Search Results (222)

Background: Wearable EEG devices offer an accessible and unobtrusive system for regular brain health monitoring outside clinical settings. However, due to the current lack of data available from wearable low-density EEG devices, we need to anticipate the extraction of biomarkers for brain health evaluation from available clinical datasets. Methods: This study evaluates multiclass dementia classification of Alzheimer’s disease, frontotemporal dementia, and healthy controls using features derived from low-density temporal EEG electrodes as a proxy for wearable EEG setups. The feature set comprises power-based metrics, including the 1/f spectral slope, and complexity metrics such as Hjorth parameters and multiscale sample entropy. Results: Our results show that multiclass differentiation of dementia, using low-density electrode configurations restricted to temporal regions, can achieve results comparable to a full-scalp configuration. Notably, electrode T5, positioned over the left temporo-posterior region, consistently outperformed other configurations, achieving a subject-level accuracy of 83.3% and an F1 score of 82.4%. Conclusions: These findings highlight the potential of single-site EEG measurement for wearable brain health devices. Full article

Accurate and robust classification of dementia subtypes using non-invasive electroencephalography (EEG) signals remains a critical challenge for clinicians and researchers in the field of neuroscience. Traditional methods often rely on limited spectral features, overlooking the rich structural and geometric information inherent in EEG dynamics. CONECT (Complex Network Conversion and Topology), a novel framework, is introduced and built upon four core innovations. First, EEG time series are transformed into weighted networks using a novel Angle-Relation Connection (ARC) rule, a geometry-based approach that links time points based on angular monotonicity. Secondly, a tunable edge-weighting function is introduced by integrating amplitude, temporal, and angular components, providing adaptable heuristics adaptable to the most promising biomarker, i.e., curvature-driven features in dementia. Additionally, two new graph-based EEG features, the Weighted Angular Irregularity Index (WAII) and the Curvature-Based Edge Feature Index (CBEFI), are proposed as potential biomarkers to capture localized irregularity and signal geometry, respectively. For the first time in a dementia EEG classification study using the OpenNeuro ds004504 dataset (raw), Ant Colony Optimization (ACO) is applied as a feature selection technique to select the most discriminative features and improve model classification and transparency. The classification results demonstrate CONECT’s potential as a promising, interpretable, and geometry-informed framework for accurate and practical dementia subtype diagnosis. Full article

This study explores the potential of accelerometer-based gait analysis as a non-invasive approach for predicting cognitive impairment in older adults. A total of 75 participants (61.3% female; mean age: 78.9 years), including cognitively normal individuals and patients with dementia, were enrolled. Walking data were collected using a six-axis waist-worn accelerometer during self-paced locomotion. Allan variance (AVAR), a robust statistical measure of frequency stability, was applied to characterize gait dynamics. AVAR-derived features, combined with participant age, were used as inputs to machine learning models, logistic regression and Light Gradient Boosting Machine (LightGBM) for classifying cognitive status based on Mini-Mental State Examination (MMSE) scores. LightGBM achieved superior performance (AUC = 0.92) compared to logistic regression (AUC = 0.85). Although mild cognitive impairment (MCI) cases were grouped with cognitively normal participants, gait-based classification revealed that MCI individuals exhibited patterns more similar to those with cognitive impairment. These results suggest that AVAR-based gait features are promising for early detection of cognitive decline in older adults. Full article

Introduction: In recent decades, the burden of mental disorders has become a major determinant of population health in the European Union, generating profound clinical, socioeconomic, and institutional consequences. Despite political recognition of this silent crisis, substantial methodological challenges persist in the transnational monitoring of mental health and in linking disease burden with the resources allocated to address it. The present analysis develops a multivariate taxonomy of EU Member States from a psychosocial perspective, using an integrative quantitative approach. Methods: This cross-sectional, comparative study follows international standards for transparent and reproducible quantitative reporting and is based on 18 harmonized clinical, epidemiological, and institutional indicators collected for 27 EU Member States over the period 2014–2023. The indicators used in this study were grouped according to their position along the care continuum. Hospital-based indicators refer to inpatient activity and institutional capacity, including total hospital discharges, psychiatric admissions (affective disorders, schizophrenia, dementia, alcohol- and drug-related disorders), and hospital bed availability. Outpatient and community-level indicators reflect the capacity of systems to provide non-hospital psychiatric care and consist primarily of psychiatrist density and total specialist medical workforce. Finally, subjective perception indicators capture population-level self-assessed health status, complementing clinical and institutional measures by integrating a psychosocial perspective. After harmonization and standardization, Principal Component Analysis (PCA) with Varimax rotation was applied to identify latent dimensions of mental health. Model adequacy was confirmed using the Kaiser–Meyer–Olkin coefficient (0.747) and Bartlett’s test of sphericity (p < 0.001). Results: Three latent dimensions explaining 77.7% of the total variance were identified: (1) institutionalized psychiatric burden, (2) functional capacity of the health care system, and (3) suicidal vulnerability associated with problematic substance use. Standardized factor scores allowed for the classification of Member States, revealing distinct patterns of psychosocial risk. For example, Germany and France display profiles marked by high levels of institutionalized psychiatric activity, while the Baltic and Southeast European countries exhibit elevated suicidal vulnerability in the context of limited medical resources. These results highlight the deep heterogeneity of psychiatric configurations in Europe and reveal persistent gaps between population needs and institutional response capacity. Conclusions: The analysis provides an empirical foundation for differentiated public policies aimed at prevention, early intervention, and stigma reduction. It also supports the case for institutionalizing a European mental health monitoring system based on harmonized indicators and common assessment standards. Overall, the findings clarify the underlying structure of mental health across the European Union and underscore the need for coherent, evidence-based strategies to reduce inequalities and strengthen system performance at the continental level. Full article

Diagnosis and prognosis of the amyotrophic lateral sclerosis and frontotemporal dementia (ALS/FTD) spectrum remain largely dependent on clinical assessments due to a lack of established fluid biomarkers. While neurofilaments and the cerebrospinal fluid (CSF) phosphorylated-tau/total-tau ratio (pTau:tTau) have been studied, their limitations, including their lack of clinical implementation and low specificity, necessitate multimodal approaches. This study aimed to characterize the biological features of the ALS/FTD spectrum through integration of clinically available parameters. We conducted a retrospective, single-center, cross-sectional study analyzing routinely collected clinical, neuroimaging, CSF, and serum data from 229 samples, including 45 from patients with ALS, 26 from patients with FTD, 158 from patients with other neurodegenerative diseases, and 29 from cognitively healthy controls. We implemented propensity score-weighted comparisons, an F1 score-based optimal cut-point determination for the pTau:tTau ratio, and a regularized XGBoost-based multimodal feature modeling approach. The biomarker and model performance was evaluated by the area under the precision–recall curve (AUC-PR). Feature importance analysis identified characteristic indicators of the ALS/FTD spectrum. Consistent with the prior literature, the pTau:tTau ratio was significantly reduced in ALS/FTD, but the classification performance was modest (AUC-PR 0.32). A multimodal model integrating clinical, biofluid, and neuroimaging features achieved a notably better performance (AUC-PR 0.75). Feature importance analysis revealed an ALS/FTD signature beyond the pTau:tTau ratio characterized by higher global cognition, younger age, an altered Aβ42/pTau ratio, and immunoglobulin changes (CSF IgG:IgA, serum IgG). Integration of clinical routine data centered on tau, amyloid, and immunological pathophysiology as well as temporal disease dynamics provide a contextualized biological characterization of the ALS/FTD spectrum. This approach offers a foundation for hypothesis generation regarding ALS/FTD pathophysiology and biomarker-supported diagnosis. Full article

Working memory is one of the most vulnerable cognitive domains in neurodegenerative diseases. According to the World Health Organization, around 55 million people worldwide were living with dementia in 2021, a number projected to exceed 150 million by 2050. Impairments in working memory occur in 80–90% of patients with Alzheimer’s disease, 40–60% with Parkinson’s disease, and about 50% with frontotemporal dementia. These deficits include reduced information capacity, slower response times, increased errors in manipulation, and difficulties in maintaining information, making them sensitive indicators of progressive decline. This review aims to systematize current approaches to modeling working memory phenotypes using electroencephalography (EEG). It highlights experimental paradigms applied to probe working memory, methods of EEG signal processing and analysis, and the integration of machine learning and neural network models. Particular emphasis is placed on studies achieving high diagnostic accuracy, with classification rates of 85–90% when distinguishing patients with neurodegeneration from healthy participants. Limitations of existing methods, especially EEG variability, are considered. The review concludes by outlining future directions: integration of multimodal EEG data, application of artificial intelligence, and development of digital cognitive biomarkers for hybrid models capable of predicting cognitive decline and advancing clinical translation. Full article

Early and accurate diagnosis of Alzheimer’s disease (AD) is critical for patient outcomes yet presents a significant clinical challenge. This study evaluates the effectiveness of four machine learning models—Logistic Regression, Random Forest, Support Vector Machine, and a Feed-Forward Neural Network—for the five-class classification of AD stages. We systematically compare model performance under two conditions, one including cognitive assessment data and one without, to quantify the diagnostic value of these functional tests. To ensure transparency, we use SHapley Additive exPlanations (SHAPs) to interpret the model predictions. Results show that the inclusion of cognitive data is paramount for accuracy. The RF model performed best, achieving an accuracy of 84.4% with cognitive data included. Without this, performance for all models dropped significantly. SHAP analysis revealed that in the presence of cognitive data, models primarily rely on functional scores like the Clinical Dementia Rating—Sum of Boxes. In their absence, models correctly identify key biological markers, including PET (positron emission tomography) imaging of amyloid burden (FBB, AV45) and hippocampal atrophy, as the next-best predictors. This work underscores the indispensable role of cognitive assessments in AD classification and demonstrates that explainable AI can validate model behavior against clinical knowledge, fostering trust in computational diagnostic tools. Full article

Research shows that individuals with heart failure are 60% more likely to develop dementia because of their shared metabolic risk factors. Developing a classification model to differentiate between these two conditions effectively is crucial for improving diagnostic accuracy, guiding clinical decision-making, and supporting timely interventions in older adults. This study proposes a novel method for dementia classification, distinguishing it from its common comorbidity, heart failure, using blood testing and personal data. A dataset comprising 11,124 imbalanced electronic health records of older adults from hospitals in Chiang Rai, Thailand, was utilized. Conditional tabular generative adversarial networks (CTGANs) were employed to generate synthetic data while preserving key statistical relationships, diversity, and distributions of the original dataset. Two groups of ensemble models were analyzed: the boosting group—extreme gradient boosting, light gradient boosting machine—and the bagging group—random forest and extra trees. Performance metrics, including accuracy, precision, recall, F1-score, and area under the receiver-operating characteristic curve were evaluated. Compared with the synthetic minority oversampling technique, CTGAN-based synthetic data generation significantly enhanced the performance of ensemble learning models in classifying dementia and heart failure. Full article

Background: Frailty is a multidimensional syndrome reflecting reduced physiological reserve, increasingly recognized as a relevant factor in the clinical assessment of older adults with cognitive disorders. Objective: To explore the association between frailty, as measured by the Multidimensional Prognostic Index (MPI), cognitive performance, and plasma biomarkers of Alzheimer’s disease (AD), and to examine the correlation between plasma and cerebrospinal fluid (CSF) biomarkers. Methods: This cross-sectional observational study included 40 patients (mean age 68.0 ± 9.0 years; 42.5% female) undergoing a diagnostic workup for cognitive decline. Patients were classified into AD (n = 20) and non-AD (n = 20) groups based on CSF AT[N] profiles. Frailty was assessed using the MPI. Linear and logistic regression models adjusted for age, sex, and education examined associations between MPI, cognitive scores, and plasma biomarkers (Aβ42, Aβ42/40, p-tau181, NfL). Correlations between plasma and CSF biomarkers and ROC analyses were also performed. Results: The AD group showed significantly higher plasma p-tau181 levels and MPI scores. MPI was positively associated with plasma p-tau181 levels (β = 4.26, p = 0.009). Plasma p-tau181 correlated strongly with CSF p-tau181 (R = 0.523, p < 0.001) and with CSF Aβ42/40 ratio (R = −0.541, p < 0.001) and showed high diagnostic accuracy (AUC = 0.910). Combining MPI with plasma biomarkers improved classification between AD and non-AD cases (AUC = 0.941). Conclusions: These findings support the value of incorporating frailty assessment in the diagnostic process of AD. The integration of geriatric tools and blood-based biomarkers may improve early detection and promote a more comprehensive approach in dementia evaluation. Full article

Alzheimer’s disease (AD) is the most prevalent form of dementia. This disease significantly impacts cognitive functions and daily activities. Early and accurate diagnosis of AD, including the preliminary stage of mild cognitive impairment (MCI), is critical for effective patient care and treatment development. Although advancements in deep learning (DL) and machine learning (ML) models improve diagnostic precision, the lack of large datasets limits further enhancements, necessitating the use of complementary data. Existing convolutional neural networks (CNNs) effectively process visual features but struggle to fuse multimodal data effectively for AD diagnosis. To address these challenges, we propose NeuroNet-AD, a novel multimodal CNN framework designed to enhance AD classifcation accuracy. NeuroNet-AD integrates Magnetic Resonance Imaging (MRI) images with clinical text-based metadata, including psychological test scores, demographic information, and genetic biomarkers. In NeuroNet-AD, we incorporate Convolutional Block Attention Modules (CBAMs) within the ResNet-18 backbone, enabling the model to focus on the most informative spatial and channel-wise features. We introduce an attention computation and multimodal fusion module, named Meta Guided Cross Attention (MGCA), which facilitates effective cross-modal alignment between images and meta-features through a multi-head attention mechanism. Additionally, we employ an ensemble-based feature selection strategy to identify the most discriminative features from the textual data, improving model generalization and performance. We evaluate NeuroNet-AD on the Alzheimer’s Disease Neuroimaging Initiative (ADNI1) dataset using subject-level 5-fold cross-validation and a held-out test set to ensure robustness. NeuroNet-AD achieved 98.68% accuracy in multiclass classification of normal control (NC), MCI, and AD and 99.13% accuracy in the binary setting (NC vs. AD) on the ADNI dataset, outperforming state-of-the-art models. External validation on the OASIS-3 dataset further confirmed the model’s generalization ability, achieving 94.10% accuracy in the multiclass setting and 98.67% accuracy in the binary setting, despite variations in demographics and acquisition protocols. Further extensive evaluation studies demonstrate the effectiveness of each component of NeuroNet-AD in improving the performance. Full article

Early and differential diagnosis of dementia is essential for timely and targeted care. This study investigated the feasibility of using an artificial intelligence (AI)-based system to discriminate between different stages and etiologies of dementia by analyzing facial emotions. We collected video recordings of 64 participants exposed to standardized audio-visual stimuli. Facial emotion features in terms of valence and arousal were extracted and used to train machine learning models on multiple classification tasks, including distinguishing individuals with mild cognitive impairment (MCI) and overt dementia from healthy controls (HCs) and differentiating Alzheimer’s disease (AD) from other types of cognitive impairment. Nested cross-validation was adopted to evaluate the performance of different tested models (K-Nearest Neighbors, Logistic Regression, and Support Vector Machine models) and optimize their hyperparameters. The system achieved a cross-validation accuracy of 76.0% for MCI vs. HCs, 73.6% for dementia vs. HCs, and 64.1% in the three-class classification (MCI vs. dementia vs. HCs). Among cognitively impaired individuals, a 75.4% accuracy was reached in distinguishing AD from other etiologies. These results demonstrated the potential of AI-driven facial emotion analysis as a non-invasive tool for early detection of cognitive impairment and for supporting differential diagnosis of AD in clinical settings. Full article

This study aims to explore the utility of artificial intelligence (AI) in classifying dementia severity based on gait analysis data and to examine how machine learning (ML) can address the limitations of conventional statistical approaches. The study included 34 individuals with mild cognitive impairment (MCI), 25 with mild dementia, 26 with moderate dementia, and 54 healthy controls. A support vector machine (SVM) classifier was employed to categorize dementia severity using gait parameters. As complexity and high dimensionality of gait data increase, traditional statistical methods may struggle to capture subtle patterns and interactions among variables. In contrast, ML techniques, including dimensionality reduction methods such as principal component analysis (PCA) and gradient-based feature selection, can effectively identify key gait features relevant to dementia severity classification. This study shows that ML can complement traditional statistical analyses by efficiently handling high-dimensional data and uncovering meaningful patterns that may be overlooked by conventional methods. Our findings highlight the promise of AI-based tools in advancing our understanding of gait characteristics in dementia and supporting the development of more accurate diagnostic models for complex or large datasets. Full article

Diagnosing dementia and recognizing substantial cognitive decline are challenging tasks. Thus, the objective of this study was to classify electroencephalograms (EEGs) recorded during a working memory task in 15 patients with mild cognitive impairment (MCogImp), 5 patients with vascular dementia (VasD), and 15 healthy controls (NC). Before creating spectrogram pictures from the EEG dataset, the data were subjected to preprocessing, which included preprocessing using conventional filters and the discrete wavelet transformation. The convolutional neural network (CNN) MobileNetV2 was employed in our investigation to identify features and assess the severity of dementia. The features were extracted from five layers of the MobileNetV2 CNN architecture—convolutional layers (‘Conv-1’), batch normalization (‘Conv-1-bn’), clipped ReLU (‘out-relu’), 2D Global Average Pooling (‘global-average-pooling2d1’), and fully connected (‘Logits’) layers. This was carried out to find the efficient features layer for dementia severity from EEGs. Feature extraction from MobileNetV2’s five layers was carried out using a decision tree (DT) and k-nearest neighbor (KNN) machine learning (ML) classifier, in conjunction with a MobileNetV2 deep learning (DL) network. The study’s findings show that the DT classifier performed best using features derived from MobileNetV2 with the 2D Global Average Pooling (global-average-pooling2d-1) layer, achieving an accuracy score of 95.9%. Second place went to the characteristics of the fully connected (Logits) layer, which achieved a score of 95.3%. The findings of this study endorse the utilization of deep processing algorithms, offering a viable approach for improving early dementia identification with high precision, hence facilitating the differentiation among NC individuals, VasD patients, and MCogImp patients. Full article

The development of positron emission tomography (PET) tracers targeting α-synuclein (α-syn) aggregates is critical for the early diagnosis, differential classification, and therapeutic monitoring of synucleinopathies such as Parkinson’s disease (PD), dementia with Lewy bodies (DLB), and multiple system atrophy. Despite recent advances, challenges including the low abundance of α-syn aggregates (10–50× lower than amyloid-beta (Aβ) or Tau), structural heterogeneity (e.g., flat fibrils in PD vs. cylindrical forms in DLB), co-pathology with Aβ/Tau, and poor metabolic stability have hindered PET tracer development for this target. To optimize our previously reported pyridothiophene-based radiotracer, [¹⁸F]asyn-44, we present the synthesis and evaluation of novel S,N-heterocyclic scaffold derivatives for α-syn. A library of 49 compounds was synthesized, with 8 potent derivatives (LMD-006, LMD-022, LMD-029, LMD-044, LMD-045, LMD-046, LMD-051, and LMD-052) demonstrating equilibrium inhibition constants (K_i) of 6–16 nM in PD brain homogenates, all of which are amenable for radiolabeling with fluorine-18. This work advances the molecular toolkit for synucleinopathies and provides a roadmap for overcoming barriers in PET tracer development, with lead compounds that can be considered for biomarker-guided clinical trials and targeted therapies. Full article

Dementia and heart failure are growing global health issues, exacerbated by aging populations and disparities in care access. Diagnosing these conditions often requires advanced equipment or tests with limited availability. A reliable tool distinguishing between the two conditions is essential, enabling more accurate diagnoses and reducing misclassifications and inappropriate referrals. This study proposes a novel measurement, the optimized weighted objective distance (OWOD), a modified version of the weighted objective distance, for the classification of dementia and heart failure. The OWOD is designed to enhance model generalization through a data-driven approach. By enhancing objective class generalization, applying multi-feature distance normalization, and identifying the most significant features for classification—together with newly integrated blood biomarker features—the OWOD could strengthen the classification of dementia and heart failure. A combination of risk factors and proposed blood biomarkers (derived from 10,000 electronic health records at Chiang Rai Prachanukroh Hospital, Chiang Rai, Thailand), comprising 20 features, demonstrated the best OWOD classification performance. For model evaluation, the proposed OWOD-based classification method attained an accuracy of 95.45%, a precision of 96.14%, a recall of 94.70%, an F1-score of 95.42%, and an area under the receiver operating characteristic curve of 97.10%, surpassing the results obtained using other machine learning-based classification models (gradient boosting, decision tree, neural network, and support vector machine). Full article