Narun Pat

This study uses domain adaptation methods to reduce cross-ethnic prediction errors in neuroimaging-based cognitive prediction using the ABCD dataset.

This study evaluates MRI modalities' ability to predict cognitive functioning across age, finding that combined MRI markers best predict between-person differences, while longitudinal changes are less captured.

This study develops multimodal MRI markers to predict and track cognitive functioning in ADHD over time, showing they capture cognitive development and symptom relationships.

The paper evaluates if individualized head models improve source-space EEG functional connectivity predictions of cognition in Parkinson's disease, finding standard templates are sufficient.

The paper benchmarks ethnic bias in MRI-based cognitive prediction models and finds that balanced sampling reduces disparities without accuracy loss, with structural MRI showing greater bias than task-based fMRI.

This paper introduces a stacking machine learning approach to improve predictability, test-retest reliability, and generalisability of brain-wide associations for cognitive abilities using multimodal MRI data.

This study evaluates Brain Age as a biomarker for fluid cognition in older adults and finds it only marginally improves prediction over chronological age.

This paper shows that integrating task-based fMRI across tasks improves prediction and test-retest reliability of cognitive abilities compared to non-task MRI modalities.

The paper develops brain-based predictive models for childhood cognition using multimodal MRI data from the ABCD study, showing stability over time and partial mediation of socio-demographic, psychological, and genetic factors.

This paper uses an explainable machine learning framework to predict and explain cognitive differences from task-based fMRI data, finding that ML models outperform traditional methods in prediction and provide consistent explanations.

This paper reviews reward processing as a cause and predictor of depression, identifies challenges, and finds reward processing abnormalities are not yet clinically predictive but may have causal roles.