Elvisha Dhamala

Spurious model comparisons are widespread in biomedical artificial intelligence

97% of 184 high-impact biomedical AI studies compare cross-validated models with tests assuming fold independence; in 69% of re-analyzable studies a significant comparison does not survive correction.

Investigating the impact of stressful life events on neuroanatomy across adolescence

This study examines how stressful life events affect adolescent neuroanatomy using ABCD data, finding mostly non-significant associations but some sex-specific effects on cortical thickness and surface area.

Neuroanatomy Reflects Individual Variability In Impulsivity in Youth

The paper investigates how neuroanatomical variability relates to impulsivity in youth using data from the ABCD Study, finding sex-specific and dynamic associations across multiple brain features.

Is the whole more than the sum of its parts? Considering global and local features of the connectome improves prediction of individuals and phenotype

This paper improves brain connectome analysis by incorporating global and local features, enhancing individual identification and phenotype prediction.

Hormonal contraceptive intake during adolescence and cortical brain measures in the ABCD Study

This study examines the impact of hormonal contraceptive use on cortical brain measures in adolescents using ABCD Study data, finding significant differences in cortical thickness and correlations with hormone levels.

Shared Neural Signatures of Socioeconomic Status, Scarcity, and Neighborhood Threat in Youth

The paper uses machine learning to link socioeconomic status, scarcity, and neighborhood threat to cortical thickness in youth, finding consistent neural signatures in memory and visual processing regions.

Convergent and Divergent Brain-Cognition Development

The paper examines how stable and changing brain network features predict cognitive development in adolescents using rs-fMRI and cognitive data from the ABCD Study.

The Cellular Underpinnings of the Human Cortical Connectome

The paper shows that cell type distributions in the cortex are spatially aligned with functional organization patterns from fMRI.

A shared spatial topography links the functional connectome correlates of cocaine use disorder and dopamine D2/3 receptor densities

This paper identifies widespread functional connectivity differences in cocaine use disorder (CUD) and links these patterns to dopamine D2/3 receptor densities across the brain.

Functional brain networks are associated with both sex and gender in children

This study shows that sex and gender are associated with distinct functional brain networks in children, with sex linked to unimodal networks and gender to heteromodal networks.

Sex differences in the functional network underpinnings of psychotic-like experiences in children

The paper examines sex differences in functional brain network connectivity associated with psychotic-like experiences in children using the ABCD Study dataset.

Sex-specific brain effective connectivity patterns associated with negative emotions

This study identifies sex-specific resting-state brain connectivity patterns associated with negative emotions in a healthy population.

Distinct brain network features predict internalizing and externalizing traits in children and adults

The paper shows that brain network features predicting internalizing and externalizing traits differ between children and adults, with more similarity within categories in children and distinct features in adults.

Brain-based predictions of psychiatric illness-linked behaviors across the sexes

The paper shows that functional brain connectivity predicts psychiatric illness-linked behaviors differently in males and females, with shared and unique patterns across sexes.

A graph-matching based metric of functional connectome distance between pairs of individuals varies with their ages, cognitive performances and familial relationships.

This study introduces a graph-matching based metric to quantify functional connectome differences between individuals and finds it correlates with age, cognitive performance, and familial relationships.

Comparison of individualized behavioral predictions across anatomical, diffusion and functional connectivity MRI

This study compares the ability of anatomical, diffusion, and functional MRI to predict individual behavioral measures, finding that functional connectivity provides the best predictions, especially for cognition.

Proportional intracranial volume correction differentially biases behavioral predictions across neuroanatomical features and populations

This study shows that proportional intracranial volume correction affects the predictive accuracy and generalizability of brain-behavior models across anatomical features and populations.

Shared functional connections within and between cortical networks predict individual cognitive abilities in males and females

The paper examines sex-independent and sex-specific relationships between functional connectivity and cognitive abilities in healthy adults using the Human Connectome Project data.

Integrating multimodal connectivity improves prediction of individual cognitive abilities

The paper integrates functional and structural brain connectivity to predict individual cognitive abilities, finding that multimodal integration outperforms single-modal approaches.

Neuroimaging Correlates of Emotional Response-Inhibition Discriminate Between Young Depressed Adults With and Without Sub-threshold Bipolar Symptoms

This study uses fMRI to compare emotional response-inhibition patterns between young adults with major depression and subthreshold bipolar symptoms, finding distinct neural activation differences.

Sex classification using long-range temporal dependence of resting-state functional MRI time series

This study identifies sex differences in brain regions using temporal dependence and volume measures from resting-state fMRI data, achieving high classification accuracy.