Andrew A. Chen

ComBatFamQC provides an R package for batch-effect diagnosis and harmonization in neuroimaging data, integrating visualization, statistical tests, and harmonization methods.

ComBat-Predict improves the generalizability of neuroimaging models to new sites by harmonizing site effects and reducing bias in cortical thickness predictions.

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.

The paper introduces a UGEE framework for analyzing multimodal neuroimaging data, showing it accurately estimates effects and is 100x faster than permutation methods.

This paper introduces ReForm, a method to calibrate MRI-based reference intervals for new samples without sharing reference data, showing comparable or better false positive rate control than alternative methods.

The paper develops a new estimator to more accurately assess machine learning model performance in predicting brain-phenotype associations and shows it reduces bias in estimating predictive accuracy.

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 develops a harmonization framework for structural connectomes to reduce site-related biases, showing that gamma-GLM improves generalizability and statistical power in multi-site analyses.

ComBatLS improves multi-site image harmonization by preserving biological variance in features, outperforming existing methods in sex-imbalanced site scenarios and reducing sex biases.

DeepCombat removes batch effects from neuroimaging data using a deep learning approach, outperforming existing methods in preserving biological variation.

The paper examines how functional connectivity develops along the sensorimotor-association axis during childhood to adolescence, finding that sensorimotor connectivity increases while association connectivity decreases, reinforcing cortical hierarchy.

This paper introduces a distance-based regression method for multimodal data that can handle different data types and dimensionalities, showing its effectiveness through simulations and real-world studies.

The paper investigates how functional connectivity patterns in brain networks predict symptoms of borderline personality disorder in adolescents and young adults using fMRI data.

The paper introduces the PARE framework to remove confounders from dimension reduction methods, showing it can eliminate batch effects in single-cell data and separate clinical from technical variability in neuroimaging.

The paper defines personalized functional networks in children to predict cognitive differences, finding that fronto-parietal network representation correlates with general cognition.

Simulations and neuroimaging analyses argue that unreliable clinical and cognitive phenotypes, not only noisy fMRI, cap biomarker discovery; aggregating across raters or repeated measures beats enlarging samples.

This study identifies scanner effects in brain community detection and proposes new harmonization methods to reduce these effects in functional connectivity analysis.

This paper introduces distributed ComBat to harmonize neuroimaging data across institutions while preserving privacy, achieving results equivalent to centralized methods.

This paper shows that removing scanner effects in mean and variance is insufficient for multivariate pattern analysis and proposes a method to harmonize covariance across scanners.

The paper identifies statistical issues in brain age gap analysis, showing that modifying the brain age gap can inflate model accuracy statistics and suggests developing new methods to quantify deviation from normal developmental trajectories.