White-matter functional network dysfunction associated with clinical phenotypes in patients with end-stage renal disease

Among end-stage renal disease (ESRD) patients, white matter (WM) is a particularly vulnerable area that is susceptible to various clinical risk factors. However, whether WM function is disrupted in ESRD patients and how this disruption provides valuable information for cognitive deficits and potential clinical phenotypes remain unknown. We enrolled 78 ESRD patients and 50 healthy controls. Using resting-state functional MRI, functional connectivity, functional covariance connectivity, and Granger causality analysis were probed interactions among ESRD-related WM functional networks. Multiple machine-learning models with 10-fold cross-validation were applied to assess the discriminative power for the ESRD-related WM functional network alterations. ESRD patients showed extensive WM network dysfunction, correlating with cognitive deficits and ESRD-specific risks (uremic toxins, calcium-phosphorus imbalance, and anemia). A logistic regression classifier achieved a maximum performance of 74.22% accuracy and 0.81 AUC. Our findings highlight ESRD-related WM functional network imbalances as potential neuroimaging markers for cognitive deficits and clinical phenotypes. Analysis of white-matter functional network alterations via resting-state fMRI and machine learning in patients with end-stage renal disease highlight end-stage renal disease-related white-matter functional network imbalances as potential neuroimaging markers for cognitive deficits and clinical phenotypes.