Background: Vitamin D deficiency has been linked to increased risks of fractures and cardiovascular (CV) events, but the clinical relevance of the ‘insufficiency’ range remains unclear. We investigated CV and fracture risks across vitamin D levels, with a focus on the insufficiency range. Methods: Using UK Biobank data, we analyzed 375,044 participants aged 40 to 69 years. Vitamin D status was categorized as deficient (<50 nmol/L), insufficient (≥50 to <75 nmol/L), or sufficient (≥75 nmol/L). Outcomes included three-point major adverse cardiovascular events (3P-MACE; myocardial infarction, stroke, and CV mortality) and major osteoporotic fractures, assessed via hospital records, registries, and death certificates. Results: The vitamin D-deficient group had an increased risk of CV events (adjusted hazard ratio [aHR], 1.17; 95% confidence interval [CI], 1.11 to 1.24) and fractures (aHR, 1.09; 95% CI, 1.01 to 1.18) compared to the vitamin D-sufficient group. Within the deficient group, the severely deficient group (<30 nmol/L) exhibited a markedly higher risk (aHR, 1.29; 95% CI, 1.21 to 1.37 for 3PMACE; and aHR, 1.20; 95% CI, 1.10 to 1.32 for fractures). In contrast, the vitamin D-insufficient group (50 to 75 nmol/L) showed no significant increase in the risk of either outcome, with no clear benefit or harm observed. Spline curve analysis revealed a negative correlation between vitamin D levels and risk, which was observed only within the deficient range and not within the insufficient range. Conclusion Vitamin D deficiency is strongly associated with increased CV disease and fracture risks, whereas the insufficiency range shows no significant risk or benefit, raising questions about its clinical relevance.

The effects of atherogenic indices on kidney function remain unclear. This study evaluated the association between atherogenic indices and risk of chronic kidney disease (CKD) in adults with metabolic derangements. Methods: A total of 4,176 participants from the Gangnam Severance Medical Cohort (2006–2021), which consisted of participants who had at least one disease related to metabolic derangements including diabetes mellitus, fatty liver, and hypertension were enrolled and atherogenic indices (lipid ratios including atherogenic index of plasma [AIP]) were assessed. The study endpoint was a composite kidney outcome (estimated glomerular filtration rate [eGFR] of <60 mL/min/1.73 m2 in at least two measurements in participants with baseline eGFR of ≥60 mL/min/1.73 m2; ≥30% decrease in eGFR from baseline in participants with baseline eGFR of <60 mL/min/1.73 m2; or the initiation of dialysis or kidney transplantation). Results: During a median follow-up of 6.0 years (interquartile range, 2.5–11.0 years), 1,266 composite kidney outcomes (30.3%) occurred. The highest quartile of AIP showed a higher risk of composite kidney outcome than the lowest quartile (hazard ratio [HR], 1.31; 95% confidence interval [CI], 1.12–1.54). This association was consistent when the AIP was treated as a continuous variable (HR per 1.0 increase, 1.51; 95% CI, 1.21–1.88). However, other atherogenic indices did not show significant associations with composite kidney outcome. Adding AIP to the traditional risk model to predict composite kidney outcomes significantly improved the C-index, net reclassification index, and integrated discrimination improvement. The association between high AIP and an increased risk of composite kidney outcome was consistent regardless of subgroup. Conclusion: High AIP was associated with an increased risk of CKD in adults with metabolic derangements.

This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.

Background: Sacubitril-valsartan reduces the risk of cardiovascular mortality among patients with heart failure with reduced ejection fraction (HFrEF). However, its long-term protective effects on cardiac function with concurrent acute kidney injury (AKI) remain unclear. This study investigated the recovery of cardiac function relative to kidney function decline. Methods: A total of 512 patients with HFrEF who started sacubitril-valsartan or valsartan treatment were enrolled in cohort 1. Additionally, patients who experienced AKI and underwent follow-up transthoracic echocardiography were enrolled in cohort 2. In cohort 1, short- and long-term kidney outcomes were analyzed. For cohort 2, changes in cardiac function in relation to changes in kidney function after drug initiation were analyzed. Results: The mean age of the patients was 68.3 ± 15.1 years, and 57.4% of the patients were male. AKI occurred in 15.9% of the sacubitril-valsartan group and 12.5% of the valsartan group. After AKI, 78.4% of patients in the sacubitril-valsartan group and 71.4% of those in the valsartan group underwent recovery. Furthermore, cardiovascular outcomes in patients who developed AKI after drug initiation were analyzed in cohort 2. The sacubitril-valsartan group showed a greater improvement in cardiac function compared with the valsartan group (12.4% ± 15.4% vs. 1.4% ± 5.7%, p = 0.046). The ratio of deltas of cardiac and kidney function in the sacubitril-valsartan and valsartan groups were –1.76 ± 2.58 and –0.20 ± 0.58, respectively (p = 0.03). Conclusion Patients with HFrEF treated with sacubitril-valsartan exhibited significant improvements in cardiovascular outcomes despite AKI.

This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.

Background: Sacubitril-valsartan reduces the risk of cardiovascular mortality among patients with heart failure with reduced ejection fraction (HFrEF). However, its long-term protective effects on cardiac function with concurrent acute kidney injury (AKI) remain unclear. This study investigated the recovery of cardiac function relative to kidney function decline. Methods: A total of 512 patients with HFrEF who started sacubitril-valsartan or valsartan treatment were enrolled in cohort 1. Additionally, patients who experienced AKI and underwent follow-up transthoracic echocardiography were enrolled in cohort 2. In cohort 1, short- and long-term kidney outcomes were analyzed. For cohort 2, changes in cardiac function in relation to changes in kidney function after drug initiation were analyzed. Results: The mean age of the patients was 68.3 ± 15.1 years, and 57.4% of the patients were male. AKI occurred in 15.9% of the sacubitril-valsartan group and 12.5% of the valsartan group. After AKI, 78.4% of patients in the sacubitril-valsartan group and 71.4% of those in the valsartan group underwent recovery. Furthermore, cardiovascular outcomes in patients who developed AKI after drug initiation were analyzed in cohort 2. The sacubitril-valsartan group showed a greater improvement in cardiac function compared with the valsartan group (12.4% ± 15.4% vs. 1.4% ± 5.7%, p = 0.046). The ratio of deltas of cardiac and kidney function in the sacubitril-valsartan and valsartan groups were –1.76 ± 2.58 and –0.20 ± 0.58, respectively (p = 0.03). Conclusion Patients with HFrEF treated with sacubitril-valsartan exhibited significant improvements in cardiovascular outcomes despite AKI.

This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.

Background: Sacubitril-valsartan reduces the risk of cardiovascular mortality among patients with heart failure with reduced ejection fraction (HFrEF). However, its long-term protective effects on cardiac function with concurrent acute kidney injury (AKI) remain unclear. This study investigated the recovery of cardiac function relative to kidney function decline. Methods: A total of 512 patients with HFrEF who started sacubitril-valsartan or valsartan treatment were enrolled in cohort 1. Additionally, patients who experienced AKI and underwent follow-up transthoracic echocardiography were enrolled in cohort 2. In cohort 1, short- and long-term kidney outcomes were analyzed. For cohort 2, changes in cardiac function in relation to changes in kidney function after drug initiation were analyzed. Results: The mean age of the patients was 68.3 ± 15.1 years, and 57.4% of the patients were male. AKI occurred in 15.9% of the sacubitril-valsartan group and 12.5% of the valsartan group. After AKI, 78.4% of patients in the sacubitril-valsartan group and 71.4% of those in the valsartan group underwent recovery. Furthermore, cardiovascular outcomes in patients who developed AKI after drug initiation were analyzed in cohort 2. The sacubitril-valsartan group showed a greater improvement in cardiac function compared with the valsartan group (12.4% ± 15.4% vs. 1.4% ± 5.7%, p = 0.046). The ratio of deltas of cardiac and kidney function in the sacubitril-valsartan and valsartan groups were –1.76 ± 2.58 and –0.20 ± 0.58, respectively (p = 0.03). Conclusion Patients with HFrEF treated with sacubitril-valsartan exhibited significant improvements in cardiovascular outcomes despite AKI.

This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.