Detection Of Dementia Research Articles

MRI-Driven Alzheimer’s Disease Diagnosis Using Deep Network Fusion and Optimal Selection of Feature

Alzheimer’s disease (AD) is a degenerative neurological condition characterized by cognitive decline, memory loss, and reduced everyday function, which eventually causes dementia. Symptoms develop years after the disease begins, making early detection difficult. While AD remains incurable, timely detection and prompt treatment can substantially slow its progression. This study presented a framework for automated AD detection using brain MRIs. Firstly, the deep network information (i.e., features) were extracted using various deep-learning networks. The information extracted from the best deep networks (EfficientNet-b0 and MobileNet-v2) were merged using the canonical correlation approach (CCA). The CCA-based fused features resulted in an enhanced classification performance of 94.7% with a large feature vector size (i.e., 2532). To remove the redundant features from the CCA-based fused feature vector, the binary-enhanced WOA was utilized for optimal feature selection, which yielded an average accuracy of 98.12 ± 0.52 (mean ± standard deviation) with only 953 features. The results were compared with other optimal feature selection techniques, showing that the binary-enhanced WOA results are statistically significant (p < 0.01). The ablation study was also performed to show the significance of each step of the proposed methodology. Furthermore, the comparison shows the superiority and high classification performance of the proposed automated AD detection approach, suggesting that the hybrid approach may help doctors with dementia detection and staging.

Early detection of dementia through retinal imaging and trustworthy AI

Alzheimer’s disease (AD) is a global healthcare challenge lacking a simple and affordable detection method. We propose a novel deep learning framework, Eye-AD, to detect Early-onset Alzheimer’s Disease (EOAD) and Mild Cognitive Impairment (MCI) using OCTA images of retinal microvasculature and choriocapillaris. Eye-AD employs a multilevel graph representation to analyze intra- and inter-instance relationships in retinal layers. Using 5751 OCTA images from 1671 participants in a multi-center study, our model demonstrated superior performance in EOAD (internal data: AUC = 0.9355, external data: AUC = 0.9007) and MCI detection (internal data: AUC = 0.8630, external data: AUC = 0.8037). Furthermore, we explored the associations between retinal structural biomarkers in OCTA images and EOAD/MCI, and the results align well with the conclusions drawn from our deep learning interpretability analysis. Our findings provide further evidence that retinal OCTA imaging, coupled with artificial intelligence, will serve as a rapid, noninvasive, and affordable dementia detection.

Using Deep Learning Neural Networks to Improve Dementia Detection: Automating Coding of the Clock-Drawing Test.

Alzheimer's disease and related dementias (ADRD) is a growing public health concern. The clock-drawing test (CDT), where subjects draw a clock, typically with hands showing 11:10, has been widely used for ADRD-screening. A limitation of including CDT in large-scale studies is that the CDT requires manual coding, which could result in biases if coders interpret and implement coding rules differently. This study created and evaluated an intelligent CDT Clock Scoring system built with Deep Learning Neural Networks (DLNN) to automatically code CDT images. We used a large, publicly available repository of CDT images from the 2011-2019 National Health and Aging Trends Study (NHATS) and compared three advanced DLNN methods - ResNet101, EfficientNet and Vision Transformers (ViT) in coding CDT into binary and ordinal (0 to 5) scores. We extended beyond the traditional nominal classification approach (which does not recognize order) by introducing structured ordering into the coding system and compared DLNN-coded CDT images with manual coding. Results suggest that ViT outperforms ResNet101 and EfficientNet, as well as manual coding. The ordinal coding system has the ability to allow researchers to minimize either under- or over-estimation errors. Starting in 2022, our developed ViT-coding system has been used in NHATS' annual CDT-coding.

Validation and comparison of virtual reality and 3D mobile games for cognitive assessment against ACE-III in 82 young participants

Current medical and clinical ecosystem for dementia detection is inadequate for its early detection. Traditional cognitive assessments are introduced after cognitive impairment has begun to disrupt the real-world functioning of the person. Moreover, these tools are paper-pen based and fail to replicate the real-world situations wherein the person ultimately lives, acts and grows. The lack of tools for early detection of dementia, combined with absence of reliable pharmacological cure compound the problems associated with dementia diagnosis and care. Advancement of technology has facilitated early prediction of disease like cancer, diabetes, heart disease, but hardly any such translation has been observed for dementia or cognitive impairment. Given this background, we examine the potential of Virtual Reality (VR) and 3D Mobile-based goal-oriented games for cognitive assessment. We evaluate three games (2 in VR, one in mobile) among 82 young participants (aged 18–28 years) and compare and contrast the game-based results with their Addenbrooke Cognitive Examination (ACE-III) scores. Three main analysis methods are used: Correlative, Z-score and Regression analysis. Positive correlation was observed for ACE-III and game-based scores. Z-scores analysis revealed no difference between the two scores, and stronger statistical significance was found between game scores and cognitive health factors like age, smoking compared to ACE-III. Specific game performances also revealed about real-world traits of participants, like hand-use confusion and direction confusion. Results establish the plausibility of using goal-oriented games for more granular, time-based, and functional cognitive assessment.

Multicenter Validation of the English Version of the Dépistage Cognitif de Québec: a Cognitive Screening Tool for Atypical Dementias.

Early detection of atypical dementia remains difficult partly because of the absence of specific cognitive screening tools. This creates undue delays in diagnosis and management. The Dépistage Cognitif de Québec (DCQ; dcqtest.org) was developed in French and later validated in participants with atypical syndromes. We report the validation of the English version. This multicentre prospective validation study was conducted in 10 centers across Canada and the United States on 260 English-speaking participants aged over 50. We translated and modified the original French DCQ to add targeted stimuli to the Visusopatial Index and social cognition vignettes to the Behavioral Index. A backward translation was performed and equivalence between languages was assessed by administering both tests to 30 bilingual participants. Mean DCQ total score (out of 100) was 95.0 (SD = 3.6). Spearman's correlation coefficient showed a strong and significant correlation (r = 0.49, p < .001) with the Montreal Cognitive Assessment. Test-retest reliability was good (Spearman's coefficient = 0.72, p < .001) and interrater reliability, excellent (intraclass correlation = 0.97, p < .001). Normative data shown in percentiles were stratified by age and education for a population-based sample of 260 English-speaking controls aged between 50 and 87years old. Similar to the French version, the English DCQ proved to be a valid cognitive screening test. The original version was very sensitive to detect atypical dementias such as primary progressive aphasias, Alzheimer's disease' variants and syndromes along the frontotemporolobar degeneration spectrum. This 20-min test can be administered à la carte and offers an alternative to detailed comprehensive neuropsychological evaluations.

Maximizing Early Dementia Detection Through Medicare Annual Wellness Visits

Maximizing Early Dementia Detection Through Medicare Annual Wellness Visits

The Impact of Pause and Filler Word Encoding on Dementia Detection with Contrastive Learning

Dementia is primarily caused by neurodegenerative diseases like Alzheimer’s disease (AD). It affects millions worldwide, making detection and monitoring crucial. This study focuses on the detection of dementia from speech transcripts of controls and dementia groups. We propose encoding in-text pauses and filler words (e.g., “uh” and “um”) in text-based language models and thoroughly evaluating their impact on performance (e.g., accuracy). Additionally, we suggest using contrastive learning to improve performance in a multi-task framework. Our results demonstrate the effectiveness of our approaches in enhancing the model’s performance, achieving 87% accuracy and an 86% f1-score. Compared to the state of the art, our approach has similar performance despite having significantly fewer parameters. This highlights the importance of pause and filler word encoding on the detection of dementia.

Gender differences in neurocognitive assessments: insights from apilot study with the International Neurocognitive Test Profile (INCP) digital battery.

The aging global population has led to an increase in the number of dementia diagnoses, with projections indicating acontinued upward trend. This demographic change presents profound challenges for patients, their families, and healthcare systems worldwide. Consequently, the demand for reliable and user-friendly screening tools that can detect dementia at early stages and monitor its progression is more critical than ever. The International Neurocognitive Test Profile (INCP), developed at the Medical University of Vienna, aims to address this need by offering adigital test battery for the early detection of dementia. This study forms apart of the INCP's ongoing development and evaluation, specifically investigating the influence of gender on test outcomes. Seventy participants, recruited through flyers at the Vienna General Hospital, completed the INCP assessment using tablets as part of the study. The effect of gender on performance across various INCP subtests was analyzed using Mann-WhitneyU tests. For further exploratory analysis, acorrelation matrix was calculated encompassing demographic variables (age and education), screening data, and all INCP subtests. The analysis revealed significant gender differences in two INCP subtests related to executive functions. Males outperformed females on the Figure Fluency Test (r = 0.30, indicating amoderate effect) and the Dice 2‑n Back Test (r = 0.29, indicating asmall effect). However, when correcting for multiple comparisons, no significant gender disparities were observed in the scores of the subtests. The identification of possible gender differences in specific subtests underscores the importance of considering gender as avariable in the further development and evaluation of the INCP. These findings offer valuable insights for the design and planning of future studies involving the INCP.

Subjective cognitive and olfactory impairments predict different prospective dementia outcomes.

Self-reported measures emerge as potential indicators for early detection of dementia and mortality. We investigated the predictive value of different self-reported measures, including subjective cognitive decline (SCD), subjective olfactory impairment (SOI), subjective taste impairment (STI), and self-reported poor health (SPH), in order to determine the risk of progressing to Alzheimer's disease (AD) dementia, Parkinson's disease (PD) dementia, or any-other-cause dementia. A total of 6,028 cognitively unimpaired individuals from the 8th wave of the English Longitudinal Study of Ageing (ELSA) were included as the baseline sample and 5,297 individuals from the 9th wave were included as 2-year follow-up sample. Self-rated measures were assessed using questions from the ELSA structured interview. Three logistic regression models were fitted to predict different the dementia outcomes. SCD based on memory complaints (OR = 11.145; P < 0.001), and older age (OR = 1.108, P < 0.001) significantly predicted the progression to AD dementia at follow-up. SOI (OR = 7.440; P < 0.001) and older age (OR = 1.065, P = 0.035) significantly predicted the progression to PD dementia at follow-up. Furthermore, SCD based on memory complaints (OR = 4.448; P < 0.001) jointly with complaints in other (non-memory) mental abilities (OR = 6.662; P < 0.001), and older age (OR = 1.147, P < 0.001) significantly predicted the progression to dementia of any other cause. Different types of complaints are specifically associated with different dementia outcomes. Our study demonstrates that self-reported measures are a useful and accessible tool when screening for individuals at risk of dementia in the general population.

Development of an AI-Based Predictive Algorithm for Early Diagnosis of High-Risk Dementia Groups among the Elderly: Utilizing Health Lifelog Data.

This study aimed to develop a predictive algorithm for the early diagnosis of dementia in the high-risk group of older adults using artificial intelligence technologies. The objective is to create an accessible diagnostic method that does not rely on traditional medical equipment, thereby improving the early detection and management of dementia. Lifelog data from wearable devices targeting this high-risk group were collected from the AI Hub platform. Various indicators from these data were analyzed to develop a dementia diagnostic model. Machine learning techniques such as Logistic Regression, Random Forest, LightGBM, and Support Vector Machine were employed. Data augmentation techniques were applied to address data imbalance, thereby enhancing the model performance. Data augmentation significantly improved the model's accuracy in classifying dementia cases. Specifically, in gait data, the SVM model performed with an accuracy of 0.879. In sleep data, a Logistic Regression was performed, yielding an accuracy of 0.818. This indicates that the lifelog data can effectively contribute to the early diagnosis of dementia, providing a practical solution that can be easily integrated into healthcare systems. This study demonstrates that lifelog data, which are easily collected in daily life, can significantly enhance the accessibility and efficiency of dementia diagnosis, aiding in the effective use of medical resources and potentially delaying disease progression.

A new test for evaluation of marginal cognitive function deficits in idiopathic normal pressure hydrocephalus through expressing texture recognition by sound symbolic words.

The number of dementia patients is increasing with population aging. Preclinical detection of dementia in patients is essential for access to adequate treatment. In previous studies, dementia patients showed texture recognition difficulties. Onomatopoeia or sound symbolic words (SSW) are intuitively associated with texture impressions and are less likely to be affected by aphasia and description of material perception can be easily obtained. In this study, we aimed to create a test of texture recognition ability expressed by SSW to detect the presence of mild cognitive disorders. The sound symbolic words texture recognition test (SSWTRT) is constructed from 12 close-up photos of various materials and participants were to choose the best SSW out of 8 choices to describe surface texture in the images in Japanese. All 102 participants seen in Juntendo University Hospital from January to August 2023 had a diagnosis of possible iNPH (age mean 77.9, SD 6.7). The answers were scored on a comprehensive scale of 0 to 1. Neuropsychological assessments included MMSE, FAB, and the Rey Auditory Verbal Learning Test (RAVLT), Pegboard Test, and Stroop Test from the EU-iNPH Grading Scale (GS). In study 1 the correlation between SSWTRT and the neuropsychological tests were analyzed. In study 2, participants were divided into two groups: the Normal Cognition group (Group A, n = 37) with MMSE scores of 28 points or above, and the Mild Cognitive Impairment group (Group B, n = 50) with scores ranging from 22 to 27 points, and its predictability were analyzed. In study 1, the total SSWTRT score had a moderate correlation with the neuropsychological test results. In study 2, there were significant differences in the SSWTRT scores between groups A and B. ROC analysis results showed that the SSWTR test was able to predict the difference between the normal and mildly impaired cognition groups. The developed SSWTRT reflects the assessment results of neuropsychological tests in cognitive deterioration and was able to detect early cognitive deficits. This test not only relates to visual perception but is likely to have an association with verbal fluency and memory ability, which are frontal lobe functions.

A novel integrated logistic regression model enhanced with recursive feature elimination and explainable artificial intelligence for dementia prediction

Dementia is a major global health issue that significantly impacts millions of individuals, families, and societies worldwide, creating a substantial burden on healthcare systems. This study introduces a novel approach for predicting dementia by employing the Logistic Regression (LR) model, enhanced with Recursive Feature Elimination (RFE), applied to a unique dataset comprising 1000 patients, with 49.60% male and 50.40% female. The LR model, recognized for its simplicity and effectiveness in binary classification tasks, is optimized through RFE, a technique that iteratively eliminates less significant features to improve model performance. The model’s effectiveness was assessed using comprehensive metrics, including accuracy, precision, recall, F1-score, Matthews Correlation Coefficient (MCC), and Kappa score. Furthermore, SHapley Additive exPlanations (SHAP) values were employed to increase the interpretability of the model, providing insights into the most influential features for dementia prediction. To address the issue of overfitting, a standardization technique was implemented, which enhanced the model’s predictive performance. The findings of this study hold potential implications for early dementia detection, informing intervention strategies, and optimizing healthcare resource allocation.

A - 4 The Potential Applications of Software Supporting the Early Detection of Cognitive Disorders and Dementia in Diagnostics and Prevention

Abstract Objective In Hungary, the process of diagnosing dementia is slow and time-consuming. Currently, there are no well-developed systems and strategies at the local level for screening, and there is no artificial intelligence algorithm that could determine early signs of dementia based on the patient’s digital behavioral patterns. Methods Two PILOTs were conducted using the PreDem platform. Over the PILOTs’ duration (2021.09.01.-2024.04.09), 61,902 test data were analyzed. The 259 participants completed SDMT-type tests, Stroop tests, and memory/word games. Results We established a unified system for task evaluation, facilitating cross-test result comparisons. Participants (n = 43,902) were grouped into three categories: 1st - presumed dementia patients (13,932), 2nd - diagnosed MS patients (16,175), and 3rd - presumably normal population (13,795). Comparing the first two groups to the normal population revealed significant differences, vividly illustrated by density functions. A key finding is the substantial improvement in individuals dealing with memory disorders and forgetfulness through regular cognitive game performance. Conclusion Study results reveal the PreDem platform’s potential as a valuable tool for early dementia detection and prevention. Combining cognitive tests and artificial intelligence, the platform can successfully identify early signs of dementia and cognitive impairment (90% accuracy), potentially leading to early diagnosis, treatment, and improved quality of life for patients and families.

Guardians of memory: The urgency of early dementia screening in an aging society.

The global aging population has led to a significant rise in the prevalence of age-related non-communicable diseases such as dementia and other cognitive disorders. In 2019, there were 57.4 million people with dementia worldwide, and this number is projected to triple by 2050. Intervening in and managing 12 potentially modifiable dementia risk factors can prevent or delay the onset and progression of about 40% of dementia cases. Neuroimaging, biomarkers, and advanced neuropsychological testing offer promising pathways for the early detection of dementia. Emphasis should be placed on educating the public about the importance of brain health and the early signs of cognitive impairment, as well as promoting dementia prevention measures. Adopting a healthy lifestyle - including a balanced diet, regular physical exercise, active social engagement, cognitive activities, and avoiding smoking and excessive alcohol consumption - can help reduce the risk of cognitive decline and prevent cognitive disorders. Government policies on dementia prevention and health care, along with early and regular dementia screening programs, can enhance the early identification and management of individuals at risk. In addition, integrating cognitive health assessments into routine medical check-ups is essential for the early screening and management of dementia.

Dementia diagnosis in young adults: a machine learning and optimization approach

AbstractIndividuals who are younger and have dementia often start experiencing its symptoms before they turn 65, with cases even documented in people as young as their thirties. Researchers strive for accurate dementia diagnosis to slow or halt its progression. This paper presents a novel Enhanced Dementia Detection and Classification Model (EDCM) comprised of four modules: data acquisition, preprocessing, hyperparameter optimization, and feature extraction/classification. Notably, the model uses texture information from segmented brain images for improved feature extraction, leading to significant gains in both binary and multi-class classification. This is achieved by selecting optimal features via a Gray Wolf Optimization (GWO)-driven enhancement model. Results demonstrate substantial accuracy improvements after optimization. For instance, using an Extra Tree Classifier for "normal" cases, the model achieves 85% accuracy before optimization. However, with GWO-optimized features and hyperparameters, the accuracy jumps to 97%.

Digital Cognitive Test for Early Detection of Dementia.

Dementia poses a significant global health problem, necessitating early detection for effective intervention. A literary review was conducted to examine current mobile-based cognitive tests. The limitations of the reviewed applications varied from accessibility to reliability. The paper addresses these limitations by proposing a digital, self-administered version of the Montreal Cognitive Assessment (MoCA) test, with future research focusing on validating the effectiveness of the proposed mobile application in early detection.

Neuropsychology and Politics Collide in the 2024 US Presdiential Election: Pitfalls of attacks on age, language, and memory.

Public perception of dementia has emerged as a key factor in the 2024 United States presidential election. The first televised presidential debate (27 June 2024) evoked a groundswell of concern about the neuropsychological health and political viability of President Joseph R. Biden, Jr. A rapid erosion of public support ensued, culminating in the collapse of the reelection campaign the following month. Political attacks on the cognitive fitness of world leaders create dissonance for clinical neuroscientists. We are ethically prohibited from remotely diagnosing public figures. Yet, we are also citizens with the right to feel and express personal concerns. In this commentary, I will address an often-uneasy relationship between politics and neuropsychology with a focus on the history and rationale for ethical guidelines such as the Goldwater Rule. I will also discuss lessons learned from recent events in the 2024 US election cycle about neurological health literacy (e.g. How is dementia diagnosed?) and broader impacts of age-based political attacks on global public health initiatives that target stigma reduction and improved early detection of dementia.

Fractal Dimension Distributions of Resting-State Electroencephalography (EEG) Improve Detection of Dementia and Alzheimer’s Disease Compared to Traditional Fractal Analysis

Fractal Dimension Distributions of Resting-State Electroencephalography (EEG) Improve Detection of Dementia and Alzheimer’s Disease Compared to Traditional Fractal Analysis

Editorial: Cognitive assessment in facilitating early detection of dementia

Editorial: Cognitive assessment in facilitating early detection of dementia

IBM Pelatihan Kader dalam Deteksi Dini Lansia dengan Demensia di Desa Deliksari, Gunungpati, Semarang

This research aims to develop a cadre training program in early detection of dementia in the elderly in Deliksari Village, Gunungpati, Semarang. Dementia is an increasingly urgent health problem in Indonesia, including in rural areas such as Deliksari Village. This program uses an educational approach and practical training to increase cadres' knowledge and skills in recognizing early signs of dementia. Training methods include the delivery of theory, case studies, and direct practice in identifying symptoms and behavior that indicate dementia. Program evaluation was carried out to measure the increase in cadres' knowledge and skills in carrying out early detection of dementia. It is hoped that the results of this research can contribute to efforts to prevent and early treat dementia at the rural community level