Andrew J. Saykin

The paper examines age-related variations in cortical thickness across different life stages using gene expression data from a large neuroimaging dataset.

The paper introduces SWAT-CNN, a deep learning method for identifying AD-associated SNPs and developing a classification model, achieving an AUC of 0.82.

The paper develops multi-task deep autoencoders to predict Alzheimer's disease progression using longitudinal DNA methylation data from peripheral blood and shows improved performance over existing methods.

The paper uses single nucleus RNA sequencing to analyze brain vascular cells in Alzheimer's disease, identifying molecular changes and interactions between vascular and astrocytic cells at the blood-brain barrier.

The paper performs genome-wide association analysis on Alzheimer's disease endophenotypes to identify main effects and stage-specific genetic interactions.

WEVar integrates functional scores from multiple methods to predict noncoding regulatory variants, outperforming existing approaches in simulation and empirical studies.

This paper develops a deep learning framework using tau PET scans to classify Alzheimer's disease and identifies key brain regions associated with the disease.

The paper identifies serum metabolites associated with brain amyloid-beta deposition, cognitive dysfunction, and progression to Alzheimer's disease.

The paper identifies cognitive subgroups in Alzheimer's disease based on MRI-derived atrophy patterns and links them to specific biological pathways using transcriptomic data.

The paper identifies a SHARPIN variant associated with limbic system atrophy and family history of Alzheimer’s disease using MRI and genome-wide data.

The paper identifies a functionally connected subnetwork of 276 multi-omic biomarkers for Alzheimer’s Disease using a modularity-constrained Lasso model applied to the ROS/MAP cohort.

This study identifies genetic variants and pathways associated with cognitive resilience to Alzheimer's disease, finding a novel locus linked to bile acid metabolism and methylation changes.

This study uses an epidemic spreading model to show that tau spreads through neuronal connections in Alzheimer's disease, with beta-amyloid accelerating this process in some brain regions.

The paper investigates the association between elevated plasma cortisol and brain volume changes in elderly cohorts, finding larger ventricles and smaller hippocampal volumes.

The paper investigates sex and APOE ε4 genotype effects on metabolic alterations in Alzheimer’s disease using stratified analysis of serum metabolites.

The paper integrates genomic and metabolomic data with biological networks to identify genetic variants and bile acids associated with Alzheimer's disease, revealing functional biological paths across multiple-omics layers.

The paper reports epigenome-wide meta-analyses of blood DNA methylation with subcortical brain volumes, identifying significant associations with hippocampal volume and potential biological mechanisms.

The paper develops a polygenic risk score integrating AD biomarkers and shows it better predicts cognitive decline than a clinical AD-based PRS.

The paper identifies differences in bile acid pathways for cholesterol clearance in Alzheimer’s disease by analyzing transcriptomes and metabolomics data from brain samples.

This study compares whole hippocampus and subfield biomarkers for Alzheimer’s disease detection and prediction using multimodal MRI data, finding subiculum biomarkers improve prediction accuracy.

The paper investigates the association between triglyceride principal component scores and Alzheimer's disease biomarkers in the ADNI cohort, finding significant links with MCI, AD, and specific brain structures.

This paper develops a blood-based machine learning model to predict cerebral spinal fluid Aβ1-42 levels, showing high accuracy in identifying Alzheimer's disease risk.

The paper identifies lipid sets in blood associated with Alzheimer's disease biomarkers and clinical symptoms using lipidomic profiling in the ADNI1 cohort.

The paper examines microglial activation in elderly brains, finding strong associations with neuropathology and cognitive decline, and identifies genetic overlaps with Alzheimer's disease.

The paper identifies genetic loci associated with cognitively-defined subgroups of late-onset Alzheimer’s disease using SNP data from multiple studies.

The paper identifies altered bile acid profiles in Alzheimer's disease, linking them to cognitive impairment and genetic variants through a large study.

The paper identifies associations between serum bile acid metabolites and AD biomarkers in the A/T/N framework, suggesting a potential role for bile acid pathways in AD pathophysiology.

This paper introduces SuStaIn, a machine learning method that identifies disease subtypes and their temporal progression from cross-sectional data, improving prediction of diagnostic conversion in neurodegenerative diseases.

The paper investigates how task-evoked functional connectivity differs from resting-state connectivity and finds that spontaneous networks, not task-evoked ones, mainly explain these differences.

The paper examines the heritability of regional brain volumes using genetic and neuroimaging data from multiple cohorts, finding high heritability and consistent patterns across populations.