Search Results (399)

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

¹⁸F-Florbetapir PET imaging is widely used to assess amyloid-β (Aβ) burden in the brain, particularly in the context of Alzheimer’s disease (AD). Conventional assessments typically rely on selected individual slices, which may limit spatial accuracy and are prone to image blurring. In the present study, we introduce novel techniques to enhance the spatial resolution and clarity of Aβ signal visualization in individuals pretreated with ¹⁸F-florbetapir. PET scans were retrospectively obtained from the Imaging and Data Archive for twelve individuals, including six cognitively unimpaired subjects and six diagnosed with AD. Each dataset consisted of 346 raw images, comprising 90 axial, 128 coronal, and 128 sagittal slices. Images were reconstructed into a single 3D volume using the 3D Slicer platform. Crucially, we applied artificial intelligence or AI-driven signal enhancement techniques to suppress background noise and amplify Aβ signals. This AI-enhanced processing improved image clarity and enabled visualization of subtle and spatially organized signal patterns. To verify anatomical location, Aβ PET signals were registered with MRI. This integrated workflow allowed us to visualize Aβ signals across regions of interest, including the brain parenchyma, skull, and cervical tissues. Our analytical approaches revealed that Aβ signals are highly concentrated and confined within non-CNS fluid compartments, forming canal-like networks that extend from the brain parenchyma toward the skull base, particularly the occipital clivus, and connect to the cervical lymph nodes. Additional Aβ signals were observed along the internal carotid plexus. These findings suggest that, when reconstruction in 3D and enhanced with AI, ¹⁸F-florbetapir PET imaging may not only reflect Aβ plaque burden in the brain but also visualize soluble Aβ species concentrated within anatomical clearance pathways leading to the peripheral lymphatic system. This approach offers a new dimension to PET signal interpretation and highlights the potential of AI-enhanced 3D in advancing neuroimaging analysis. Full article

Background: Alzheimer’s disease (AD) remains the leading cause of dementia worldwide, with anti-amyloid monoclonal antibodies (MABs) marking a significant advance as the first disease-modifying therapies. Their use, however, is limited by amyloid-related imaging abnormalities (ARIA), which appear as vasogenic edema or effusion (ARIA-E) and hemosiderin-related changes (ARIA-H) on MRI. Variability in imaging protocols, subtle early findings, and the lack of standardized risk models challenge detection and management. Methods: This narrative review summarizes current artificial intelligence (AI) applications for ARIA detection and risk prediction. A comprehensive literature search across PubMed, Embase, and Scopus identified studies focusing on MRI-based AI analysis, lesion quantification, and predictive modeling. Results: The evidence is organized into six thematic domains: ARIA definitions, imaging challenges, foundations of AI in neuroimaging, detection tools, predictive frameworks, and future perspectives. Conclusions: AI offers promising avenues to standardize ARIA evaluation, improve lesion quantification, and enable individualized risk prediction. Progress will depend on multicenter datasets, shared frameworks, and prospective validation. Ultimately, AI-driven neuroimaging may transform how treatment-related complications are monitored in the era of anti-amyloid therapy. Full article

Background: Amyloid positron emission tomography (PET) has been proposed as a tool to monitor myelination in multiple sclerosis (MS). We present baseline results from an ongoing prospective study, which is the first to include both early and standard phases of amyloid PET in patients with newly diagnosed MS. Methods: The prospective study includes patients with newly diagnosed MS (January 2023–February 2024). Clinical evaluation includes neurological disability (EDSS) and neuropsychological assessment. Brain MRI, early [¹⁸F]florbetaben (FBB) PET (eFBB; 0–5, 0–10 min post-injection), and standard FBB PET (sFBB; 90 min post-injection) were acquired. Normal-appearing white matter (NAWM) and damaged white matter (DWM) in MRI were segmented and co-registered with PET images. Results are presented as standardized uptake values (SUV), with the ratio using cerebellum as the reference region (SUVR) and the percentage of change between the DWM and NAWM. Results: Twenty patients were included (35.05 ± 10.72 years; 75% women). Both eFBB and sFBB acquisitions showed significantly lower SUVRmax and SUVRmean, and higher SUVRmin in the DWM compared to NAWM (p < 0.001) in all patients. SUV parameters in both DWM and NAWM from eFBB and sFBB PET correlated with the number of relapses and EDSS (r = −0.454 and r = −0.446, respectively; p < 0.05). Additionally, SUVR values in the DWM during eFBB correlated with cognitive impairment (SDMT; r = −0.516, p < 0.01), fatigue (MFIS-5; r = −0.450, p < 0.05), and quality of life (EQ-5D; r = −0.490, p < 0.05). Conclusions: Quantitative analysis of dual-phase FBB PET demonstrates differential uptake between DWM and NAWM, which is probably associated with demyelination and neurodegeneration. These preliminary findings suggest that amyloid PET may have predictive value for disease activity and progression, supporting its potential as a biomarker in MS. Follow-up data from this study are needed to support the baseline results. Full article

The identification of brain clearance failure as a precursor to a large variety of neurodegenerative diseases has shifted fluid dynamics from a secondary to a tertiary target of brain health. The identification of the glymphatic system, detailing cerebrospinal fluid entry along perivascular spaces and exit via perivenous and meningeal lymphatic pathways, provided a challenge to previous diffusion models and established aquaporin-4–dependent astroglial polarity as a governing principle of solute transport. Multiple lines of evidence now support a coupled glymphatic–venous axis, wherein vasomotion, venous outflow, and lymphatic drainage are functionally interrelated. Failure of any axis will cascade and affect the entire axis, linking venous congestion, aquaporin-4 disassembly, and meningeal lymphatic failure to protein aggregation, neuroinflammation, edema, and intracranial hypertension. Specific lines of evidence from diffusion tensor imaging along vascular spaces, clearance MRI, and multi-omic biomarkers can provide a measure of transport. Therapeutic strategies are rapidly advancing from experimental strategies to translational approval, including behavioral optimization, closed-loop sleep stimulation, vascular and lymphatic therapies, focused ultrasound, pharmacological polarity recoupling, and regenerative bioengineering. Novel computational approaches, such as digital twin dynamic modeling and adaptive trial designs, suggest that clearance measures may serve as endpoints to be approved by the FDA. This review is intended to bridge relevant mechanistic and translational reviews, focusing on impaired clearance as an exploitable systems defect rather than an incapacitating secondary effect. Improving our understanding of the glymphatic-venous axis Injury may lead to future target strategies that advance cognitive resilience, alleviate disease burden, and improve quality of life. By clarifying the glymphatic–venous axis, we provide a mechanistic link between impaired interstitial clearance and the pathological accumulation of amyloid-β, tau, and α-synuclein in neurodegenerative diseases. The repair of aquaporin-4 polarity, venous compliance, and lymphatic drainage might therefore open new avenues for the diagnosis and treatment of Alzheimer’s and Parkinson’s disease, supplying both biomarkers of disease progression and new targets for early intervention. These translational implications not only locate clearance failure as an epiphenomenon of neurodegeneration but, more importantly, as a modifiable driver of the course of neurodegeneration. Full article

Background: Early diagnosis of Alzheimer’s disease (AD) is constrained by invasive and costly tests. Aggregation of $\beta$-amyloid and the A$\beta$42/A$\beta$40 ratio in cerebrospinal fluid (CSF) and blood are key biomarkers. Fluorescent probes can report aggregate states, and artificial intelligence (AI) can extract subtle patterns from spectral and blood data. This review synthesizes how probes and AI can identify aggregates and assess the A$\beta$42/A$\beta$40 ratio in body fluids to facilitate earlier AD diagnosis. Methods: PRISMA-compliant searches were conducted in Scopus, PubMed, Web of Science, and IEEE Xplore. Results: Twenty-eight studies met inclusion criteria. Plasma A$\beta$42/A$\beta$40 was lower in PET-positive individuals by ∼7–18%, with higher performance for mass spectrometry (mean AUC ≈ 0.80) than immunoassays (AUC ≈ 0.71). CSF A$\beta$42/A$\beta$40 showed larger group differences (∼50% reductions in PET+) and stronger PET concordance, outperforming plasma. Fluorescent probes—including AN-SP and CRANAD-28—were sensitive to early aggregates and showed in vivo imaging potential, but evidence is largely preclinical or from small cohorts. AI/ML approaches frequently achieved within-study accuracies >90% (e.g., 94–100% in spectral tasks), yet external validation and head-to-head tests of ratio alone versus ratio + AI remain scarce. Conclusions: Plasma A$\beta$42/40 —particularly by mass spectrometry—currently provides the most reproducible fluid approximation to amyloid PET (mean AUC ≈ 0.80). Fluorescent probes sensitively detect oligomeric A$\beta$ species and show in vivo potential, but evidence remains largely preclinical or from small cohorts. AI/ML methods can extract additional signal from spectral and multivariate blood data, yet consistent incremental gains over optimized Aβ42/40 assays have not been demonstrated due to limited external validation and head-to-head comparisons. Full article

Alzheimer’s disease accounts for approximately 50% to 80% of all causes of dementia. Co-existence of AD with other diseases causing dementia poses a diagnostic challenge, as we are still far from diagnosing AD accurately in order to manage it appropriately. Neuroimaging techniques, not only help diagnose AD but also consistently feature in diagnostic and research criteria for AD as biomarkers. Molecular biomarkers including positron emission tomography (PET) and single-photon emission computed tomography (SPECT), and structural biomarkers including magnetic resonance imaging (MRI), have been used in various therapeutic and prognostic studies in AD. This review highlights the recent advances in neuroimaging biomarkers, including molecular biomarkers (PET and SPECT tracers) and structural biomarkers (MRI), for AD. For the purpose of this review, molecular biomarkers have been further subcategorized into non-specific radiotracers (FDG-PET and blood flow SPECT) and specific amyloid- and tau-related radiotracers. The aim of this review is to discuss the recent advances and evidence of molecular and structural biomarkers of AD. Full article

Background: attention-deficit/hyperactivity disorder (ADHD) and Alzheimer’s disease (AD) are distinct neurological conditions that may share genetic and molecular underpinnings. ADHD, a neurodevelopmental disorder, affects approximately 5% of children and 3% of adults globally, while AD, a neurodegenerative disorder, is the leading cause of dementia in older adults. Emerging evidence suggests potential overlapping contributors, including pathways related to synaptic plasticity, neuroinflammation, and oxidative stress. Methods: this systematic review investigated potential genetic predispositions linking Attention-Deficit/Hyperactivity Disorder (ADHD) and Alzheimer’s Disease (AD). Following PRISMA guidelines, a search was conducted in Web of Science, Embase, PsycINFO, and PubMed using keywords related to ADHD, AD, and genetic factors. Studies included were original human studies utilizing genetic analyses and ADHD polygenic risk scores (PRS), with AD confirmed using established diagnostic criteria. Exclusion criteria comprised non-original studies, animal research, and articles not addressing genetic links between ADHD and AD. Screening was conducted with Rayyan software (version 1.4.3), assessing relevance based on titles, abstracts, and full texts. Results:. The search identified 1450 records, of which 1092 were screened after duplicates were removed. Following exclusions, two studies met inclusion criteria. One study analyzed ADHD-PRS in 212 cognitively unimpaired older adults using amyloid-beta (Aβ) PET imaging and tau biomarkers. The findings revealed that ADHD-PRS was associated with progressive cognitive decline, increased tau pathology, and frontoparietal atrophy in Aβ-positive individuals, suggesting that ADHD genetic liability may exacerbate AD pathology. Another study assessed ADHD-PRS in a cohort of 10,645 Swedish twins, examining its association with 16 somatic conditions. The results showed modest risk increases for cardiometabolic, autoimmune, and neurological conditions, with mediation effects through BMI, education, tobacco use, and alcohol misuse, but no direct link between ADHD-PRS and dementia. Discussion and conclusions: this review highlights preliminary but conflicting evidence for a genetic intersection between ADHD and AD. One study suggests that ADHD genetic liability may exacerbate AD-related pathology in Aβ-positive individuals, whereas another large registry-based study finds no direct link to dementia, with associations largely mediated by lifestyle factors. The potential ADHD–AD relationship is likely complex and context-dependent, influenced by biomarker status and environmental confounders. Longitudinal studies integrating genetics, biomarkers, and detailed lifestyle data are needed to clarify this relationship. Full article

Introduction: Genes in the endolysosome and autophagy pathways are major contributors to hereditary spastic paraplegia (HSP). A pathogenetic link between HSP and Alzheimer disease (AD) involving macroautophagy is well established. Sortilin-related receptor 1 (SORL1), an endosomal trafficking protein, plays a key role in glutamatergic neuron homeostasis and white matter tract integrity. Until now, SORL1 has only been associated with dominant AD and cerebral amyloid angiopathy. Methods: A case of HSP with cerebroretinal vasculopathy (CRV) negative on exome sequencing was further investigated using whole-genome sequencing. RNA-seq, Western blot, and immunofluorescence imaging were performed to explore a potential loss-of-function mechanism. Results: Sequencing revealed a biallelic SORL1 splice donor variant (c.1211 + 1G > A). Transcriptomics confirmed nonsense-mediated decay and aberrant splicing, predicting a disrupted reading frame. Reduced SORLA protein levels and significant enlargement of endolysosomes in patient-derived fibroblasts further cemented the pathogenicity of the variant. Conclusions: The probability that SORL1 acts as a recessive disease-causing gene gathers support from the following data: SORL1 genomic constraint score pRec = 1, high meiotic recombination rates on the locus, phenotype of Sorl1^−/− mice reminiscent of HSP with CRV, and endolysosomal enlargement in SORL1^−/− glutamatergic neurons in vitro. Taken together, SORL1 is probably a new candidate for a recessive form of complicated HSP. Full article

Anti-amyloid monoclonal antibodies have finally achieved their translational breakthrough after many years of unmet expectations. The FDA granted traditional approval to lecanemab in July 2023, and the European Medicines Agency approved it in late 2024 with specific genetic restrictions; meanwhile, donanemab received FDA approval in July 2024 and EMA marketing authorization just one month ago. These agents consistently clear cerebral amyloid and slow clinical decline modestly in early-stage, biomarker-confirmed Alzheimer’s disease (AD). On the other hand, they also create significant safety risks, including amyloid-related imaging abnormalities (ARIA) and substantial operational requirements for health systems that are already under pressure. Therefore, precise risk management based on APOE genotyping and the presence of cerebral amyloid angiopathy and cerebral microbleeds should be performed before therapy is initiated. The near-term agenda should prioritize the following areas of study: (1) biomarker-driven front-end triage (including emerging plasma assays); (2) ARIA-aware care pathways and shared decision making; (3) outcome-based coverage and rational pricing; (4) clinical trials that layer anti-amyloid therapy into combinatorial strategies targeting tau protein, neuroinflammation, and synaptic resilience. Full article

Alzheimer’s disease (AD) is the most common cause of dementia worldwide, and there are still no strategies to slow or prevent its clinical progression. Significant financial and research resources have been invested into studying the pathology of AD. However, its pathogenesis is not fully understood. This review provides a comprehensive analysis of current understanding of AD pathogenesis, including classical hypotheses (amyloid cascade, tau pathology, neuroinflammation, oxidative stress), emerging mechanisms (cellular senescence, endoplasmic reticulum stress, ubiquitin-proteasome system dysfunction), and alternative mechanisms (cholinergic dysfunction, glutamate excitotoxicity, disruption of the microbiota–gut–brain axis, and autophagy). Schematic illustrations summarize the relationships between the hypotheses and their role in the pathogenesis of AD. Particular attention is paid to the systematization of promising biological targets and the analysis of modern ligands of various nature, including small molecules, peptides, antibodies and their fragments, natural compounds, as well as innovative hybrid and multifunctional structures. A separate section is devoted to radiopharmaceuticals for PET imaging (Florbetaben, Flortaucipir, etc.) and promising therapeutic agents. Thus, in this review we (1) systematize modern concepts of AD pathogenesis, including classical, emerging mechanisms and alternative hypotheses; (2) conduct a comparative analysis of ligand classes (small molecules, peptides, antibodies, etc.) and their therapeutic potential; and (3) discuss the clinical prospects of radiopharmaceuticals for PET imaging and targeted therapy. The work provides a comprehensive analysis of modern approaches, which can help in the development of more effective drugs against AD. Full article

Autopsy studies have shown that Alzheimer’s disease (AD) often coexists with cerebrovascular injury, affecting cognitive outcomes and the effectiveness of anti-amyloid-beta (Aβ) drugs. No fluid biomarkers of cerebrovascular injury have been identified yet. We investigated the association between white matter hyperintensities (WMH) severity and fluid biomarkers, including cerebrospinal fluid (CSF) neurofilament light chain and plasma placental growth factor (PlGF) levels. This study included 242 patients from memory clinics. Magnetic resonance imaging (MRI), CSF, and plasma samples were collected. Patients were classified as AD+ or non-AD based on the CSF Aβ42/Aβ40 ratio. In the discovery cohort (79 AD+ and 20 non-AD patients with 3D-T1 images), we analyzed the association between WMH volume and plasma PlGF. In the validation cohort (54 AD+ patients without 3D-T1 images), we analyzed the association between WMH grading and plasma PlGF. Among AD+ patients in the discovery cohort, plasma PlGF levels remained significantly associated with WMH volume and grading after adjusting for age, sex, and global cognition. Among the AD+ patients in the validation cohort, the high-PlGF (above median) group had significantly greater WMH volumes and a higher number of patients with a high WMH grading than the low-PlGF (below median) group. Plasma PlGF is a promising marker of cerebrovascular injury in AD. Full article

The rapid advancements in computer processing, algorithmic development, and the availability of large-scale datasets have positioned Artificial Intelligence (AI) as a valuable tool across multiple domains, including Medicine. In the field of Nuclear Medicine neuroimaging, with Positron Emission Tomography (PET), AI has demonstrated significant potential in improving diagnostic accuracy for neurodegenerative cognitive disorders. This is especially relevant for the early diagnosis, preclinical detection, and prediction of disease progression in Alzheimer’s disease (AD), the most prevalent form of cognitive impairment in individuals over 65 years of age. This narrative review aims to synthesize current advances, explore future directions, and highlight outstanding challenges in the application of Artificial Intelligence to PET imaging for the clinical management of Alzheimer’s disease, with particular focus on three key modalities: ¹⁸F-FDG PET, Amyloid PET, and Tau PET. Full article

Alzheimer’s disease (AD) is the most common cause of dementia, pathologically defined by extracellular amyloid-β (Aβ) plaques and intracellular tau neurofibrillary tangles. Recent U.S. Food and Drug Administration (FDA) approvals of anti-amyloid monoclonal antibodies (mAbs) aducanumab, lecanemab, and donanemab represent the first disease-modifying therapies for early AD. These therapies have generated both optimism and controversy due to modest efficacy and safety concerns, particularly amyloid-related imaging abnormalities (ARIAs). This review synthesizes current evidence on the efficacy, safety, and biomarker-guided use of anti-Aβ mAbs in AD. Methods: We searched PubMed, Scopus, Web of Science, and Google Scholar to 31 July 2025 for studies on anti-amyloid mAbs in AD. Sources included peer-reviewed articles and regulatory reports. The extracted data covered study design, population, amyloid confirmation, dosing, outcomes, biomarkers, ARIA incidence, and management. Results: Anti-amyloid mAbs consistently demonstrated robust amyloid clearance and modest slowing of clinical decline in early symptomatic AD. Differences emerged across agents in efficacy signals, safety profiles, and regulatory outcomes. Lecanemab and donanemab showed more consistent cognitive benefits, while aducanumab yielded mixed findings, leading to its withdrawal. ARIAs were the most frequent adverse events, occurring more often in APOE ε4 carriers and typically during early treatment. Biomarker analyses also revealed favorable downstream effects, including reductions in phosphorylated tau and markers of astroglial injury, supporting engagement of disease biology. Conclusions: Anti-amyloid mAbs provide proof of concept for AD modification, with the greatest benefit in early disease stages and moderate tau burden. Optimal use requires biomarker confirmation of the amyloid, careful tau staging, and genetic risk assessment. While limitations remain, these therapies represent a pivotal step toward precision neurology and may serve as a foundation for multimodal strategies targeting tau, neuroinflammation, and vascular pathology. Full article

Background: Polybasic peptides are being developed as components of reagents for diagnosing and treating patients with systemic amyloidosis. In addition to fibrils, amyloid deposits ubiquitously contain heparan sulfate proteoglycans. We have hypothesized that pan amyloid-targeting peptides can specifically engage, in addition to fibrils, a subset of glycosaminoglycans (GAGs) with high negative charge density. In this study, we characterized the binding of peptides p5+14 (a PET imaging agent for amyloid [¹²⁴I-evuzamitide]) and p5R (a fusion protein used in the therapeutic AT-02) to GAGs. Methods: The peptide structure was evaluated in the presence of low molecular weight heparin using circular dichroism, and their interaction with synthetic GAGs of varying length and charge was interrogated. The binding patterns of p5+14 and p5R were compared using correlation analyses. Results: The peptides exist as mixed structural-fractions in solution but adopt an α-helical structure in the presence of heparin. Both peptides preferentially recognize heparin and heparan sulfate GAGs with a linear positive correlation between binding and the total charge and charge density. Conclusions: These peptides have previously been shown to specifically target amyloid deposits in vivo. A component of this specificity is their preferential interaction with a subset of heparan sulfate GAGs that have high charge density, potentially related to the degree of 6-O-sulfation. These data support the hypotheses that amyloid-associated GAGs have unique sulfation patterns, thereby explaining why these peptides do not bind GAGs found on the plasma membrane and extracellular matrix of healthy tissues. Full article