Christos A. Davatzikos

The paper introduces MIRTH, an imputation-based harmonization method that mitigates site effects in neuroimaging data without data leakage, achieving high predictive accuracy in machine learning studies.

The paper identifies two neuroanatomical subtypes of callous-unemotional traits using machine learning in a community sample of youth, showing distinct clinical and environmental profiles.

This study identifies genetic loci and pathways associated with limbic white matter microstructure in aging and Alzheimer's Disease using multi-cohort diffusion MRI and bulk RNA-seq data.

The paper develops and evaluates new batch effect correction methods for neuroimaging data that account for spatial correlations, showing improved performance over existing methods.

The paper uses machine learning to predict autopsy-confirmed neuropathology from clinical, neuroimaging, and CSF biomarkers, finding that different modalities best predict specific pathologies.

This study improves modeling of amyloid-β spread in Alzheimer's Disease using a gene-modulated network diffusion framework, showing better performance in correlation and replicability across cohorts.

The paper presents a curated dataset of processed diffusion MRI data from the ABCD Study, showing that specific diffusion metrics are sensitive to adolescent white matter development and robust to image quality variation.

This study identifies two axes of white matter development in human cortico-cortical tracts using diffusion MRI across three datasets, revealing non-uniform maturation patterns.

This study identifies subtypes of functional connectivity development in youth using fMRI data, revealing spatial patterns linked to cognitive performance and gene expression.

This paper links molecular mechanisms to Alzheimer's disease and aging by integrating neuroimaging endophenotypes with molecular quantitative trait loci.

This study introduces an interpretable predictive model to identify functional connectivity patterns predictive of cognitive traits in youth, showing improved accuracy and fine-grained characterization.

The paper introduces Reproducible Brain Charts (RBC), an open data resource integrating brain development data from 6,346 youth, showing the benefits of harmonized phenotypes and reproducible processing for studying psychopathology.

This paper demonstrates that real-time brain decoding using personalized functional networks enhances the effectiveness of transcranial magnetic stimulation for working memory.

This study addresses dementia classification bias across ethnic groups using few-shot learning and domain alignment, reducing performance gaps between White American and Hispanic cohorts.

The paper identifies nine neuroimaging endophenotypes linked to genetic loci and shows they improve prediction of systemic diseases and mortality.

The paper identifies robust sex differences in personalized functional brain network topography in youth, linked to X-linked genes and brain regions involved in psychiatric disorders.

This paper introduces a self-supervised deep learning framework to compute individualized multi-scale hierarchical functional networks from fMRI data and shows their association with biological phenotypes.

The paper develops organ-specific metabolome-based biological age gaps using UK Biobank data and links them to cardiometabolic conditions and mortality risk.

The paper uses tiled whole genome sequence data to identify genetic signatures associated with Alzheimer's disease using machine learning methods.

This study identifies 393 genomic loci associated with biological age gaps in nine human organ systems using UK Biobank data, revealing organ-specific and pleiotropic genetic effects.

This study identifies genetic subtypes of Alzheimer's Disease using cell-based gene networks and polygenic risk scores, then repositions existing drugs for AD treatment.

The paper uses GWAS summary statistics to analyze the genetic architecture of 2024 multi-organ AI endophenotypes, revealing genetic correlations and causal relationships across diseases.

The paper examines how sex, race, and APOE-ε4 allele status affect white matter microstructure across multiple aging and Alzheimer's disease cohorts.

pNet is an open-source toolbox for creating personalized functional networks from fMRI data, offering multiple interfaces and methods to enhance reliability and reproducibility.

This study identifies sixteen genome-wide significant loci associated with brain age gaps derived from MRI modalities and highlights potential causal relationships between brain aging and diseases.

This study identifies white matter fiber covariance networks in youth, showing their development aligns with executive function and hierarchical cortical maturation patterns.

This paper develops a self-supervised deep learning method to compute personalized brain functional networks from fMRI data, showing it can identify canonical networks and predict individual differences in behavior and schizophrenia status.

The paper identifies 617 novel genomic loci and pathways associated with structural covariance patterns in the human brain using a stochastic multivariate factorization method.

This paper develops an automated framework for analyzing low-field MRI scans to detect biomarkers of severe brain swelling in cerebral malaria.

The paper examines how individual differences in functional brain network topography relate to psychopathology dimensions in youth using machine learning and fMRI data.