Dementia and Cognitive Impairment Research

The paper compares medial temporal lobe atrophy patterns in early-onset and late-onset amnestic Alzheimer's disease, finding similar atrophy levels but differences in specific subregions.

The paper investigates how APOE4 and infections together contribute to brain glucose hypometabolism, a marker of Alzheimer's pathology, using ADNI data.

This study evaluates digital cognitive assessments as low-burden tools for predicting cognitive decline and tau accumulation in Alzheimer's disease, finding they outperform Aβ and tau PET in detecting mild cognitive impairment and predicting decline.

This study uses cognitive modeling of the Mnemonic Similarity Task to detect early signs of Alzheimer's Disease before cognitive decline, showing better prediction of biomarkers than traditional metrics.

The paper examines how modifiable factors and genetic determinants interact with pathological load to influence tau pathology progression in Alzheimer's disease.

The paper develops a multivariate methylation risk score using blood DNA methylation data to predict dementia risk and cognitive impairment in Alzheimer's and Parkinson's disease cohorts.

The paper uses machine learning on multi-cohort transcriptomic and proteomic data to identify molecular subtypes of cognitive resilience in Alzheimer's disease and finds two major subgroups with distinct proteomic and neuroimaging features.

The paper introduces DunedinPACNI, a brain MRI-based aging measure that predicts dementia conversion, morbidity, and mortality.

This study explores cognitive tests sensitive to sleep quantity and early dementia-related cognitive changes in middle-aged and older adults.

This paper uses multi-sensory-evoked potentials and a support vector machine to classify aMCI with high accuracy, showing better performance when combining multiple modalities.

The paper investigates how peripheral insulin resistance affects cerebral glucose metabolism and working memory in healthy adults, finding greater impacts in younger adults.

This paper introduces a tensor kernel learning method to integrate multimodal data for Alzheimer's disease classification, achieving improved accuracy compared to single-modality approaches.

This paper evaluates CNN models for brain age prediction and dementia classification using diffusion MRI, showing improved performance after dataset harmonization across Indian and North American cohorts.

This paper compares deep learning models for predicting cognitive performance trajectories using real-world data and finds CNNs to be the most robust for pattern recognition and overfitting resistance.

The paper quantifies retinal perivascular amyloid plaque distribution in relation to cognitive performance, finding higher peri-arteriolar amyloid burden and correlations with cognitive decline.

ABRIM collects and shares MRI and behavioral data from 295 adults to study cognitive aging, focusing on brain connectivity, myelinization, iron content, and cognitive functions across the lifespan.

This study examines the association between terminally differentiated effector memory T cells (TEMRAs) and cognitive and AD-related biomarkers in an aging cohort, finding CD8+ TEMRAs correlate with neuroinflammation markers.

The paper examines the relationship between cardiometabolic factors, blood beta-amyloid, and white matter hyperintensities in dementia-free individuals with cognitive complaints, finding stronger associations with cardiometabolic markers.

This paper develops an AI-ensembled network to classify Alzheimer's disease stages and predict progression using MRI data from ADNI.

The paper examines amygdalar tau binding and connectivity in preclinical Alzheimer's disease, finding associations with anxiety symptoms.

This study finds reduced consciousness and arousal in mild cognitive impairment (MCI) using MEG biomarkers, with lower LZ complexity and higher TAR indicating decreased consciousness and increased drowsiness.

This study links cardiometabolic state, measured by an allostatic load index, with neurovascular burden and brain structure/function changes across age using EEG and MRI data.

PVTAD classifies Alzheimer's disease and cognitively normal cases using a pyramid vision transformer on white matter MRI data, achieving 97.7% accuracy.

This study investigates rich club alterations in Alzheimer's Disease and Mild Cognitive Impairment using multimodal imaging, finding accelerated gray matter atrophy and increased amyloid deposition in rich club regions.

This paper develops AITeQ, a machine learning framework for Alzheimer's disease prediction using a 5-gene signature identified from RNA-Seq data.

This study finds that frontotemporal dementia patients show higher delay discounting, linked to impulsivity symptoms and pulvinar atrophy.

This study shows that poor cerebrovascular health slows processing speed through anterior white matter changes in middle-aged adults, with effects specific to cognition and risk factor duration.

The paper identifies brain structure signatures linked to Alzheimer's genetic risk across disease stages using compositional data analysis.