“Advances in biomarker discovery and diagnostics for alzheimer’s disease”

Neurological Sciences, Год журнала: 2025, Номер unknown

Опубликована: Фев. 1, 2025

Язык: Английский

---

Harnessing artificial intelligence in Alzheimer's disease management: navigating ethical challenges in AI

AI and Ethics, Год журнала: 2025, Номер unknown

Опубликована: Фев. 19, 2025

Язык: Английский

---

Biomarker Identification for Alzheimer’s Disease Using a Multi-Filter Gene Selection Approach

International Journal of Molecular Sciences, Год журнала: 2025, Номер 26(5), С. 1816 - 1816

Опубликована: Фев. 20, 2025

There is still a lack of effective therapies for Alzheimer's disease (AD), the leading cause dementia and cognitive decline. Identifying reliable biomarkers therapeutic targets crucial advancing AD research. In this study, we developed an aggregative multi-filter gene selection approach to identify biomarkers. This method integrates hub ranking techniques, such as degree bottleneck, with feature algorithms, including Random Forest Double Input Symmetrical Relevance, applies aggregation improve accuracy robustness. Five publicly available AD-related microarray datasets (GSE48350, GSE36980, GSE132903, GSE118553, GSE5281), covering diverse brain regions like hippocampus frontal cortex, were analyzed, yielding 803 overlapping differentially expressed genes from 464 492 normal cases. An independent dataset (GSE109887) was used external validation. The identified 50 prioritized genes, achieving AUC 86.8 in logistic regression on validation dataset, highlighting their predictive value. Pathway analysis revealed involvement critical biological processes synaptic vesicle cycles, neurodegeneration, function. These findings provide insights into potential AD.

Язык: Английский

---

Integrating NLP and LLMs to discover biomarkers and mechanisms in Alzheimer's disease

SLAS TECHNOLOGY, Год журнала: 2025, Номер unknown, С. 100257 - 100257

Опубликована: Фев. 1, 2025

Alzheimer's disease (AD) is a progressive neurological condition characterized by cognitive decline, memory loss, and aberrant behaviour. It affects millions of people globally one the main causes dementia. The neurodegenerative known as AD has intricate, multifaceted mechanisms that make it difficult to comprehend identify in its early stages. Conventional diagnostic techniques frequently fail detect By combining Natural Language Processing (NLP) Large Models (LLMs), this research suggests novel approach for identifying potential biomarkers underlying AD. Clinical data gathered from publicly accessible databases healthcare facilities, including genetic information, neuroimaging scans, medical records. pre-processing unstructured clinical notes involves tokenization profiles are normalized Z-score normalization consistency. Multi-Input Convolutional Neural Networks (MI-CNN) employed efficiently fuse diverse sources, allowing thorough analysis. Key linked identified categorized using Genetic Algorithm combined with Bidirectional Encoder Representations Transformers (BERT) (GenBERT). fine-tuning BERT's hyperparameters optimization approaches, GenBERT enables effective analysis large datasets, such patient histories, data, notes. combination strategy increases feature selection model's capacity minute genomic linguistic patterns suggestive goal integrated provide tools new insights into pathogenesis disease, which could transform methods detecting treating As concerns prediction, model performs better than current techniques, obtaining highest accuracy (98.30%) F1-score (0.97), well greater precision (0.95) recall (0.92). Additionally, demonstrates reliably both positive negative cases sensitivity (98.65%) specificity (99.73%). Overall, offers trustworthy useful tool diagnosis.

Язык: Английский

---

Cognitive performance classification of older patients using machine learning and electronic medical records

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 24, 2025

Dementia rates are projected to increase significantly by 2050, posing considerable challenges for healthcare systems worldwide. Developing efficient diagnostic tools is critical, and machine learning (ML) algorithms have shown potential improving the accuracy of cognitive impairment classification. This study aims address in current leveraging readily available electronic medical record (EMR) data simplify enhance classification impairment. The analysis includes 283 older adults, categorized into three groups: 144 individuals with mild (MCI), 38 dementia, 101 healthy controls. Various ML techniques evaluated classify performance levels based on input features such as sociodemographic variables, lab results, comorbidities, Body Mass Index (BMI), functional scales. Key predictors distinguishing controls from MCI identified. These history myocardial infarction, vitamin D3 levels, Instrumental Activities Daily Living (IADL) scale, age, sodium levels. nonlinear Support Vector Machine (SVM) a Radial Basis Function (RBF) kernel achieve best classification, an 69%, AUC 0.75, Matthews Correlation Coefficient (MCC) 0.43. For those most influential factors include IADL (ADL) education, age. Here, Random Forest algorithm demonstrates superior performance, achieving 84% accuracy, 0.96, MCC 0.71. two models consistently outperform other techniques, K-Nearest Neighbors, Multi-Layer Perceptron, linear SVM, Naive Bayes, Quadratic Discriminant Analysis, Linear AdaBoost, Gaussian Process Classifiers. findings suggest that EMR can be effective resource initial impairments. Integrating these ML-driven approaches primary care settings may facilitate early identification patients who could benefit further assessments.

Язык: Английский

---

Harnessing Artificial Intelligence in Early Detection and Diagnosis of Alzheimer's Disease: Current and Future Applications

Indus journal of bioscience research., Год журнала: 2025, Номер 3(2), С. 199 - 212

Опубликована: Фев. 25, 2025

Alzheimer's Disease (AD) is a neurodegenerative disorder requiring early detection. This study compares AI models—Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and Random Forest (RF)—in analyzing neuroimaging data (MRI, PET) to enhance AD prediction improve diagnosis using machine learning techniques. Through the application of multi-modal in form genetic, clinical, data, also investigates effectiveness combining different types predictability models for diagnosis. Feature importance analysis was performed methods like SHAP (SHAP (Shapley Additive Explanations) values determine most important variables model predictions, e.g., certain brain regions or genetic components. The generalizability real-world applicability by training on an independent dataset representing diverse clinical settings. performance each assessed variety statistical measures accuracy, precision, recall, F1-score, Area Under Curve (AUC). findings showed that CNN better compared SVM RF all metrics with highest accuracy (92%), precision (93%), recall (91%), AUC (0.95). suggest effectively detects subtle patterns, making it strong tool While well, superior accuracy. Cross-validation confirmed its generalizability, crucial use. Implementing models, especially CNN, may enable earlier detection, timely interventions, improved patient outcomes Alzheimer’s care. References

Язык: Английский

---

Fluid-based biomarkers for neurodegenerative diseases

Ageing Research Reviews, Год журнала: 2025, Номер unknown, С. 102739 - 102739

Опубликована: Март 1, 2025

Язык: Английский

---

AI-Derived Blood Biomarkers for Ovarian Cancer Diagnosis: Systematic Review and Meta-Analysis

Journal of Medical Internet Research, Год журнала: 2025, Номер 27, С. e67922 - e67922

Опубликована: Март 24, 2025

Background Emerging evidence underscores the potential application of artificial intelligence (AI) in discovering noninvasive blood biomarkers. However, diagnostic value AI-derived biomarkers for ovarian cancer (OC) remains inconsistent. Objective We aimed to evaluate research quality and validity AI-based OC diagnosis. Methods A systematic search was performed MEDLINE, Embase, IEEE Xplore, PubMed, Web Science, Cochrane Library databases. Studies examining accuracy AI were identified. The risk bias assessed using Quality Assessment Diagnostic Accuracy Studies–AI tool. Pooled sensitivity, specificity, area under curve (AUC) estimated a bivariate model meta-analysis. Results total 40 studies ultimately included. Most (n=31, 78%) included evaluated as low bias. Overall, pooled AUC 85% (95% CI 83%-87%), 91% 90%-92%), 0.95 0.92-0.96), respectively. For contingency tables with highest accuracy, 95% 90%-97%), 97% 95%-98%), 0.99 0.98-1.00), Stratification by algorithms revealed higher sensitivity specificity machine learning (sensitivity=85% specificity=92%) compared those deep (sensitivity=77% specificity=85%). In addition, serum reported substantially (94%) (96%) than plasma (sensitivity=83% specificity=91%). external validation demonstrated significantly (specificity=94%) without (specificity=89%), while reverse observed (74% vs 90%). No publication detected this Conclusions demonstrate satisfactory performance diagnosis are anticipated become an effective modality future, potentially avoiding unnecessary surgeries. Future is warranted incorporate into models, well prioritize adoption methodologies. Trial Registration PROSPERO CRD42023481232; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023481232

Язык: Английский

---

Blood biomarkers for clinical applications in Alzheimer's disease: A narrative review

NeuroMarkers., Год журнала: 2025, Номер 2(2), С. 100078 - 100078

Опубликована: Март 27, 2025

Язык: Английский

---

Predictive machine learning and multimodal data to develop highly sensitive, composite biomarkers of disease progression in Friedreich Ataxia

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Апрель 4, 2025

Friedreich Ataxia (FRDA) is a rare, inherited progressive movement disorder for which there currently no cure. The field urgently requires more sensitive, objective, and clinically relevant biomarkers to enhance the evaluation of treatment efficacy in clinical trials speed up process drug discovery. This study pioneers development relevant, multidomain, fully objective composite disease severity progression, using multimodal neuroimaging background data (i.e., demographic, history, genetics). Data from 31 individuals with FRDA controls longitudinal natural history IMAGE-FRDA, were included. Using an elasticnet predictive machine learning (ML) regression model, we derived weighted combination background, structural MRI, diffusion quantitative susceptibility imaging (QSM) measures that predicted Rating Scale (FARS) high accuracy (R² = 0.79, root mean square error (RMSE) 13.19). also exhibited strong sensitivity progression over two years (Cohen's d 1.12), outperforming FARS score alone (d 0.88). approach was validated Assessment (SARA), demonstrating potential robustness ML-derived composites surpass individual act as complementary or surrogate markers progression. However, further validation, refinement, integration additional modalities will open new opportunities translating these into practice FRDA, well other rare neurodegenerative diseases.

Язык: Английский

---