Disparities in accelerated brain aging in recent-onset and chronic schizophrenia

Psychological Medicine, Год журнала: 2025, Номер 55

Опубликована: Янв. 1, 2025

Abstract Background Patients with schizophrenia experience accelerated aging, accompanied by abnormalities in biomarkers such as shorter telomere length. Brain age prediction using neuroimaging data has gained attention research, consistently reported increases brain-predicted difference (brain-PAD). However, its associations clinical symptoms and illness duration remain unclear. Methods We developed brain models structural magnetic resonance imaging (MRI) from 10,938 healthy individuals. The were validated on an independent test dataset comprising 79 controls, 57 patients recent-onset schizophrenia, 71 chronic schizophrenia. Group comparisons the of brain-PAD analyzed multiple linear regression. SHapley Additive exPlanations (SHAP) values estimated feature contributions to model, between-group differences SHAP group-by-SHAP value interactions also examined. Results exhibited increased 1.2 0.9 years, respectively. Between-group identified right lateral prefrontal area (false discovery rate [FDR] p = 0.022), observed left (FDR 0.049). A negative association between Full-scale Intelligence Quotient scores was noted, which did not significant after correction for comparisons. Conclusions Brain-PAD pronounced early phase Regional contributing likely vary duration. Future longitudinal studies are required overcome limitations related sample size, heterogeneity, cross-sectional design this study.

Язык: Английский

Enhancing Brain Age Estimation Under Uncertainty: A Spectral-normalized Neural Gaussian Process Approach Utilizing 2.5D Slicing

NeuroImage, Год журнала: 2025, Номер unknown, С. 121184 - 121184

Опубликована: Апрель 1, 2025

Brain age gap, the difference between estimated brain and chronological via magnetic resonance imaging, has emerged as a pivotal biomarker in detection of abnormalities. While deep learning is accurate estimating age, absence uncertainty estimation may pose risks clinical use. Moreover, current 3D models are intricate, using 2D slices hinders comprehensive dimensional data integration. Here, we introduced Spectral-normalized Neural Gaussian Process (SNGP) accompanied by 2.5D slice approach for seamless integration single network with low computational expenses, extra without added model complexity. Subsequently, compared different methods Pearson correlation coefficient, metric that helps circumvent systematic underestimation during training. SNGP shows excellent generalization on dataset 11 public datasets (N=6327), competitive predictive performance (MAE=2.95). Besides, demonstrates superior (MAE=3.47) an independent validation set (N=301). Additionally, conducted five controlled experiments to validate our method. Firstly, adjustment improved accelerated aging adolescents ADHD, 38% increase effect size after adjustment. Secondly, exhibited OOD capabilities, showing significant differences across Asian non-Asian datasets. Thirdly, DenseNet backbone was slightly better than ResNeXt, attributed DenseNet's feature reuse capability, robust set. Fourthly, site harmonization led decline performance, consistent previous studies. Finally, significantly outperformed methods, improving increasing In conclusion, present cost-effective method uncertainty, utilizing slicing enhanced showcasing promise applications.

Язык: Английский