Cognitive Examination in cognitive impairment screening in HIV-positive individuals

Extended Application of Digital Clock Drawing Test in the Evaluation of Alzheimer's Disease Based on Artificial Intelligence and the Neural Basis.

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. 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. 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. 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.

Comparison of time spent and score in digital recognition test and free recall tests in the identification of mild cognitive impairment and Alzheimer disease

AbstractBackgroundDigital memory tests are proposed for the screening of mild cognitive impairment (MCI) and Alzheimer disease (AD). However, previous studies are seldom measuring the time spent of a participant in a memory test. So, it is unclear whether the time spent in a digital memory test can be a predictive factor for the identification of MCI and AD. The objective of this study is to evaluate the diagnostic performance of the digital recognition test, immediate and delayed free recall test in the identification of MCI and AD.MethodsA digital test platform included a recognition test, an immediate and a delayed free recall test was developed. The score and time spent (from participant start to answer the question to finish answering the question) of each memory test were measured. Participants with MCI and AD were consecutive patients in clinics, the controls were recruited from a community elderly center. Regression derived score was calculated using binary logistic regression. Receiver operating characteristic (ROC) curves were used to examine the ability of the memory tests to identify MCI and AD from controls. The area under the curve (AUC) was calculated.ResultsA total of 46 controls, 37 MCI, and 37 AD participants were recruited. In the digital recognition test, the controls had significantly shorter time spent than the MCI participants (mean difference (MD)=‐12.3 seconds, SD=3.64, p=0.001) and MCI participants had significantly shorter time spent than AD participants (MD=‐15.6, SD=6.1, p=0.01). However, no difference in time spent between 3 groups of participants was found in the immediate and delayed free recall test. In the identification of MCI and AD from control, the AUC of time spent and score in digital recognition test were 0.74 and 0.76, respectively. The AUC of regression derived score with taking time spent and the score was 0.85. The AUCs of immediate and delayed free recall tests were 0.71 and 0.76, respectively.ConclusionsThis study showed that both score and time spent in the digital recognition test are predictive factors for the identification of MCI and AD. A combination of score and time spent can enhance the performance of the digital recognition test.

Comparing drawing under instructions with image copying for mild cognitive impairment (MCI) or dementia screening: A meta‐analysis of 92 diagnostic studies

AbstractBackgroundDrawing is a major component of cognitive screening for dementia. It can be performed without language restriction. Drawing pictures under instructions and copying images are different screening approaches. The objective of this study was to compare the diagnostic performance between drawing under instructions and image copying for MCI and dementia screening.MethodA literature search was carried out in the OVID databases with keywords related to drawing for cognitive screening. Study quality and risk of bias were assessed by QUADAS‐2. The level of diagnostic accuracy across different drawing tests were pooled by bivariate analysis in a random effects model. Summary estimates of sensitivity and specificity with 95% CI and prediction region were presented in a hierarchical summary receiver operating characteristic (HSROC) curve. The area under the hierarchical summary receiver‐operating characteristic curve (AUC) was constructed to summarize the diagnostic performance.ResultNinety‐two studies with sample size of 22,085 were included. The pooled results for drawing under instructions showed a sensitivity of 79% (95% CI: 76 – 83%) and a specificity of 80% (95% CI: 77 – 83%) with AUC of 0.87 (95% CI: 0.83 – 0.89). The pooled results for image copying showed a sensitivity of 71% (95% CI: 62 – 79%) and a specificity of 83% (95% CI: 72 – 90%) with AUC of 0.83 (95% CI: 0.80 – 0.86) (Fig. 1). Subgroup analysis for the diagnostic accuracy for MCI and dementia showed that both drawing under instructions and image copying have better diagnostic performance for patients with dementia. The AUC of drawing under instructions and image copying for patients with dementia were 0.88 (95% CI: 0.85 – 0.91) and 0.85 (95% CI: 0.82 – 0.88) and the AUC for patients with MCI were 0.77 (0.73 – 0.80) and 0.73 (95% CI: 0.69 – 0.77), respectively. Most of the studies used clock‐drawing test as the screening test.ConclusionDrawing under instructions showed a similar diagnostic performance when compared with image copying for cognitive screening and the administration of image copying is relatively simpler. Self‐screening for dementia is feasible to be done at home in the near future.