Background Chronic kidney disease (CKD) is a major global health burden, and early identification of individuals at risk remains challenging. This study aimed to identify plasma proteomic biomarkers associated with incident CKD and develop a machine learning-based prediction model integrating proteomic and clinical data. Methods We conducted a prospective cohort study of 27,429 UK Biobank participants without baseline CKD after excluding those with estimated glomerular filtration rate <60 mL/min/1.73 m2 or urinary albumin-to-creatinine ratio ≥3 mg/mmol. Among 2,920 plasma proteins, protein-wide Cox regression with Bonferroni correction was followed by least absolute shrinkage and selection operator (LASSO) regression and Light Gradient Boosting Machine (LightGBM)-based feature selection. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), calibration metrics, reclassification indices, and landmark-based prediction analyses, with SHapley Additive exPlanations (SHAP), Kaplan-Meier, and sensitivity analyses. Results A total of 205 proteins were significantly associated with incident CKD. LASSO identified 23 candidates, and LightGBM identified four key proteins (EDA2R, GDF15, HAVCR1, and SCARB2). The four-protein model showed comparable performance to the demographic model (AUC, 0.796 vs. 0.805; p = 0.14), while their combination improved discrimination (AUC, 0.830 [95% confidence interval, 0.806-0.855]; p < 0.001). The combined model also showed improved performance across 5-year, 10-year, and >10-year CKD prediction horizons. SHAP and Kaplan-Meier analyses consistently supported the predictive value of these proteins, and sensitivity analyses confirmed robustness. Conclusion Integrating plasma proteomics with machine learning improves internal risk prediction for incident CKD. The parsimonious four-protein panel may provide complementary information for CKD risk stratification, although external validation is needed before clinical application.
Background This study aimed to evaluate the kidney, cardiovascular, and mortality outcomes of combined sodium-glucose cotransporter 2 inhibitors (SGLT2i) and glucagon-like peptide-1 receptor agonists (GLP-1RA) therapy compared with SGLT2i monotherapy in patients with chronic kidney disease (CKD). Methods Using TriNetX electronic health records, we compared patients initiating combined therapy with those initiating SGLT2i alone. Propensity score matching (1:1) was applied. The index date was defined as treatment initiation, with patients required to maintain the assigned treatment strategy during the first 6 months. Outcome follow-up began 6 months after the index date and continued to 2 years after the index date. Primary outcomes were major adverse kidney events (MAKE) and major adverse cardiovascular events (MACE), and the secondary outcome was all-cause mortality. Results Among 178,930 patients, 1,154 (0.65%) initiated combined therapy of SGLT2i and GLP-1RA, and 24,134 (13.49%) initiated monotherapy of SGLT2i. After matching, each group included 1,150 patients. Combined therapy was associated with a lower risk of MAKE (adjusted hazard ratio [aHR], 0.62; 95% confidence interval [CI], 0.48-0.80; p < 0.01) and all-cause mortality (aHR, 0.58; 95% CI, 0.40-0.83; p < 0.01) compared with SGLT2i alone. There was no significant reduction in risk of MACE (aHR, 0.88; 95% CI, 0.70-1.11; p = 0.29). Conclusion Among patients with CKD, initiation of combined SGLT2i and GLP-1RA therapy was associated with lower risks of MAKE and all-cause mortality compared with SGLT2i monotherapy. Further studies are needed to clarify effects on kidney and mortality outcomes.
Background Evidence on the effectiveness of third-dose messenger RNA (mRNA) coronavirus disease 2019 (COVID-19) vaccination during the Omicron-dominant period in Asian hemodialysis (HD) patients remains limited. We evaluated the clinical effectiveness of a third mRNA vaccine dose against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, hospitalization, and mortality in Korean HD patients. Methods Using the Korea Disease Control and Prevention Agency-National Health Insurance Service database, we conducted a nationwide cohort study of HD patients aged ≥18 years who received two or three doses of BNT162b2 or mRNA-1273 before January 16, 2022. Study outcomes were SARS-CoV-2 infection, hospitalization, and death. Cox proportional hazards models were used to assess the associations between third-dose vaccination and clinical outcomes. Results Among 66,389 HD patients (mean age, 65.7 ± 12.9 years; 60.5% male), 55,125 (83.0%) received three vaccine doses and 11,264 (17.0%) received two doses. Receipt of three doses was associated with a significantly lower risk of SARS-CoV-2 infection (adjusted hazard ratio [aHR], 0.58; 95% confidence interval [CI], 0.56-0.60). Among 17,886 patients with SARS-CoV-2 infection, third-dose vaccine recipients had a lower risk of hospitalization (aHR, 0.65; 95% CI, 0.62-0.70) and 30-day mortality (aHR, 0.35; 95% CI, 0.30-0.41) compared with those who received two doses. Receipt of mRNA-1273 as the third dose was associated with lower observed risks of infection and hospitalization than receipt of BNT162b2. Conclusion A third dose of an mRNA COVID-19 vaccine was associated with lower risks of SARS-CoV-2 infection, hospitalization, and mortality among HD patients during the Omicron-dominant period. These findings support the clinical importance of booster vaccination in this high-risk population.
