Kidney Failure Risk Equation Research Articles

Heterogeneous Treatment Effects of Intensive Glycemic Control on Kidney Microvascular Outcomes and Mortality in ACCORD.

Identifying and quantifying treatment effect variation across patients is the fundamental challenge of precision medicine. Here we quantify heterogeneous treatment effects of intensive glycemic control in the Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial, considering three outcomes of interest-a composite kidney outcome (driven by macroalbuminuria), all-cause mortality, and first assisted hypoglycemic event. We demonstrate that the effects of intensive glycemic control vary with risk of kidney failure, as predicted by the kidney failure risk equation (KFRE). Participants at highest risk of kidney failure gain the largest absolute kidney benefit of intensive glycemic control but also experience the largest absolute risk of death and hypoglycemic events. Our findings illustrate the value of identifying clinically meaningful treatment heterogeneity, particularly when treatments have different effects on multiple end points. Clear criteria to individualize glycemic targets in patients with type II diabetes are lacking. In this post hoc analysis of the ACCORD, we evaluate whether the KFRE can identify patients for whom intensive glycemic control confers more benefit in preventing kidney microvascular outcomes. We divided the ACCORD trial population into quartiles on the basis of 5-year kidney failure risk using the KFRE. We estimated conditional treatment effects within each quartile and compared them with the average treatment effect in the trial. The treatment effects of interest were the 7-year restricted mean survival time (RMST) differences between intensive and standard glycemic control arms on ( 1 ) time-to-first development of severely elevated albuminuria or kidney failure and ( 2 ) all-cause mortality. We found evidence that the effect of intensive glycemic control on kidney microvascular outcomes and all-cause mortality varies with baseline risk of kidney failure. Patients with elevated baseline risk of kidney failure derived the most from intensive glycemic control in reducing kidney microvascular outcomes (7-year RMST difference of 114.8 [95% confidence interval 58.1 to 176.4] versus 48.4 [25.3 to 69.6] days in the entire trial population) However, this same patient group also experienced a shorter time to death (7-year RMST difference of -56.7 [-100.2 to -17.5] v. -23.6 [-42.2 to -6.6] days). We found evidence of heterogenous treatment effects of intensive glycemic control on kidney microvascular outcomes in ACCORD as a function of predicted baseline risk of kidney failure. Patients with higher kidney failure risk experienced the most pronounced reduction in kidney microvascular outcomes but also experienced the highest risk of all-cause mortality.

External validation of the KFRE and Grams prediction models for kidney failure and death in a Spanish cohort of patients with advanced chronic kidney disease.

The Kidney Failure Risk Equation (KFRE) is a 2- and 5-year kidney failure prediction model that is applied in chronic kidney disease (CKD) G3 + . The Grams model predicts kidney failure and death at 2 and 4years in CKD G4 + . There are limited external validations of the Grams model, especially for predicting mortality before kidney failure. We performed an external validation of the Grams and Kidney Failure Risk Equation prediction models in incident patients with CKD G4 + at Hospital Universitario Fundación Alcorcón, Spain, between 1/1/2014 and 31/12/2018, ending follow-up on 30/09/2023. Discrimination was performed calculating the area under the receiver-operating characteristiccurve. Calibration was assessed using the Hosmer-Lemeshow test and the Brier score. The study included 339 patients (mean age 72.2 ± 12.7years and baseline estimated glomerular filtration rate 20.6 ± 5.0ml/min). Both models showed excellent discrimination. The area under the curve (AUC) for Kidney Failure Risk Equation-2 and Grams-2 were 0.894 (95% CI 0.857-0.931) and 0.897 (95%CI 0.859-0.935), respectively. For Grams-4 the AUC was 0.841 (95%CI 0.798-0.883), and for Kidney Failure Risk Equation-5 it was 0.823 (95% CI 0.779-0.867). For death before kidney failure, the Grams model showed acceptable discrimination (AUC 0.708 (95% CI 0.626-0.790) and 0.744 (95% CI 0.683-0.804) for Grams-2 and Grams-4, respectively). Both models presented excellent calibration for predicting kidney failure. Grams model calibration to estimate mortality before kidney failure was also excellent. In all cases, Hosmer-Lemeshow test resulted in a p-value greater than 0.05, and the Brier score was less than 0.20. In a cohort of patients with CKD G4 + from southern Europe, both the Grams and Kidney Failure Risk Equation models are accurate in estimating the risk of kidney failure. Additionally, the Grams model provides a reliable estimate of the risk of mortality before kidney failure.

Strategies to Guide Preemptive Waitlisting and Equity in Waittime Accrual by Race/Ethnicity.

Use of eGFR to determine preemptive waitlisting eligibility may contribute to racial/ethnic disparities in access to waitlisting, which can only occur when the eGFR falls to ≤20 ml/min per 1.73 m 2 . Use of an alternative risk-based strategy for waitlisting may reduce these inequities ( e.g. , a kidney failure risk equation [KFRE] estimated 2-year risk of kidney failure) rather than the standard eGFR threshold for determining waitlist eligibility. Our objective was to model the amount of preemptive waittime that could be accrued by race and ethnicity, applying two different strategies to determine waitlist eligibility. Using electronic health record data, linear mixed models were used to compare racial/ethnic differences in preemptive waittime that could be accrued using two strategies: estimating the time between an eGFR ≤20 and 5 ml/min per 1.73 m 2 versus time between a 25% 2-year predicted risk of kidney failure (using the KFRE, which incorporates age, sex, albuminuria, and eGFR to provide kidney failure risk estimation) and eGFR of 5 ml/min per 1.73 m 2 . Among 1290 adults with CKD stages 4-5, using the Chronic Kidney Disease Epidemiology Collaboration equation yielded shorter preemptive waittime between an eGFR of 20 and 5 ml/min per 1.73 m 2 in Black (-6.8 months; 95% confidence interval [CI], -11.7 to -1.9), Hispanic (-10.2 months; -15.3 to -5.1), and Asian/Pacific Islander (-10.3 months; 95% CI, -15.3 to -5.4) patients compared with non-Hispanic White patients. Use of a KFRE threshold to determine waittime yielded smaller differences by race and ethnicity than observed when using a single eGFR threshold, with shorter time still noted for Black (-2.5 months; 95% CI, -7.8 to 2.7), Hispanic (-4.8 months; 95% CI, -10.3 to 0.6), and Asian/Pacific Islander (-5.4 months; -10.7 to -0.1) individuals compared with non-Hispanic White individuals, but findings only met statistical significance criteria in Asian/Pacific Islander individuals. When we compared potential waittime availability using a KFRE versus eGFR threshold, use of the KFRE yielded more equity in waittime for Black ( P = 0.02), Hispanic ( P = 0.002), and Asian/Pacific Islander ( P = 0.002) patients. Use of a risk-based strategy was associated with greater racial equity in waittime accrual compared with use of a standard single eGFR threshold to determine eligibility for preemptive waitlisting.

CKD stage-specific utility of two equations for predicting 1-year risk of ESKD.

The Kidney Failure Risk Equation (KFRE) and Kaiser Permanente Northwest (KPNW) models have been proposed to predict progression to ESKD among adults with CKD within 2 and 5 years. We evaluated the utility of these equations to predict the 1-year risk of ESKD in a contemporary, ethnically diverse CKD population. We conducted a retrospective cohort study of adult members of Kaiser Permanente Northern California (KPNC) with CKD Stages 3-5 from January 2008-September 2015. We ascertained the onset of ESKD through September 2016, and calculated stage-specific estimates of model discrimination and calibration for the KFRE and KPNW equations. We identified 108,091 eligible adults with CKD (98,757 CKD Stage 3; 8,384 CKD Stage 4; and 950 CKD Stage 5 not yet receiving kidney replacement therapy), with mean age of 75 years, 55% women, and 37% being non-white. The overall 1-year risk of ESKD was 0.8% (95%CI: 0.8-0.9%). The KFRE displayed only moderate discrimination for CKD 3 and 5 (c = 0.76) but excellent discrimination for CKD 4 (c = 0.86), with good calibration for CKD 3-4 patients but suboptimal calibration for CKD 5. Calibration by CKD stage was similar to KFRE for the KPNW equation but displayed worse calibration across CKD stages for 1-year ESKD prediction. In a large, ethnically diverse, community-based CKD 3-5 population, both the KFRE and KPNW equation were suboptimal in accurately predicting the 1-year risk of ESKD within CKD stage 3 and 5, but more accurate for stage 4. Our findings suggest these equations can be used in1-year prediction for CKD 4 patients, but also highlight the need for more personalized, stage-specific equations that predicted various short- and long-term adverse outcomes to better inform overall decision-making.

Colombian Validation of the Kidney Failure Risk Equation with Four Variables

Colombian Validation of the Kidney Failure Risk Equation with Four Variables

Kidney Failure Risk Equation Prediction in a Real-World Population with CKD

Kidney Failure Risk Equation Prediction in a Real-World Population with CKD

On the Accuracy of the Kidney Failure Risk Equation

On the Accuracy of the Kidney Failure Risk Equation

Using the kidney failure risk equation to predict end-stage kidney disease in CKD patients of South Asian ethnicity: an external validation study

BackgroundThe kidney failure risk equation (KFRE) predicts the 2- and 5-year risk of needing kidney replacement therapy (KRT) using four risk factors — age, sex, urine albumin-to-creatinine ratio (ACR) and creatinine-based estimated glomerular filtration rate (eGFR). Although the KFRE has been recalibrated in a UK cohort, this did not consider minority ethnic groups. Further validation of the KFRE in different ethnicities is a research priority. The KFRE also does not consider the competing risk of death, which may lead to overestimation of KRT risk. This study externally validates the KFRE for patients of South Asian ethnicity and compares methods for accounting for ethnicity and the competing event of death.MethodsData were gathered from an established UK cohort containing 35,539 individuals diagnosed with chronic kidney disease. The KFRE was externally validated and updated in several ways taking into account ethnicity, using recognised methods for time-to-event data, including the competing risk of death. A clinical impact assessment compared the updated models through consideration of referrals made to secondary care.ResultsThe external validation showed the risk of KRT differed by ethnicity. Model validation performance improved when incorporating ethnicity and its interactions with ACR and eGFR as additional risk factors. Furthermore, accounting for the competing risk of death improved prediction. Using criteria of 5 years ≥ 5% predicted KRT risk, the competing risks model resulted in an extra 3 unnecessary referrals (0.59% increase) but identified an extra 1 KRT case (1.92% decrease) compared to the previous best model. Hybrid criteria of predicted risk using the competing risks model and ACR ≥ 70 mg/mmol should be used in referrals to secondary care.ConclusionsThe accuracy of KFRE prediction improves when updated to consider South Asian ethnicity and to account for the competing risk of death. This may reduce unnecessary referrals whilst identifying risks of KRT and could further individualise the KFRE and improve its clinical utility. Further research should consider other ethnicities.

Proteinuria, measured or estimated albuminuria for risk prediction in patients with chronic kidney disease?

Although albuminuria is the gold standard for defining chronic kidney disease (CKD), total proteinuria has also been widely used in real-world clinical practice. Moreover, the superiority of the prognostic performance of albuminuria over proteinuria in patients with CKD remains inconclusive. Therefore, we aimed to compare the predictive performances of albuminuria and proteinuria in these patients. From the Korean Cohort Study for Outcome in Patients with CKD we included 2099 patients diagnosed with CKD grades 1-5 who did not require kidney replacement therapy. We measured the spot urine albumin:creatinine ratio (mACR) and protein:creatinine ratio (PCR) and estimated the ACR (eACR) using the PCR. Kidney failure risk equation (KFRE) scores were calculated using the mACR, PCR and eACR. The primary outcome was the 5-year risk of kidney failure with replacement therapy (KFRT). The eACR significantly underestimated mACR in patients with low albuminuria levels. The time-dependent area under the receiver operating characteristics curve showed excellent predictive performance for all KFRE scores from the mACR, PCR and eACR. However, eACR was inferior to mACR based on the continuous net reclassification index (cNRI) and integrated discrimination improvement index (IDI) in all CKD cause groups, except for the group with an unclassified aetiology. Moreover, the cNRI and IDI statistics indicated that both eACR and PCR were inferior to mACR in patients with low albuminuria (<30mg/g). Conversely, the predictive performance of PCR was superior in severe albuminuria and nephrotic-range proteinuria, in which the IDI and cNRI of the PCR were greater than those of the mACR. The mACR, eACR and PCR showed excellent performance in predicting KFRT in patients with CKD. However, eACR was inferior to mACR in patients with low albuminuria, indicating that measuring rather than estimating albuminuria is preferred for these patients.

Implementation of the Kidney Failure Risk Equation in a United States Nephrology Clinic

The kidney failure risk equation (KFRE) estimates a person's risk of kidney failure and has great potential utility in clinical care. We used mixed methods to explore implementation of the KFRE in nephrology clinics. KFRE scores were integrated into the electronic health record at Johns Hopkins Medicine and were displayed to nephrology providers. Documentation of KFRE scores increased over time, reaching 25% of eligible outpatient nephrology clinic notes at month 11. Three providers documented KFRE scores in >75% of notes, whereas 25 documented scores in<10% of notes. Surveys and focus groups of nephrology providers were conducted to probe provider views on the KFRE. Survey respondents (n= 25) reported variability in use of KFRE for decisions such as maintaining nephrology care, referring for transplant evaluation, or providing dialysis modality education. Provider perspectives on the use of KFRE, assessed in 2 focus groups of 4 providers each, included 3 common themes as follows: (i) KFRE scores may be most impactful in the care of specific subsets of people with chronic kidney disease (CKD); (ii) there is uncertainty about KFRE risk-based thresholds to guide clinical care; and (iii) education of patients, nephrology providers, and non-nephrology providers on appropriate interpretations of KFRE scores may help maximize their utility. Implementation of the KFRE was limited by non-uniform provider adoption of its use, and limited knowledge about utilization of the KFRE in clinical decisions.

Planning vascular access creation: The promising role of the kidney failure risk equation.

Planning for vascular access (VA) creation is essential in pre-dialysis patients although optimal timing for VA referral and placement is debatable. Guidelines suggest referral when eGFR is 15-20 mL/min/1.73 m2. This study aimed to validate the use of kidney failure risk equation (KFRE) in VA planning. Retrospective analysis of all adult patients with CKD who were referred for first VA placement, namely AVF or AVG, at a tertiary center, between January 2018 and December 2019. The four-variable KFRE was calculated. Start of KRT, mortality, and VA placement were assessed in a 2-year follow-up. We used Cox regression to predict KRT start and calculated the ROC curve. 256 patients were included and 64.5% were male, mean age was 70.4 ± 12.9 years and mean eGFR was 16.09 ± 10.43 mL/min/1.73 m2. One hundred fifty-nine patients required KRT (62.1%) and 72 (28.1%) died in the 2-year follow-up. The KFRE accurately predicted KRT start within 2-years (38.3 ± 23.8% vs 17.6 ± 20.9%, p < 0.001; HR 1.05 95% CI (1.06-1.12), p < 0.001), with an auROC of 0.788 (p < 0.001, 95% CI (0.733-0.837)). The optimal KFRE cut-off was >20%, with a HR of 9.2 (95% CI (5.06-16.60), p < 0.001). Patients with KFRE ⩾ 20% had a significant lower mean time from VA consult to KRT initiation (10.8 ± 9.4 vs 15.6 ± 10.3 months, p < 0.001). On a sub-analysis of patients with an eGFR < 20 mL/min/1.73 m2, a KFRE ⩾ 20% was also a significant predictor of 2-year start of KRT, with an HR of 6.61 (95% CI (3.49-12.52), p < 0.001). KFRE accurately predicted 2-year KRT start in this cohort of patients. A KFRE ⩾ 20% can help to establish higher priority patients for VA placement. The authors suggest referral for VA creation when eGFR < 20 mL/min/1.73 m2 and KFRE ⩾ 20%.

Combining robust urine biomarkers to assess chronic kidney disease progression.

Urinary biomarkers may improve the prediction of chronic kidney disease (CKD) progression. Yet, data reporting the applicability of most commercial biomarker assays to the detection of their target analyte in urine together with an evaluation of their predictive performance are scarce. 30 commercial assays (ELISA) were tested for their ability to quantify the target analyte in urine using strict (FDA-approved) validation criteria. In an exploratory analysis, LASSO (Least Absolute Shrinkage and Selection Operator) logistic regression analysis was used to identify potentially complementary biomarkers predicting fast CKD progression, determined as the 51CrEDTA clearance-based measured glomerular filtration rate (mGFR) decline (>10% per year) in a subsample of 229 CKD patients (mean age, 61 years; 66% men; baseline mGFR, 38mL/min) from the NephroTest prospective cohort. Among the 30 assays, directed against 24 candidate biomarkers, encompassing different pathophysiological mechanisms of CKD progression, 16 assays fulfilled the FDA-approved criteria. LASSO logistic regressions identified a combination of five biomarkers including CCL2, EGF, KIM1, NGAL, and TGF-α that improved the prediction of fast mGFR decline compared to the kidney failure risk equation variables alone: age, gender, mGFR, and albuminuria. Mean area under the curves (AUC) estimated from 100 re-samples was higher in the model with than without these biomarkers, 0.722 (95% confidence interval 0.652-0.795) vs. 0.682 (0.614-0.748), respectively. Fully-adjusted odds-ratios (95% confidence interval) for fast progression were 1.87 (1.22, 2.98), 1.86 (1.23, 2.89), 0.43 (0.25, 0.70), 1.10 (0.71, 1.83), 0.55 (0.33, 0.89), and 2.99 (1.89, 5.01) for albumin, CCL2, EGF, KIM1, NGAL, and TGF-α, respectively. This study provides a rigorous validation of multiple assays for relevant urinary biomarkers of CKD progression which combination may improve the prediction of CKD progression. This work was supported by Institut National de la Santé et de la Recherche Médicale, Université de Paris, Assistance Publique Hôpitaux de Paris, Agence Nationale de la Recherche, MSDAVENIR, Pharma Research and Early Development Roche Laboratories (Basel, Switzerland), and Institut Roche de Recherche et Médecine Translationnelle (Paris, France).

#5522 USING THE KIDNEY FAILURE RISK EQUATION TO PREDICT END-STAGE KIDNEY DISEASE IN CKD PATIENTS OF SOUTH ASIAN ETHNICITY: AN EXTERNAL VALIDATION STUDY

Abstract Background and Aims The Kidney Failure Risk Equation (KFRE) predicts the 2- and 5-year risk of needing kidney replacement therapy (KRT) using four risk factors – age, sex, urine albumin-to-creatinine ratio (ACR), and creatinine-based estimated glomerular filtration rate (eGFR). Although the KFRE has been recalibrated in a UK cohort, this did not consider minority ethnic groups. Further validation of the KFRE in different ethnicities is a research priority. The KFRE also does not consider the competing risk of death, which may lead to overestimation of KRT risk. This study externally validates the KFRE for patients of South Asian ethnicity and compares methods for accounting for ethnicity and the competing event of death. Method Data were gathered from an established UK cohort containing 35,539 individuals diagnosed with chronic kidney disease. The KFRE was externally validated and updated in several ways taking into account ethnicity, using recognised methods for time-to-event data, including the competing risk of death. A clinical impact assessment compared the updated models through consideration of referrals made to secondary care. Results The external validation showed risk of KRT differed by ethnicity. Model validation performance improved when incorporating ethnicity and its interactions with ACR and eGFR as additional risk factors. Further, accounting for the competing risk of death improved prediction. Using a criteria of 5 year ≥5% predicted KRT risk, the competing risks model resulted in an extra 3 unnecessary referrals (0.59% increase) but identified an extra 1 KRT case (1.92% decrease) compared to the previous best model. A hybrid criteria of predicted risk using the competing risks model and the previous guidelines should be used in referrals to secondary care. Conclusion The accuracy of KFRE prediction improves when updated to consider South Asian ethnicity and to account for the competing risk of death. This may reduce referrals whilst identifying risks of KRT and could further individualise the KFRE and improve its clinical utility. Further research should consider other ethnicities.

#5227 KIDNEY FAILURE RISK EQUATION (KFRE) VS GRAMS SCORE, WHICH ONE PREDICTS BETTER THE INITIATION OF RENAL REPLACEMENT THERAPY?

Abstract Background and Aims In patients with Advanced Chronic Kidney Disease (ACKD) stage G4 it is necessary to use prognostic tools to predict the need for Kidney Replacement Therapy (KRT), especially in elderly patients, the most used is the Kidney Failure Risk Equation (KFRE). The Grams Score (GS) predicts the risk of KRT, cardiovascular events and mortality, providing better prediction for the choice of KRT modality but requires more parameters in its equation. Ours objective was compare both KFRE and GS prognostic equations to validate which one better predicts the onset of KRT. Method Descriptive, retrospective study of a cohort of patients older than 65 years with G4 CKD attending for the first time in 2016–2017. Follow-up for 5 years or first clinical event defined as need for KRT (including Conservative Renal Treatment with GFR = &amp;lt;8 ml/min/1.72m2) or death. Variables needed to calculate KFRE and GS were collected, as well as events occurred. Results 271 patients who met the inclusion criteria were analyzed. The clinical characteristics are shown in Table 1. The Grams model showed good discrimination for initiating KRT at 2 and 4 years, AUC 0.84 [95%CI 0.77-0.91] and AUC 0.81 [95%CI 0.75-0.87], respectively. The ROC curves presented by both equations showed good discrimination, AUC 0.82 [95%CI 0.74-0.91] and AUC 0.80 [95%CI 0.74-0.87].When comparing the need for 2-year KRT with both equations, we observed both ROC curves were similar (p = 0.356). Table 2 shows results from logistic regression analysis. For the 2-year KRT event by Grams, patients with a score &amp;gt; = 17.85% were 11.53 [95%CI 5.16-27.78] times more likely to initiate KRT. However, compared to KFRE with a score &amp;gt; = 20.77%, they had 17.53 [95%CI 7.59-40.47] times higher probability of KRT (both p&amp;lt;0.001). When we compared both equations in multivariate analysis only the KFRE was significant (ODR 0.217 (95%CI 0.87-0.54). Conclusion In our population, both prognostic equations showed good discrimination to program initiation of KRT. However, the GS could underestimate this need while the KFRE seems to discriminate it better.

#4918 IS THE KIDNEY FAILURE RISK EQUATION VALID IN PREDICTING END STAGE KIDNEY DISEASE IN ADULTS WITH GLOMERULOPATHIES?

Abstract Background and Aims The Kidney Failure Risk Equation (KFRE) is a clinical tool that predicts the 2- and 5- year risk of progression to end stage kidney disease (ESKD) in patients with chronic kidney disease (CKD) stages 3a-5. The equation's accuracy and its predictive performance in subjects with glomerulopathies were not properly evaluated and validated. The current study examined the 4 variable KFRE in subjects with advanced CKD from glomerulopathy etiologies by evaluating discrimination and calibration at 2 and 5 years. Method This retrospective, single-center, cohort study included 558 subjects who were diagnosed by kidney biopsy with primary or secondary glomerulopathies between 1st January 2008 and 31st December 2016 and followed until 31st December 2021 for a mean follow-up time of 85.3 (95%CI 78.9 to 91.8) months. Patients with inadequate biopsy samples, histological findings other than glomerulopathy, those with missing data, and those with eGFR &amp;gt; 60 ml/min/1.73 m2 were excluded. The 4-variable KFRE using eGFR, urinary albumin to creatinine ratio (uACR), age, and sex was calculated using the data from the first visit. The primary outcome of the study was the need for renal replacement therapy (RRT) initiation (dialysis or kidney transplant). The area under the receiver operator characteristic curve (AUC) and calibration plots were used to measure discrimination and calibration of the KFRE in specific glomerulopathy etiologies: IgA nephropathy, diabetic nephropathy, amyloidosis, endocapillary and crescentic glomerulonephritis, lupus nephritis, minimal change disease, membranous nephropathy, focal segmental glomerulosclerosis and membranoproliferative glomerulonephritis. Results In this cohort, most of the patients were males (57.7%) and the median age was 53 (95%CI 53 to 57) years. The median eGFR was 30,5 (95%CI 28 to 32,6) ml/min/ 1.73 m2 and the median uACR 1932 (95% CI 1633 to 2200) mg/g. The most common glomerulopathies were IgA nephropathy (21.3%), diabetic nephropathy (13.4%), and membrano-proliferative glomerulonephritis (9.5%). The median 2-year and 5-year KFRE score was 2.2 (95%CI 1.8 to 2.7) % and 18.9 (95%CI 17.8 to 19.7) % respectively. During the first 2 years of follow-up 154 (27.5%) subjects needed RRT and 93 (16.6%) subjects died, while 218 (39%) started RRT and 108 (19.3%) died within 5 years from the kidney biopsy. The 4-variable KFRE provided good discrimination in the whole cohort with an AUC of 0.728 (95% CI 0.686-0.770) for predicting ESRD at 2-years and 0.725 (95% CI 0.686-0.767) at 5 years (Figure 1A). There was also a good to excellent discrimination of 2-years and 5-years KFRE across all glomerulopathy etiologies, with statistically significant p-values (p&amp;lt;0.05), with the exception of diabetic nephropathy and endocapillary GN which had a non-significant AUC (Figure 2). Calibration plots were adequate both overall and across glomerulopathy etiologies; however, the predicted risks for kidney failure were overestimated across CKD etiologies, especially in those with low to moderate risk in the 2-years model. Notably the calibration plot for the 5-years KFRE showed that the predicted risk was near the observed risk across all glomerulopathies (Figure 1B). Conclusion The 4 variable-KFRE seems to be a good predictive tool in patients with glomerulopathies both for 2 and 5-years, except for diabetic nephropathy and endocapillary glomerulonephritis.

#2654 USE OF SUPERVISED DEEP LEARNING ALGORITHM TO PREDICT RISK OF RENAL REPLACEMENT THERAPY(RRT) IN PATIENTS WITH CHRONIC KIDNEY DISEASE (CKD)

Abstract Background and Aims Chronic kidney disease (CKD) is one of the most common causes of mortality, affecting around 10% adults worldwide [1]. Although statistical models for predicting risk of renal replacement therapy (RRT) have been developed for a decade [2], referral of patients with CKD to nephrology service is often based on clinical experience of primary care physicians. The use of deep learning algorithms (DLAs) allow clinicians to capture complex, multidimensional, non-linear relationships instead of relying on linear relationships between independent variables and outcome. Our study aims to develop a DLA that has at least non-inferior performance compared to the Kidney Failure Risk Equation (KFRE), which is a well-established and validated risk prediction tool [3]. Method This is a retrospective cohort study carried out in 3 major acute hospitals in Hong Kong providing a total of 3000 beds from Jan 1, 2009 to Mar 31, 2022. All patients aged &amp;gt; 18 with an estimated glomerular filtration rate (eGFR)&amp;lt;30ml/min/1.73 m2 according to the CKD-EPI formula, who attended follow-up for at least 3 months in nephrology clinic of the 3 hospitals, were recruited. Those who were on chronic RRT, received renal transplantation or had an eGFR&amp;lt;15 ml/min/1.73 m2 before referral were excluded. Supervised DLAs of different structures and their combinations were created and trained. Data in the test set were fed into models to predict the risk of requiring RRT in 2 years and 5 years. Predictive performance of these models were compared with that of KFRE [3]. Results 4992 patients were recruited in the study. Data of 499 patients were isolated as test set and were not used for model training. 1576 patients progressed to stage 5 CKD during their follow-up, and 989 patients required initiation of RRT during the study timeframe. When compared with KFRE (4-variable: ROC-AUC = 0.84, 95%CI:0.835-0.852; 8-variable: ROC-AUC = 0.84, 95%CI:0.830-0.847), almost all DLAs showed statistically significant superior robustness in predicting the risk of requiring RRT (Figure 1). No significant difference was found between performance of DLAs combining different neural network layers and those with single structures (CNN+LSTM+ANN layers ROC-AUC = 0.90, 95%CI:0.896-0.902; CNN ROC-AUC = 0.91, 95%CI:0.907-0.914) (Table 1). Conclusion The use of DLAs provided better prediction in the risk of requiring RRT when compared with KFRE.

#5059 EXTERNAL VALIDATION OF THE KFRE AND GRAMS PREDICTION MODELS FOR DEATH AND KRT IN A SPANISH POPULATION WITH ADVANCED CHRONIC KIDNEY DISEASE

Abstract Background and Aims The Kidney Failure Risk Equation (KFRE) is used to predict the risk of kidney replacement therapy (KRT) initiation in the following 2 and 5 years, in patients with chronic kidney disease (CKD) stages G3-G5. The Grams model is applied exclusively to stage G4-G5 patients who have a higher risk of dying or requiring KRT. This model predicts both events, KRT and death, at 2 and 4 years, but unlike the KFRE, it considers the patient's death as a competing event with respect to the start of RRT. It has been suggested that the Grams model makes a more accurate prediction of the onset of KRT in the long term, since by including mortality as a competing event it does not overestimate the risk of KRT. However, there are few external validations of the Grams model to predict mortality in patients with CKD G4+. We performed an external validation of both models with respect to the start of KRT and mortality in a Spanish population with CKD G4+, followed up prospectively during 4-9 years. Method We conducted a prospective cohort analysis of incident patients followed in the Advanced Chronic Kidney Disease clinic of the Hospital Universitario Fundación Alcorcón, Spain between 1-1-2014 and 31-12-2018 who had CKD G4-G5. Clinical data was registered prospectively in a database at each visit to the clinic. Follow-up ended on 31-12-2022. For each patient, the follow-up time ranged from 4 to 9 years. The outcomes were: observed incidence of KRT (haemodialysis, peritoneal dialysis, or pre-emptive kidney transplantation) by 2, 4 and 5 years and death at 2 and 4 years before starting KRT. The predictors used in the study were calculated at the time of initial clinic referral and included the 2-year and 4-year Grams’ calculator risk scores (Grams-2 and Grams-4, respectively) for KRT and death and the 2-year and 5-year 4-variable KFRE scores for KRT (KFRE-2 and KFRE-5 respectively). We performed calibration and discrimination analyses to evaluate the performance of both predictive models. Discrimination was assessed by calculating the area under the ROC curve (C-statistic with 95% confidence interval). Calibration was assessed by using the Hosmer-Lemeshow test, through calculation of the slope and intercept, and visually by generating a calibration plot, evaluating the level of agreement between predicted probabilities versus observed outcomes. Overall model performance was evaluated using the Brier score as a composite measure of both model discrimination and calibration. Results We studied 347 patients, 31.1% were women, with a mean age of 72.1 ± 12.7 years, 52.4% with cardiovascular disease and 58.8% diabetics. At the start, the mean eGFR was 20.7 ± 5.0 ml/min and the median urine albumin-creatinine ratio was 327 (IQR 52-1118) mg/g. At 2, 4 and 5 years the percentage of patients who required KRT was 20.2%, 38.3% and 45.7% respectively, while 12.7% and 23.6% died at 2 and 4 years respectively, before starting KRT. For KTR both models had an excellent discrimination. For KFRE-2 and Grams-2 the AUC was 0.896 (95% CI 0.858-0.933) and 0.904 (95% CI 0.866-0.941) respectively, for Grams-4 the AUC was 0.842 (95% CI 0.801-0.884), and for KFRE-5 the AUC was 0.805 (95% CI 0.751-0.859). For death before KTR the Grams model demonstrated an acceptable discrimination, with an AUC of 0.726 (95% CI 0.646-0.806) and 0.749 (95% CI 0.690-0.809) for Grams-2 and Grams-4 respectively. There was excellent calibration for KRT for both models, the Hosmer-Lemeshow test presented a p&amp;gt;0.05 in all cases, the Brier score was less than 0.20. The adjustment was very precise and only in the event of estimated risks greater than 70% at 2 and 4 years is the observed risk overestimated. The calibration of the Grams model to estimate mortality before starting KTR was also excellent, although for estimated risks greater than 50% at 4 years the observed risk is underestimated. Conclusion In a Spanish cohort of patients with CKD G4+, the Grams and KFRE models adequately estimate the risk of KRT. The Grams model provides an acceptable estimate of the risk of death before starting KRT at both 2 and 4 years. It can be considered for treatment planning and information for patients with CKD G4+.

#4727 FLOZINATION: A ROLLING QUALITY IMPROVEMENT PROGRAMME

Abstract Background and Aims Sodium glucose linked transporter-2 inhibitors (SGLT2i) reduce renal and cardiovascular end points in people with chronic kidney disease (CKD), both with and without diabetes. Despite exciting data from the CREDENCE and DAPA-CKD trials, implementation of new evidence to every day clinical practice can be challenging. We present the results of a rolling quality improvement project regarding SGLT2i prescription. The aim of the project was to support clinicians in the evidence based prescribing of SGLT2i for CKD. Method Three renal units who share a single electronic clinical database agreed a joint protocol and staged implementation programme. These tertiary referral renal units cover a population of around 2.3 million people. The important timeline regarding SGLT2i licensing and interventions is shown in Figure 1. Interventions were as follows: 1. Identification of patients meeting the licensing criteria for prescription of canagliflozin for CKD with diabetes. 2. Addition of an alert to the electronic patient record. 3. SGLT2i protocol developed and advertised via poster in outpatient clinic sites. 4. Evaluation of clinician attitude to prescribing. 5. Measurement of number of patients meeting the licensing criteria for prescription of dapagliflozin for CKD with and without diabetes. Measurement of SGLT2i prescription was audited from the electronic record. Results In the first wave of the programme, 326 patients were identified as suitable under the initial licensing criteria for canagliflozin, and electronic alerts were added to the records of these patients. When measuring number of patients who may be suitable under the dapagliflozin licensing, there were 562 patients with diabetes and 5262 without diabetes. In a survey of clinician attitudes, 94% suggested they felt well equipped to prescribe SGLT2i. Prescribing of SGLT2i across time is shown in Figure 2. 1146 patients have been prescribed SGLT2i. Age was 64±13 years, and the majority were male (68%) with type 2 diabetes mellitus (61%). Most (73.6%) were treated with angiotensin converting enzyme inhibitor (ACEi) or angiotensin receptor blocker (ARB). More than half (54%) of patients live in areas with high levels of socio-economic deprivation (Scottish Index of Multiple Deprivation quintiles 1 or 2). Estimated glomerular filtration rate was 40.9±23.5ml/min/1.73 m2 and Kidney Failure Risk Equation (KFRE) 5 year risk of end stage kidney disease (ESKD) was 23.2±28.2%. In comparison with the general outpatient clinic population, the distribution of socioeconomic deprivation was similar, but a higher proportion were female (46%). Conclusion An iterative quality improvement project was designed around the evolving drug licensing of SGLT2i and capitalised on local strengths, including an effective and well used clinical electronic database shared across renal units. Clinicians have been supported in SGLT2i prescribing with highly visible clinical protocols, and electronic alerts to highlight candidate patients. A high level of SGLT2i prescribing has been achieved in a population at high risk of ESKD. Further interventions should focus on prescribing in groups where gaps have been identified – such as women and those without diabetes. Other units would be recommended to capitalise on existing strengths, exploit the use of clinical databases, and ensure protocols are inclusive and well-advertised in order to optimise evidence based treatment of CKD.

#4175 PERFORMANCES OF THE 5-YEAR KIDNEY FAILURE RISK EQUATION IN A TERTIARY SINGLE CENTER CHRONIC KIDNEY DISEASE COHORT (CKD CAREMEAU)

Abstract Background and Aims Chronic kidney disease (CKD) is a common disease with a heterogeneous course. The Kidney Failure Risk Equation (KFRE) is designed to predict 5-year End stage renal disease (ESRD). This score has shown poor performance in predicting 5-years ESRD in elderly patients, probably because of a competitive risk with death. Indeed, patients with type 2 diabetes are numerous and older than non-diabetic patients, with higher risks of death, and thus à higher competitive risk. In this context, we aimed to evaluate the performance of the KFRE score at 5 years, in a cohort from a tertiary center, according to diabetic status. Method The CKD Caremeau (CKDC) cohort is a single-center tertiary cohort of adults seen by a nephrologist for CKD. We studied CKDC patients included between January 2008 and December 2017 and followed them. We excluded patients younger than 45 years. KFRE score covariates were collected at the first visit, and Renal replacement therapy (RRT) (dialysis or kidney transplantation) and death before ESRD were collected during follow-up through December 2022. Multiple imputation (Monte Carlo) was used for missing albuminuria. Score performance was calculated with discrimination (area under curve (AUC)) and calibration (observed versus predicted risks), according to diabetic status, at 5 years. Results Of the 3046 patients included, 1288 (42%) had diabetes. 558 (18%) albuminuria were missing and imputed. For diabetic patients, median follow-up time was 5.3 [3.0–7.6] years, median age was 73 [66–80] years, 843 (65%) patients were males, median eGFR was 38 [27–50], median albuminuria was 204 [57–671] mg/g, 177 (14%) developed ESRD, and 398 (30%) died, with a median 5-years KFRE score of 4 [0.65–17.6] %. For non-diabetic patients, median time of follow-up was 5.5 [3.3–8.2] years, median age was 72 [63–81] years old, 1027 (58%) were males, median eGFR was 40 [27–53], median albuminuria was 113 [38–399] mg/g, 205 (12%) experimented ESRD, and 501 (29%) died, with a median 5-year KFRE score of 2 [0.18–14] %. Discrimination was not modified by diabetic status at 5 years (p = 0.67). Calibration was also unaffected by diabetic status, with an overall overestimation at 5 years. Conclusion The performance of the KFRE score was not modified by diabetic status, meaning that age is probably more important than diabetic status for the competitive risk of death in CKD patients.

Chronic kidney disease in the elderly and frail patient: perspectives with opinions and comments.

Chronic kidney disease is common in elderly and frail people. The importance of age in staging chronic kidney disease is discussed as well as the possible constraints of staging what is actually a 'continuum' of disease progression. Frailty is a biological state characterized by the decline of several physiological systems and strongly correlated with adverse health outcomes, including mortality. Frailty is measured by the Comprehensive Geriatric Assessment, which focuses on quantitative rating scales that determine not only the clinical profile and pathological risk of frail individuals, but also their residual capacities, functional status, and quality of life. There is circumstantial evidence that Comprehensive Geriatric Assessment can improve both survival and quality of life in elderly chronic kidney disease patients. Despite the long list of emerging risk factors and markers of chronic kidney disease progression, it is the authors' opinion that a single biochemical parameter can hardly cover the complexity of chronic kidney disease in elderly and frail patients. Among the numerous clinical scores proposed, the European Renal Best Practice guidelines recommend the Renal Epidemiology and Information Network score and the Kidney Failure Risk Equations. The former provides a reasonable estimate of short-term mortality risk, the latter provides the risk of chronic kidney disease progression. In conclusion, the elderly individual with advanced chronic kidney disease is often comorbid and frail with peculiarities in terms of disease grading, clinical assessment and monitoring. The time has come to reshape the care of this growing number of patients by focusing on multidisciplinary teams both in the hospital and in the community.