Neuroimaging analysis in brain disorders faces a persistent challenge: brain signals are complex and high-dimensional, while high-quality labeled datasets remain limited. This review article systematically examines how self-supervised learning can help address that gap by learning meaningful representations directly from unlabeled neuroimaging data. It covers major methodological families, including contrastive, generative, and hybrid generative-contrastive approaches, and discusses their applications in functional MRI, EEG, and multimodal brain network analysis.

The review argues that self-supervised learning offers more than annotation efficiency. It may enable more transferable and clinically useful representations for disease screening, diagnosis, and prognosis across heterogeneous datasets and disorders. At the same time, interpretability, data heterogeneity, missing modalities, and clinical validation remain major barriers. Future work will likely focus on stronger multimodal fusion, better cross-site generalization, and more clinically adaptable model design.

Dietary management in patients with end-stage renal disease (ESRD) has long lacked robust evidence directly linking nutrient intake to clinical outcomes, particularly in peritoneal dialysis populations. This study analyzed 12 years of longitudinal data from 656 patients, combining frequent follow-up assessments with detailed dietary records to evaluate associations between nutrient intake and mortality risk using both multivariable and nonlinear modeling approaches.

The findings demonstrate that most diet–outcome relationships are nonlinear, highlighting the importance of identifying optimal intake ranges rather than relying on single thresholds. In addition, the effects of nutrient intake vary across different nutritional states, as indicated by serum albumin levels, emphasizing the need for personalized dietary strategies. This study provides evidence-based reference ranges for nutritional management and introduces a methodological framework for future research on diet and long-term outcomes in chronic disease populations.

This study investigates the causal relationship between epilepsy subtypes and brain connectivity within resting-state networks using a bidirectional Mendelian randomization framework. By leveraging large-scale genetic and neuroimaging datasets, the researchers provide a more reliable assessment of causality beyond traditional observational studies.

The results demonstrate that genetic generalized epilepsy is associated with functional alterations in attention and motor-related brain networks, while brain connectivity changes do not appear to causally drive epilepsy. These findings deepen our understanding of epilepsy as a network-level disorder and suggest new avenues for targeted intervention and precision medicine.