Polygenic Risk-Informed White Matter Integrity Improves Deep Learning-Based Prediction of Youth Depression
Cha, J.; Min, J. J.; Wang, H.; Lee, E.; Kim, B.-G.; Kim, G.; Choi, S. Y.; Choi, K.; Hong, S. H.; Jang, Y.; Rah, Y. J.; Kim, J. Y.; Han, S.; Lee, K. H.; Kim, J.; van Dijk, M. T.; Kim, J.-W.; Chung, G. H.; Chung, D.; Lee, S. A.; Joo, Y. Y.
Show abstract
Early detection of youth depression is crucial, given its rising prevalence and long-term consequences. Although genetic factors contribute significantly to youth depression, their integration with neuroimaging remains limited. We present a deep learning framework using polygenic scores (PGS) to pretrain a 3D convolutional neural network on diffusion MRI (track-weighted fractional anisotropy), capturing gene-brain associations from a multi-ethnic cohort in the Adolescent Brain Cognitive Development Study (N=4,741). Fine-tuned for predicting depression, the model improved cross-sectional (N=266; AUC=0.62) and two-year predictions of depression and suicidality (AUC=0.61-0.66). It outperformed unimodal models, increasing accuracy by up to 24% over PGS-only and 5.8% over brain-only models. Explainable artificial intelligence identified key white matter tracts--superior longitudinal fasciculus, cingulum and corpus callosum--as predictive features. Decision curve analysis showed greater clinical utility. The model generalized to an independent Korean youth sample (N=108; AUC=0.67), supporting the cross-ethnic scalability of PGS-informed diffusion MRI for precision psychiatry
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Applying Machine-Learning and Deep-Learning to Predict Depression from Brain MRI and Identify Depression-Related Brain Biology 95%
- Differential and spatial expression meta-analysis of genes identified in genome-wide association studies of depression 95%
- Mendelian randomization integrating GWAS and eQTL data revealed genes pleiotropically associated with major depressive disorder 94%
Similar papers in this journal
- Heterogeneity in Depression: evidence for distinct clinical and neurobiological profiles 96%
- Dimensional and Categorical Solutions to Parsing Depression Heterogeneity in a Large Single-Site Sample 95%
- Predictive Patterns of Antidepressant Response from Pre-Treatment Reward Processing using Functional MRI and Deep Learning: Key Results from the EMBARC Randomized Clinical Trial 95%
Similar papers in this journal
- Structural brain alterations associated with suicidal thoughts and behaviors in young people: results across 21 international studies from the ENIGMA Suicidal Thoughts and Behaviours consortium 94%
- Functional dysconnectivity of visual and somatomotor networks yields a simple and robust biomarker for psychosis 94%
- MRI-derived estimation of biological aging in patients with affective disorders in a 9-year follow-up - a prospective marker of future recurrence 94%
Similar papers in this journal
- Energy inefficiency underpinning brain state dysregulation in individuals with major depressive disorder 96%
- A generalizable functional connectivity signature characterizes brain dysfunction and links to rTMS treatment response in cocaine use disorder 95%
- Dissecting causal relationships between cortical morphology and neuropsychiatric disorders: a bidirectional Mendelian randomization study 94%
Similar papers in this journal
- Maladaptive avoidance learning in the orbitofrontal cortex in adolescents with major depression 95%
- Brain structure and function show distinct relations with genetic predispositions to mental health and cognition 95%
- Machine learning identifies large-scale reward-related activity modulated by dopaminergic enhancement in major depression 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.