CARDIORENAL RISK IN PATIENTS WITH ATRIAL FIBRILLATION AND CHRONIC KIDNEY DISEASE IN ARID REGIONS

Resume. Background: Atrial fibrillation (AF) and chronic kidney disease (CKD) frequently coexist and are linked through shared risk factors, haemodynamic stress, inflammation, metabolic abnormalities, and vascular dysfunction. Their combination increases the complexity of stroke prevention, bleeding-risk assessment, heart-failure management, and prediction of renal decline. In arid regions, extreme heat, dehydration, and electrolyte disturbances may add potentially modifiable stressors to this cardiorenal vulnerability. Artificial intelligence (AI) may support integrated risk estimation by combining longitudinal clinical, laboratory, electrocardiographic, echocardiographic, and environmental data. Objective: To review current evidence on the bidirectional relationship between AF and CKD, the possible relevance of heat exposure to cardiovascular and renal outcomes, and the opportunities and limitations of AI-based prediction in populations living in arid regions. Methods: This narrative review synthesizes major clinical guidelines and selected peer-reviewed reviews, systematic reviews, and methodological guidance published mainly from 2020 to 2025, alongside key earlier sources. The review focuses on clinically relevant mechanisms, risk assessment, environmental exposures, model development, and research priorities for arid regions. Conclusions: AF and CKD should be managed as interdependent conditions rather than isolated diagnoses. Current evidence supports systematic assessment of estimated glomerular filtration rate (eGFR), albuminuria, AF burden, cardiac structure and function, thromboembolic risk, bleeding risk, and treatment-related renal changes. Heat-related physiological stress is biologically plausible and supported by broader cardiovascular and kidney literature, but its specific contribution to combined AF–CKD outcomes in Central Asian arid settings remains insufficiently quantified. AI-based models could integrate these domains, provided they are transparent, externally validated, calibrated, and evaluated for clinical utility and fairness. Keywords: atrial fibrillation; chronic kidney disease; cardiorenal syndrome; heat exposure; arid climate; risk prediction; artificial intelligence; machine learning; Uzbekistan.

Hali tarjima qilinmagan