Kwon Wook Joo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kwon Wook Joo has a total of 334 co-authors. Here are the top co-authors by number of shared publications:
- Dong Ki Kim
Division of Nephrology, Department of Internal Medicine, Seoul National University Hospital, Seoul, Republic of Korea
59 shared publications - Seung Seok Han
Department of Internal Medicine, Seoul National University Hospital, Seoul, Republic of Korea
41 shared publications - Yon Su Kim
Division of Nephrology, Department of Internal Medicine, Seoul National University Hospital, Seoul, Republic of Korea
41 shared publications - Hajeong Lee
Transplantation Center, Seoul National University Hospital, Seoul, Republic of Korea
25 shared publications - Yaerim Kim
Department of Internal Medicine, Keimyung University School of Medicine, Daegu, Republic of Korea
25 shared publications - Sehoon Park
Transplantation Center, Seoul National University Hospital, Seoul, Republic of Korea
24 shared publications
Latest Publications
- Open Access
- 28 October 2026
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
- Vol. 45 (6) , 991-1001
Effect of off-label vitamin D analog use for albuminuria in early nondiabetic nephropathy: a double-blind, randomized, placebo-controlled trial
Background: Albuminuria is one of the factors promoting the progression of chronic kidney disease (CKD). The study aimed to assess the efficacy and safety of calcitriol for the reduction of microalbuminuria in patients with nondiabetic nephropathy.Methods: In this randomized, double-blind, placebo-controlled, and multicenter study, adult patients with nondiabetic CKD stage 3 or greater and albuminuria were included. Participants were administered calcitriol or placebo for 6 months and followed for up to 12 months. The primary outcome was the change in urine protein-to-creatinine ratio (UPCR), and secondary outcomes included the changes in renal function and vitamin D level. The safety was assessed by recording adverse events during the treatment and follow-up.Results: A total of 159 subjects were enrolled. The UPCR at 24 and 48 weeks was significantly decreased compared to the baseline in the calcitriol group (ΔUPCR, –0.24 g/g [95% CI, –0.43 to –0.05] and –0.22 g/g [95% CI, –0.43 to –0.01], respectively), but the mean changes of UPCR during 24 weeks and 48 weeks were no significant difference between the two groups. No significant differences were in the change in renal function and vitamin D level. Seventy-eight adverse events were reported during the treatment phase, and there were no significant differences in the type or frequency of adverse events between the two groups.Conclusion: Although calcitriol treatment showed a significant reduction of proteinuria from baseline, the effect was insufficient in nondiabetic CKD compared to placebo. Therefore, the use of calcitriol for the reduction of albuminuria is worth considering.
- 28 October 2026
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
- Vol. 45 (6) , 991-1001
Open AccessEffect of off-label vitamin D analog use for albuminuria in early nondiabetic nephropathy: a double-blind, randomized, placebo-controlled trial
Background: Albuminuria is one of the factors promoting the progression of chronic kidney disease (CKD). The study aimed to assess the efficacy and safety of calcitriol for the reduction of microalbuminuria in patients with nondiabetic nephropathy.Methods: In this randomized, double-blind, placebo-controlled, and multicenter study, adult patients with nondiabetic CKD stage 3 or greater and albuminuria were included. Participants were administered calcitriol or placebo for 6 months and followed for up to 12 months. The primary outcome was the change in urine protein-to-creatinine ratio (UPCR), and secondary outcomes included the changes in renal function and vitamin D level. The safety was assessed by recording adverse events during the treatment and follow-up.Results: A total of 159 subjects were enrolled. The UPCR at 24 and 48 weeks was significantly decreased compared to the baseline in the calcitriol group (ΔUPCR, –0.24 g/g [95% CI, –0.43 to –0.05] and –0.22 g/g [95% CI, –0.43 to –0.01], respectively), but the mean changes of UPCR during 24 weeks and 48 weeks were no significant difference between the two groups. No significant differences were in the change in renal function and vitamin D level. Seventy-eight adverse events were reported during the treatment phase, and there were no significant differences in the type or frequency of adverse events between the two groups.Conclusion: Although calcitriol treatment showed a significant reduction of proteinuria from baseline, the effect was insufficient in nondiabetic CKD compared to placebo. Therefore, the use of calcitriol for the reduction of albuminuria is worth considering.
- 12 June 2026
- Published by Wolters Kluwer Health in Clinical Journal of the American Society of Nephrology
- Vol. 21 (9) , 1531-1544
Stage-Specific Progression of Cardiovascular-Kidney-Metabolic Health and Mortality in a Nationwide Cohort of East Asian Adults
Background: Cardiovascular-Kidney-Metabolic (CKM) syndrome represents the progressive interplay among metabolic dysfunction, kidney impairment, and cardiovascular disease (CVD), ultimately contributing to higher mortality. We investigated how changes across CKM stages correlate with subsequent all-cause mortality in a nationwide population-based cohort. Methods: We analyzed data from 2,812,170 adults aged ≥20 years who underwent two general health screenings four years apart through the Korean National Health Insurance Service, with CKM stages classified according to clinical criteria reflecting progressive metabolic, kidney, and cardiovascular risk. Stage-specific CKM stage change (improve, sustain, or progress) and its association with all-cause mortality were evaluated using multivariable Cox regression analysis, adjusted for clinicodemographic variables. Results: During the four-year exposure assessment period, 674,465 adults (24%) experienced CKM stage progress, 1,802,489 (64%) sustained their CKM stage, and 335,216 (12%) improved. Over a subsequent 6.4-year follow-up, CKM stage progress was significantly associated with an higher risk of all-cause mortality [adjusted HR 1.38 (1.36–1.41)], whereas CKM stage improvement was associated with a lower risk [adjusted HR 0.93 (0.90–0.95)]. Notably, even early-stage progression (from stage 0 to stage 1) was linked to a higher mortality risk [adjusted HR 1.08 (1.01–1.15)], with a stepwise higher risk observed with progression to more advanced follow-up CKM stages. The association between CKM stage progress and mortality was more pronounced in older adults. Conclusion: Worsening of CKM stage is associated with higher all-cause mortality from early to advanced stages, whereas CKM stage improvement is associated with lower mortality risk. These findings provide epidemiologic real-world evidence supporting the importance of monitoring and intervening on CKM progression across its full spectrum to lower long-term mortality risk.
- 12 June 2026
- Published by Wolters Kluwer Health in Clinical Journal of the American Society of Nephrology
- Vol. 21 (9) , 1531-1544
Stage-Specific Progression of Cardiovascular-Kidney-Metabolic Health and Mortality in a Nationwide Cohort of East Asian Adults
Background: Cardiovascular-Kidney-Metabolic (CKM) syndrome represents the progressive interplay among metabolic dysfunction, kidney impairment, and cardiovascular disease (CVD), ultimately contributing to higher mortality. We investigated how changes across CKM stages correlate with subsequent all-cause mortality in a nationwide population-based cohort. Methods: We analyzed data from 2,812,170 adults aged ≥20 years who underwent two general health screenings four years apart through the Korean National Health Insurance Service, with CKM stages classified according to clinical criteria reflecting progressive metabolic, kidney, and cardiovascular risk. Stage-specific CKM stage change (improve, sustain, or progress) and its association with all-cause mortality were evaluated using multivariable Cox regression analysis, adjusted for clinicodemographic variables. Results: During the four-year exposure assessment period, 674,465 adults (24%) experienced CKM stage progress, 1,802,489 (64%) sustained their CKM stage, and 335,216 (12%) improved. Over a subsequent 6.4-year follow-up, CKM stage progress was significantly associated with an higher risk of all-cause mortality [adjusted HR 1.38 (1.36–1.41)], whereas CKM stage improvement was associated with a lower risk [adjusted HR 0.93 (0.90–0.95)]. Notably, even early-stage progression (from stage 0 to stage 1) was linked to a higher mortality risk [adjusted HR 1.08 (1.01–1.15)], with a stepwise higher risk observed with progression to more advanced follow-up CKM stages. The association between CKM stage progress and mortality was more pronounced in older adults. Conclusion: Worsening of CKM stage is associated with higher all-cause mortality from early to advanced stages, whereas CKM stage improvement is associated with lower mortality risk. These findings provide epidemiologic real-world evidence supporting the importance of monitoring and intervening on CKM progression across its full spectrum to lower long-term mortality risk.
- Open Access
- 11 June 2026
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
- Vol. 45 (5) , 724-742
Development and external validation of an explainable machine learning model for predicting chronic kidney disease progression in the Korean population
Background: Current risk stratification models, such as the Kidney Failure Risk Equation (KFRE), exhibit variable performance across ethnic groups and fail to capture dynamic clinical trajectories. This study aimed to develop and validate a Korean-specific machine learning (ML) model for predicting chronic kidney disease (CKD) progression using an ensemble approach.Methods: We used electronic health records from Seoul National University Hospital for model development (n = 28,209) and the Korean Genome and Epidemiology Study (KoGES) CKD cohort for external validation (n = 3,960). The primary outcome was a composite of ≥40% decline in estimated glomerular filtration rate (eGFR) or progression to end-stage renal disease within 2 years. A soft-voting ensemble of four ML algorithms (XGBoost, LightGBM, CatBoost, and Random Forest) was developed.Results: The ensemble model demonstrated robust discrimination in internal validation (area under the receiver operating characteristic curve [AUROC], 0.939; 95% confidence interval [CI], 0.934–0.944), significantly exceeding the KFRE (AUROC, 0.879–0.884). External validation in the KoGES cohort showed comparable discrimination (AUROC, 0.859; 95% CI, 0.798–0.914) versus KFRE (four-variable AUROC, 0.882; 95% CI, 0.818–0.935). Shapley Additive exPlanations (SHAP) analysis identified baseline eGFR, serum creatinine, eGFR slope, albumin, and hemoglobin as key prognostic features, supporting a complementary framework using KFRE for community screening and the ML model for hospital-based risk stratification.Conclusion: The ensemble ML model accurately predicts short-term CKD progression in Korean patients. By incorporating longitudinal features and ensemble learning, it provides a precise alternative to Western-derived equations, particularly in tertiary care settings.
- 11 June 2026
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
- Vol. 45 (5) , 724-742
Open AccessDevelopment and external validation of an explainable machine learning model for predicting chronic kidney disease progression in the Korean population
Background: Current risk stratification models, such as the Kidney Failure Risk Equation (KFRE), exhibit variable performance across ethnic groups and fail to capture dynamic clinical trajectories. This study aimed to develop and validate a Korean-specific machine learning (ML) model for predicting chronic kidney disease (CKD) progression using an ensemble approach.Methods: We used electronic health records from Seoul National University Hospital for model development (n = 28,209) and the Korean Genome and Epidemiology Study (KoGES) CKD cohort for external validation (n = 3,960). The primary outcome was a composite of ≥40% decline in estimated glomerular filtration rate (eGFR) or progression to end-stage renal disease within 2 years. A soft-voting ensemble of four ML algorithms (XGBoost, LightGBM, CatBoost, and Random Forest) was developed.Results: The ensemble model demonstrated robust discrimination in internal validation (area under the receiver operating characteristic curve [AUROC], 0.939; 95% confidence interval [CI], 0.934–0.944), significantly exceeding the KFRE (AUROC, 0.879–0.884). External validation in the KoGES cohort showed comparable discrimination (AUROC, 0.859; 95% CI, 0.798–0.914) versus KFRE (four-variable AUROC, 0.882; 95% CI, 0.818–0.935). Shapley Additive exPlanations (SHAP) analysis identified baseline eGFR, serum creatinine, eGFR slope, albumin, and hemoglobin as key prognostic features, supporting a complementary framework using KFRE for community screening and the ML model for hospital-based risk stratification.Conclusion: The ensemble ML model accurately predicts short-term CKD progression in Korean patients. By incorporating longitudinal features and ensemble learning, it provides a precise alternative to Western-derived equations, particularly in tertiary care settings.
- Open Access
- 1 March 2026
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
- Vol. 45 (2) , 210-219
Medical costs in the peridiagnosis period of various biopsy-confirmed kidney diseases in South Korea
Background: In-depth investigation is imperative to scrutinize medical costs associated with the periods before and after biopsies for diverse kidney diseases in South Korea. Long-term epidemiological data, including follow-up information, is essential for comparing risks linked to various kidney diseases and their adverse outcomes. Methods: Patients diagnosed with glomerulonephritis (GN), tubulointerstitial nephritis (TIN), and acute tubular necrosis (ATN) at Seoul National University Hospital between 2012 and 2018 were included. We linked the prospective cohort data of biopsy-confirmed kidney disease patients (KORNERSTONE) from our study hospital to the national claims database of Korea, covering both medical events and insured costs. We analyzed medical costs during the periods before and after kidney biopsies, categorized by specific diagnoses, and delved into adverse prognostic outcomes. Results: Our study involved 1,390 patients with biopsy-confirmed GN, TIN, and ATN. After diagnosis, monthly average medical costs increased for most kidney diseases, excluding membranous nephropathy, Henoch-Schönlein purpura, and amyloidosis. The most substantial yearly average medical cost increase was observed in the ATN, acute TIN (ATIN), and chronic TIN (CTIN) groups. Costs rose for most kidney disease categories, except for amyloidosis. Higher myocardial infarction, stroke, and death rates were noted in CTIN, ATIN, and ATN compared to other types, with lupus nephritis displaying the highest end-stage kidney disease progression rate. Conclusion: In South Korea, medical costs for the majority of GN, TIN, and ATN patients increased following kidney biopsy diagnosis. This current data provides valuable epidemiological insights into the medical costs and prognosis of various kidney diseases in the country.
- 1 March 2026
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
- Vol. 45 (2) , 210-219
Open AccessMedical costs in the peridiagnosis period of various biopsy-confirmed kidney diseases in South Korea
Background: In-depth investigation is imperative to scrutinize medical costs associated with the periods before and after biopsies for diverse kidney diseases in South Korea. Long-term epidemiological data, including follow-up information, is essential for comparing risks linked to various kidney diseases and their adverse outcomes. Methods: Patients diagnosed with glomerulonephritis (GN), tubulointerstitial nephritis (TIN), and acute tubular necrosis (ATN) at Seoul National University Hospital between 2012 and 2018 were included. We linked the prospective cohort data of biopsy-confirmed kidney disease patients (KORNERSTONE) from our study hospital to the national claims database of Korea, covering both medical events and insured costs. We analyzed medical costs during the periods before and after kidney biopsies, categorized by specific diagnoses, and delved into adverse prognostic outcomes. Results: Our study involved 1,390 patients with biopsy-confirmed GN, TIN, and ATN. After diagnosis, monthly average medical costs increased for most kidney diseases, excluding membranous nephropathy, Henoch-Schönlein purpura, and amyloidosis. The most substantial yearly average medical cost increase was observed in the ATN, acute TIN (ATIN), and chronic TIN (CTIN) groups. Costs rose for most kidney disease categories, except for amyloidosis. Higher myocardial infarction, stroke, and death rates were noted in CTIN, ATIN, and ATN compared to other types, with lupus nephritis displaying the highest end-stage kidney disease progression rate. Conclusion: In South Korea, medical costs for the majority of GN, TIN, and ATN patients increased following kidney biopsy diagnosis. This current data provides valuable epidemiological insights into the medical costs and prognosis of various kidney diseases in the country.
- Open Access
- 1 January 2026
- Published by XMLink in Journal of Korean Medical Science
- Vol. 41 (7) , e70
Heterogeneous Kidney Patterns in Diabetic Patients Following SGLT2 Inhibitor Use
Bae S, et al. J Korean Med Sci. 2026 Feb;41(7):e70. https://doi.org/10.3346/jkms.2026.41.e70
- 1 January 2026
- Published by XMLink in Journal of Korean Medical Science
- Vol. 41 (7) , e70
Open AccessHeterogeneous Kidney Patterns in Diabetic Patients Following SGLT2 Inhibitor Use
Bae S, et al. J Korean Med Sci. 2026 Feb;41(7):e70. https://doi.org/10.3346/jkms.2026.41.e70
- 1 December 2025
- Published by Wolters Kluwer Health in Journal of the American Society of Nephrology
- Vol. 37 (5) , 984-994
Bone Mineral Density and the Risk of Fracture According to eGFR in Postmenopausal Women
Key Points: Lower bone mineral density was associated with a higher risk of fracture, irrespective of eGFR. At a similar bone mineral density, the fracture risk was higher with lower eGFR, more prominently for hip fractures than for vertebral fractures. The higher risk of fracture associated with lower eGFR was more pronounced in individuals with poor static balance. Background: Although both lower bone mineral density (BMD) and impaired kidney function are well-established risk factors for fracture, large-scale studies evaluating their effects and interaction on fracture, particularly site-specific fractures including vertebra and hip, are still limited. Methods: The main study population included female participants aged 66 years who underwent BMD assessment through dual-energy x-ray absorptiometry through the Korean National Screening Program between 2010 and 2016. BMD was categorized as normal, osteopenia, and osteoporosis on the basis of T -score. Kidney function was classified as eGFR ≥60, 45–59, and 2 . Primary outcome was any fracture, including vertebral, hip, and other fractures, defined using International Classification of Diseases, Tenth Revision codes. Subgroup analysis was performed by physical performance, including the single-leg stance test. Results: Among 551,548 participants included in the main study population, 80,514 developed any fracture over a median follow-up of 8.2 (interquartile range, 6.7–10.0) years. The prevalence of osteoporosis was 36%, and those with lower BMD showed higher eGFR and lower body mass index. Lower BMD was associated with a higher risk of any fracture, irrespective of eGFR, with nonsignificant interaction ( P for interaction = 0.54). Among participants with normal BMD, those with eGFR 2 showed a greater risk of hip fracture than those with normal eGFR (adjusted hazard ratio, 2.44 [1.88–3.18]), whereas vertebral fracture risks were similar across different eGFR categories at a given BMD status. Furthermore, a higher fracture risk with lower eGFR was more pronounced in women with poor static balance assessed by the single-leg stance test than in those with normal static balance. Conclusions: In postmenopausal women, lower BMD was associated with a higher fracture risk, irrespective of eGFR. However, at any given BMD, lower eGFR was associated with a greater risk for hip fracture, but not for vertebral fracture.
- 1 December 2025
- Published by Wolters Kluwer Health in Journal of the American Society of Nephrology
- Vol. 37 (5) , 984-994
Bone Mineral Density and the Risk of Fracture According to eGFR in Postmenopausal Women
Key Points: Lower bone mineral density was associated with a higher risk of fracture, irrespective of eGFR. At a similar bone mineral density, the fracture risk was higher with lower eGFR, more prominently for hip fractures than for vertebral fractures. The higher risk of fracture associated with lower eGFR was more pronounced in individuals with poor static balance. Background: Although both lower bone mineral density (BMD) and impaired kidney function are well-established risk factors for fracture, large-scale studies evaluating their effects and interaction on fracture, particularly site-specific fractures including vertebra and hip, are still limited. Methods: The main study population included female participants aged 66 years who underwent BMD assessment through dual-energy x-ray absorptiometry through the Korean National Screening Program between 2010 and 2016. BMD was categorized as normal, osteopenia, and osteoporosis on the basis of T -score. Kidney function was classified as eGFR ≥60, 45–59, and 2 . Primary outcome was any fracture, including vertebral, hip, and other fractures, defined using International Classification of Diseases, Tenth Revision codes. Subgroup analysis was performed by physical performance, including the single-leg stance test. Results: Among 551,548 participants included in the main study population, 80,514 developed any fracture over a median follow-up of 8.2 (interquartile range, 6.7–10.0) years. The prevalence of osteoporosis was 36%, and those with lower BMD showed higher eGFR and lower body mass index. Lower BMD was associated with a higher risk of any fracture, irrespective of eGFR, with nonsignificant interaction ( P for interaction = 0.54). Among participants with normal BMD, those with eGFR 2 showed a greater risk of hip fracture than those with normal eGFR (adjusted hazard ratio, 2.44 [1.88–3.18]), whereas vertebral fracture risks were similar across different eGFR categories at a given BMD status. Furthermore, a higher fracture risk with lower eGFR was more pronounced in women with poor static balance assessed by the single-leg stance test than in those with normal static balance. Conclusions: In postmenopausal women, lower BMD was associated with a higher fracture risk, irrespective of eGFR. However, at any given BMD, lower eGFR was associated with a greater risk for hip fracture, but not for vertebral fracture.
- Open Access
- 1 November 2025
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
- Vol. 44 (6) , 941-949
Impact of albuminuria on early-onset type 2 diabetes mellitus: a nationwide population-based study
Background: Early-onset diabetes mellitus has a significant lifetime burden and is associated with higher morbidity and mortality. Since insulin resistance is one of the mechanisms of podocyte injury, we aimed to evaluate the effect of albuminuria on newly developed early-onset type 2 diabetes mellitus (T2DM). Methods: We screened 6,891,399 subjects aged ≥20 and <40 years without a history of prediabetes or diabetes from the Korean National Health Insurance Service database between 2009 and 2012. A multivariate Cox proportional hazard model was used to identify the impact of albuminuria on early-onset T2DM. Results: Among a total of 5,383,779 subjects, 62,148 subjects (1.2%) developed early-onset diabetes over 7.3 ± 1.2 years. Albuminuria was significantly associated with early-onset T2DM (adjusted hazard ratio [aHR], 1.62; 95% confidence interval [CI], 1.55–1.70) after adjustment for age, sex, anthropometric data, physical exercise status, serum glucose, and total cholesterol. The risk of early-onset T2DM increased more in subjects with more components of metabolic syndrome (MetS). Among each component of MetS, hypertriglyceridemia was prominently associated with early-onset T2DM (aHR, 2.02; 95% CI, 1.81–2.25) in subjects with albuminuria. Conclusion: Dipstick albuminuria was significantly associated with early-onset T2DM in young adult populations. Close monitoring of albuminuria is warranted for disease risk modification, especially in subjects with MetS.
- 1 November 2025
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
- Vol. 44 (6) , 941-949
Open AccessImpact of albuminuria on early-onset type 2 diabetes mellitus: a nationwide population-based study
Background: Early-onset diabetes mellitus has a significant lifetime burden and is associated with higher morbidity and mortality. Since insulin resistance is one of the mechanisms of podocyte injury, we aimed to evaluate the effect of albuminuria on newly developed early-onset type 2 diabetes mellitus (T2DM). Methods: We screened 6,891,399 subjects aged ≥20 and <40 years without a history of prediabetes or diabetes from the Korean National Health Insurance Service database between 2009 and 2012. A multivariate Cox proportional hazard model was used to identify the impact of albuminuria on early-onset T2DM. Results: Among a total of 5,383,779 subjects, 62,148 subjects (1.2%) developed early-onset diabetes over 7.3 ± 1.2 years. Albuminuria was significantly associated with early-onset T2DM (adjusted hazard ratio [aHR], 1.62; 95% confidence interval [CI], 1.55–1.70) after adjustment for age, sex, anthropometric data, physical exercise status, serum glucose, and total cholesterol. The risk of early-onset T2DM increased more in subjects with more components of metabolic syndrome (MetS). Among each component of MetS, hypertriglyceridemia was prominently associated with early-onset T2DM (aHR, 2.02; 95% CI, 1.81–2.25) in subjects with albuminuria. Conclusion: Dipstick albuminuria was significantly associated with early-onset T2DM in young adult populations. Close monitoring of albuminuria is warranted for disease risk modification, especially in subjects with MetS.
- Open Access
- 22 August 2025
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
Machine learning-based utilization of lipid panels in predicting kidney dysfunction
Background: Dyslipidemia is a risk factor for atherosclerotic cardiovascular disease, but its relationship with kidney dysfunction varies depending on the patient and kidney status. Herein, we used a machine learning model to select lipid panels to improve the predictability of kidney dysfunction. Methods: A total of 9,403 patients whose lipid panels and low-density lipoprotein subfraction scores were measured were enrolled. The primary outcome was kidney outcome, which was defined as the development of end-stage kidney disease or a 50% decline in kidney function. The secondary outcome was a composite outcome, defined as the occurrence of either the kidney outcome or allcause death. Five machine learning models were utilized to predict 1-and 3-year outcomes. Feature ranking was employed to identify key factors contributing to model performance. Results: At 3 years, 117 patients (1.2%) experienced kidney outcomes, and 691 (7.4%) experienced composite outcomes. All of the models that used all the features demonstrated high predictive power, with the area under the receiver operating characteristic curve (AUROC) exceeding 0.85. Although the overall performance of the model that selectively uses lipid panels and creatinine was lower than that of models using all features, its predictive ability for kidney outcomes remained compatible, with AUROC values exceeding 0.78. Feature ranking analysis indicated that apolipoprotein A1, apolipoprotein B, and low-density lipoprotein cholesterol were significant contributors to model performance. Conclusion: Machine learning models incorporating lipid panels successfully predict the risk of kidney dysfunction, which can help clinicians in precisely identifying patients who are at risk of kidney dysfunction through lipid panel assessments.
- 22 August 2025
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
Open AccessMachine learning-based utilization of lipid panels in predicting kidney dysfunction
Background: Dyslipidemia is a risk factor for atherosclerotic cardiovascular disease, but its relationship with kidney dysfunction varies depending on the patient and kidney status. Herein, we used a machine learning model to select lipid panels to improve the predictability of kidney dysfunction. Methods: A total of 9,403 patients whose lipid panels and low-density lipoprotein subfraction scores were measured were enrolled. The primary outcome was kidney outcome, which was defined as the development of end-stage kidney disease or a 50% decline in kidney function. The secondary outcome was a composite outcome, defined as the occurrence of either the kidney outcome or allcause death. Five machine learning models were utilized to predict 1-and 3-year outcomes. Feature ranking was employed to identify key factors contributing to model performance. Results: At 3 years, 117 patients (1.2%) experienced kidney outcomes, and 691 (7.4%) experienced composite outcomes. All of the models that used all the features demonstrated high predictive power, with the area under the receiver operating characteristic curve (AUROC) exceeding 0.85. Although the overall performance of the model that selectively uses lipid panels and creatinine was lower than that of models using all features, its predictive ability for kidney outcomes remained compatible, with AUROC values exceeding 0.78. Feature ranking analysis indicated that apolipoprotein A1, apolipoprotein B, and low-density lipoprotein cholesterol were significant contributors to model performance. Conclusion: Machine learning models incorporating lipid panels successfully predict the risk of kidney dysfunction, which can help clinicians in precisely identifying patients who are at risk of kidney dysfunction through lipid panel assessments.
- Open Access
Association Between Healthy Dietary Patterns and Chronic Kidney Disease in Patients with Diabetes: Findings from Korean National Health and Nutrition Examination Survey 2019–2021
Background/Objectives: Although a healthy dietary pattern is a modifiable lifestyle factor in the prevention of chronic kidney disease (CKD), studies that investigate the association between a healthy diet and prevalent CKD in patients with diabetes, using the Korean Healthy Eating Index (KHEI), are lacking. Methods: This cross-sectional study included 1991 patients with diabetes from the eighth Korean National Health and Nutrition Examination Survey 2019–2021. A higher KHEI indicated healthier eating habits. CKD was defined as an estimated glomerular filtration rate < 60 mL/min/1.73 m2 or urine albumin–creatinine ratio ≥ 30 mg/g. The risk of prevalent CKD was evaluated according to the median KHEI value using logistic regression analysis adjusted for various clinicodemographic characteristics. Each KHEI component score was compared between those with and those without CKD, using the Student’s t-test. Results: Participants with a higher KHEI were older, with higher proportions of women, non-smokers, and non-alcoholics. A higher KHEI was significantly associated with a lower risk of prevalent CKD (adjusted odds ratio [aOR], 0.73 [0.58–0.93]). Subgroup analysis revealed stronger associations in those without hypertension status (aOR, 0.57 [0.37–0.87]) with at least high school education (aOR, 0.56 [0.38–0.81]). Moreover, patients with diabetes and CKD had significantly lower KHEI, particularly in the adequacy category components, including breakfast consumption, total fruit intake, and dairy product intake. Conclusions: A healthier dietary pattern was associated with a lower risk of prevalent CKD in patients with diabetes. Dietary intervention, which recommends the intake of breakfast, fruits, and dairy products, may be an effective strategy for CKD prevention.
Open AccessAssociation Between Healthy Dietary Patterns and Chronic Kidney Disease in Patients with Diabetes: Findings from Korean National Health and Nutrition Examination Survey 2019–2021
Background/Objectives: Although a healthy dietary pattern is a modifiable lifestyle factor in the prevention of chronic kidney disease (CKD), studies that investigate the association between a healthy diet and prevalent CKD in patients with diabetes, using the Korean Healthy Eating Index (KHEI), are lacking. Methods: This cross-sectional study included 1991 patients with diabetes from the eighth Korean National Health and Nutrition Examination Survey 2019–2021. A higher KHEI indicated healthier eating habits. CKD was defined as an estimated glomerular filtration rate < 60 mL/min/1.73 m2 or urine albumin–creatinine ratio ≥ 30 mg/g. The risk of prevalent CKD was evaluated according to the median KHEI value using logistic regression analysis adjusted for various clinicodemographic characteristics. Each KHEI component score was compared between those with and those without CKD, using the Student’s t-test. Results: Participants with a higher KHEI were older, with higher proportions of women, non-smokers, and non-alcoholics. A higher KHEI was significantly associated with a lower risk of prevalent CKD (adjusted odds ratio [aOR], 0.73 [0.58–0.93]). Subgroup analysis revealed stronger associations in those without hypertension status (aOR, 0.57 [0.37–0.87]) with at least high school education (aOR, 0.56 [0.38–0.81]). Moreover, patients with diabetes and CKD had significantly lower KHEI, particularly in the adequacy category components, including breakfast consumption, total fruit intake, and dairy product intake. Conclusions: A healthier dietary pattern was associated with a lower risk of prevalent CKD in patients with diabetes. Dietary intervention, which recommends the intake of breakfast, fruits, and dairy products, may be an effective strategy for CKD prevention.
- Open Access
- 31 March 2025
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
- Vol. 44 (2) , 265-276
Associations of metabolic variabilities and cardiovascular outcomes according to estimated glomerular filtration rate in chronic kidney disease: a nationwide observational cohort study
Background: The impact of baseline estimated glomerular filtration rate (eGFR) on the risk of adverse outcomes according to metabolic parameter variabilities in chronic kidney disease has rarely been investigated. Methods: We conducted a retrospective nationwide cohort study using the National Health Insurance System data in Korea from 2007 to 2013 to identify individuals with three or more health screenings. The metabolic components variability was defined as intraindividual variability between measurements using the variability independent of the mean. The metabolic variability score was defined as the total number of high-variability metabolic components. Multivariable-adjusted Cox regression analysis was conducted to evaluate the risks of all-cause mortality, myocardial infarction, and ischemic stroke. Results: During a mean follow-up of 6.0 ± 0.7 years, 223,531 deaths, 107,140 myocardial infarctions, and 116,182 ischemic strokes were identified in 9,971,562 patients. Low eGFR categories and higher metabolic variability scores were associated with a higher risk of adverse outcomes. The degree of association between metabolic variability and adverse outcomes was significantly larger in those with low eGFR categories than in those with preserved eGFR (p for interaction < 0.001). Representatively, those with high metabolic variability in the eGFR of <15 mL/min/1.73 m2 group showed a prominently higher risk for all-cause mortality (adjusted hazard ratio [aHR], 5.28; 95% confidence interval [CI], 4.02–6.94) when the degree was compared to the findings in those with preserved (eGFR of ≥60 mL/min/1.73 m2) kidney function (aHR, 2.55; 95% CI, 2.41–2.69). Conclusion: The degree of adverse association between metabolic variability and poor prognosis is accentuated in patients with impaired kidney function.
- 31 March 2025
- Published by The Korean Society of Nephrology in Kidney Research and Clinical Practice
- Vol. 44 (2) , 265-276
Open AccessAssociations of metabolic variabilities and cardiovascular outcomes according to estimated glomerular filtration rate in chronic kidney disease: a nationwide observational cohort study
Background: The impact of baseline estimated glomerular filtration rate (eGFR) on the risk of adverse outcomes according to metabolic parameter variabilities in chronic kidney disease has rarely been investigated. Methods: We conducted a retrospective nationwide cohort study using the National Health Insurance System data in Korea from 2007 to 2013 to identify individuals with three or more health screenings. The metabolic components variability was defined as intraindividual variability between measurements using the variability independent of the mean. The metabolic variability score was defined as the total number of high-variability metabolic components. Multivariable-adjusted Cox regression analysis was conducted to evaluate the risks of all-cause mortality, myocardial infarction, and ischemic stroke. Results: During a mean follow-up of 6.0 ± 0.7 years, 223,531 deaths, 107,140 myocardial infarctions, and 116,182 ischemic strokes were identified in 9,971,562 patients. Low eGFR categories and higher metabolic variability scores were associated with a higher risk of adverse outcomes. The degree of association between metabolic variability and adverse outcomes was significantly larger in those with low eGFR categories than in those with preserved eGFR (p for interaction < 0.001). Representatively, those with high metabolic variability in the eGFR of <15 mL/min/1.73 m2 group showed a prominently higher risk for all-cause mortality (adjusted hazard ratio [aHR], 5.28; 95% confidence interval [CI], 4.02–6.94) when the degree was compared to the findings in those with preserved (eGFR of ≥60 mL/min/1.73 m2) kidney function (aHR, 2.55; 95% CI, 2.41–2.69). Conclusion: The degree of adverse association between metabolic variability and poor prognosis is accentuated in patients with impaired kidney function.