Chronic kidney disease (CKD) is a major global health problem and an important driver of cardiovascular morbidity and mortality. Sleep disorders are highly prevalent in people with, or at risk of, CKD, but their specific contribution to CKD onset and progression has not been clearly defined. Unlike previous reviews that have focused mainly on symptom burden, quality of life, or general management of sleep problems in CKD, this narrative review is explicitly centred on renal outcomes. We examine whether common sleep disorders-insomnia, abnormal sleep duration, restless legs syndrome, periodic limb movement disorder, and obstructive sleep apnoea (OSA) and central sleep apnoea-are associated with an increased risk of incident CKD and with faster progression of established CKD [estimated glomerular filtration rate (eGFR) decline, albuminuria, end-stage kidney disease]. We synthesize evidence from prospective cohorts, administrative databases, and Mendelian randomization studies, with particular attention to residual confounding, incomplete sleep phenotyping, and overlap between sleep disorders, especially unrecognized OSA. Observational data suggest that poor sleep quality and abnormal sleep duration are modestly associated with incident CKD and CKD progression, although independence from OSA remains uncertain. In contrast, evidence linking OSA to reduced eGFR, albuminuria, and accelerated CKD progression is more consistent, and bidirectional relations between CKD and OSA are increasingly recognized. We also review pathophysiological pathways that plausibly connect sleep disorders to renal injury and critically appraise preliminary interventional data on OSA treatment and kidney outcomes. Finally, we outline the clinical implications of integrating outcome-oriented sleep assessment into nephrology and hypertension care and propose a research agenda to determine whether systematic detection and treatment of sleep disorders, particularly OSA, should be adopted as a strategy to prevent CKD onset and slow CKD progression.
This perspective examines how artificial intelligence (AI) may reshape nephrology over the next two decades while keeping the nephrologist's role central. Prediction models for acute kidney injury and chronic kidney disease progression, and multimodal tools such as KidneyIntelX, will deliver continuous, patient-level risk estimates from electronic health records, biomarkers, imaging, and wearable devices. Large language models (LLMs) are "copilots" for documentation, triage, education, and patient counseling, with potential to reduce administrative burden but also risks of hallucinations, bias, and uneven accuracy. Nephrologists will need new competencies in model calibration, fairness, communication, and ethics to decide when to follow or override algorithmic advice, especially for older, frail, and multimorbid patients. Overall, AI can support proactive, person-centred kidney care only if clinicians help design, govern, evaluate, and critically supervise these emerging technologies within robust, learning healthcare systems.
