Risk Of Renal Replacement Therapy Research Articles

Deep learning algorithms for predicting renal replacement therapy initiation in CKD patients: a retrospective cohort study

BackgroundChronic kidney disease (CKD) requires accurate prediction of renal replacement therapy (RRT) initiation risk. This study developed deep learning algorithms (DLAs) to predict RRT risk in CKD patients by incorporating medical history and prescriptions in addition to biochemical investigations.MethodsA multi-centre retrospective cohort study was conducted in three major hospitals in Hong Kong. CKD patients with an eGFR < 30ml/min/1.73m2 were included. DLAs of various structures were created and trained using patient data. Using a test set, the DLAs' predictive performance was compared to Kidney Failure Risk Equation (KFRE).ResultsDLAs outperformed KFRE in predicting RRT initiation risk (CNN + LSTM + ANN layers ROC-AUC = 0.90; CNN ROC-AUC = 0.91; 4-variable KFRE: ROC-AUC = 0.84; 8-variable KFRE: ROC-AUC = 0.84). DLAs accurately predicted uncoded renal transplants and patients requiring dialysis after 5 years, demonstrating their ability to capture non-linear relationships.ConclusionsDLAs provide accurate predictions of RRT risk in CKD patients, surpassing traditional methods like KFRE. Incorporating medical history and prescriptions improves prediction performance. While our findings suggest that DLAs hold promise for improving patient care and resource allocation in CKD management, further prospective observational studies and randomized controlled trials are necessary to fully understand their impact, particularly regarding DLA interpretability, bias minimization, and overfitting reduction. Overall, our research underscores the emerging role of DLAs as potentially valuable tools in advancing the management of CKD and predicting RRT initiation risk.

The renal outcome post contrast exposure in patient with diabetes and SGLT2 inhibitor

Abstract Introduction Contrast-induced nephropathy (CIN) is increasingly prevalent as the increased age and comorbidities. Though most CIN can be reversible, some may progress to acute kidney disease (AKD) and subsequent chronic kidney disease (CKD)1-3. Sodium–glucose cotransporter-2 (2SGLT) inhibitor has been known to bring better renal outcomes 4-7. However, whether it affect contrast-induced kidney injury is not known well. we Purpose We aimed to investigate the renal outcomes post-contrast exposure in patients with diabetes and SGLT2 inhibitor. Materials and methods We used the Taipei Medical University Clinical Research Database (TMUCRD), composed of clinical data from 3 teaching hospitals. which stores electronic health data of 3 million patients. Patients with diabetes and exposure to contrast in CT-imaging studies or catheter-based angiography from 2016 to 2020 were included. The primary outcome was major kidney adverse event (MAKE), which included acute kidney disease (AKD), chronic kidney disease (CKD), renal replacement therapy (RRT), new onset of urinary albumin-creatinine ratio (uACR), eGFR decline ≥ 40% and all-cause mortality. We used overlap weighting to reduce confounding factors, as in observational studies. Results A total of 12,421 patients were included in this study, of them, 920 and 11501 patients were categorized to SGLT2 inhibitor users and non SGLT2 inhibitor users, respectively. SGLT2 inhibitor user had lower MAKE risk as compared with non-SGLT2 inhibitor i user (incidence rate: 37.9 v.s. 53.4 per 1,000 person months, P value = 0.0002) after exposure to contrast media. The incidence rate of AKD, CKD, and eGFR decline ≥ 40% were significantly lower in SGLT2 inhibitor user. However, there were no significantly different in the risk of RRT, new onset of uACR or all-cause mortality. Conclusions In this retrospective cohort study, we found that SGLT2 inhibitor user was associated with lower MAKE comparing with non-SGLT2 inhibitor user after contrast exposure in patients with diabetes.Outcomes of DM patients with PCI or contKaplan-Meier plot of major adverse kidne

Acute Kidney Injury and Sepsis after Cardiac Surgery: The Roles of Tissue Inhibitor Metalloproteinase-2, Insulin-like Growth Factor Binding Protein-7, and Mid-Regional Pro-Adrenomedullin.

Identifying a panel of markers detecting kidney injury before the glomerular filtration rate reduction is a challenge to improving the diagnosis and management of acute kidney injury (AKI) in septic patients. This study evaluated the roles of tissue inhibitor metal proteinase-2, insulin growth factor binding protein-7 (TIMP2*IGFBP7), and mid-regional pro-adrenomedullin (MR-proADM) in patients with AKI. This study was prospectively conducted in an intensive care unit (ICU) enrolling 230 patients who underwent cardiac surgery. Biomarkers were evaluated before and after 4 h of the cardiac surgery. Whereas urine and creatinine alterations appeared at 23.2 (12.7-36.5) hours after cardiac surgery, urinary TIMP2*IGBP7 levels were higher at 4 h in AKI patients (1.1 ± 0.4 mg/L vs. 0.08 ± 0.02 mg/L; p < 0.001). Its concentration > 2 mg/L increases AKI risk within the following 24 h, clearly identifying the population at high risk of renal replacement therapy (RRT). In patients with sepsis, MR-proADM levels were 2.3 nmol/L (0.7-7.8 nmol/L), with the highest values observed in septic shock patients (5.6 nmol/L (3.2-18 nmol/L)) and a better diagnostic profile than procalcitonin and C-reactive protein to identify septic patients. MR-proADM values > 5.1 nmol/L and urine TIMP2*IGBP7 levels > 2 mg/L showed a significantly faster progression to RRT, with a mean follow-up time of 1.1 days. TIMP2*IGBP7 and MR-proADM precociously diagnose AKI in septic patients after cardiac surgery, giving prognostic information for RRT requirement.

Alactic base excess predicts the use of renal replacement therapy in patients with septic shock

BackgroundAlactic base excess (ABE) is a novel biomarker that estimates the renal capability of handling acid–base alterations during the sepsis. Hence, the aim of this study was to evaluate the use of ABE to predict the renal replacement therapy (RRT) in patients with septic shock.MethodsA total of 164 patients admitted to the intensive care units with a diagnosis of septic shock according to the third international consensus on sepsis and septic shock (Sepsis-3) were included. This study was retrospective, single center, and conducted between January 1, 2016, and December 31, 2020. The individuals were stratified in patients who did [n = 68] or did not [n = 96] receive the RRT. The diagnostic performed of the variables for the classification into patients who required RRT was evaluated by receiver operating characteristic (ROC) analysis and area under curve (AUC) was calculated. Univariate and multivariate logistic regression models were used to identify risk factors for RRT.ResultsThe median age of the patients was 59 years and female sex (51.8%) predominated. ABE (odds ratio [OR] 1.2270, [95% confidence interval [CI] 1.0453–1.4403], p = 0.0124) and urea (OR 1.0114, [95% CI 1.0053–1.0176], p = 0.0002) were associated with risk of RRT. HCO3− (OR 0.6967, [95% CI 0.5771–0.8410], p = 0.0002) was a protective factor of RRT. ABE (AUC = 0.649, p < 0.0008), HCO3− (AUC = 0.729, p < 0.0001), and urea (AUC = 0.76, p < 0.0001) had a cutoff point of ≤ − 5.7 mmol/L, ≤ 19.36 mmol/L and > 75 mg/dL, respectively.ConclusionAlthough HCO3− is associated with low risk, ABE and urea are independent risk factors for RRT in the patients with septic shock.

#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.

#2969 IS DIABETES MELLITUS ASSOCIATED WITH WORSE KIDNEY OUTCOME IN PATIENTS WITH GLOMERULOPATHIES?

Abstract Background and Aims Diabetes mellitus (DM) is the leading cause of end stage kidney disease and a major risk factor for cardio-vascular disease and death. While it is known that subjects with diabetic nephropathy (DN) have a worse kidney outcome compared to other non-diabetic glomerulopathies, it is not certain whether DM independently influences the kidney outcome in subjects diagnosed with glomerulopathies (GP) other than diabetic nephropathy. Method This retrospective study included 1200 adults [50 (95%CI 48 to 51) years, 56% males, eGFR 48.5 (95%CI 45.9 to 51.3) mL/min], with kidney biopsy (KB) proven GP between 1st Jan. 2008 and 31st Dec. 2017. Subjects were followed for a mean of 89 (95%CI 85.5 to 92.4) months until 31st May 2018. The primary endpoints were the initiation of chronic renal replacement therapy (RRT) or death. Subjects with inappropriate biopsy sample, insufficient data and RRT prior to KB were excluded. Demographic, clinical and laboratory data at the time of biopsy were retrieved from medical records. Kidney survival was evaluated by Kaplan-Meier method and a competitive risk to event analysis was used to estimate the risk of RRT, considering death as a competing event. Variables related to kidney outcome were evaluated by the subdistribution hazard function using Fine-Gray model. According to the presence or absence of DM and the types of GP, subjects were divided in three groups: GP without DM (n = 987 pts.), GP with DM (n = 65 pts.), and DN (n = 148 pts.). Results GP with DM subjects were older (60 (95%CI 56 to 64) years vs. 55.5 (95%CI 54 to 59) years in DN group vs. 47 (95%CI 45 to 48) years in GP without DM; p&amp;lt;0.001). Males were predominant in all groups, with higher frequency in DN group (66.9% vs. 54.9% - GP without DM vs. 61.5% - GP with DM; p = 0.01). DN group had higher Charlson comorbidity index [5 (95%CI 4 to 5) vs. 2 (95%CI 2 to 2) in GP without DM vs. 3 (95%CI 3 to 4) in GP with DM; p&amp;lt;0.001], lower eGFR (31.3 (95%CI 25.4 to 36.7)mL/min vs. 51.9 (95%CI 48.9 to 55.8)mL/min in GP without DM vs. 43.2 (95%CI 35.4 to 51.3) mL/min in GP with DM; p&amp;lt;0.001) and higher proteinuria (4.9 (95%CI 3.8 to 6) g/g vs. 2.6 (95%CI 2.35 to 2.9) g/g in GP without DM vs. 4.3 (95%CI 2.7 to 6.7) g/g in GP with DM); p&amp;lt;0.001]. During the follow-up period, 24.3% needed RRT, while 11.4% died. The highest RRT initiation and death frequency was in DN group (40.5% vs. 21.7% in GP without DM vs. 27.7% in GP with DM; p&amp;lt;0.001, and 18.2% vs. 10% in GP without DM vs. 19.9% in GP with DM; p = 0.004). In the univariate time-dependent analysis, subjects with DN had the worse kidney outcome (log rank p&amp;lt;0.001) (Fig. 1), however the kidney survival was similar between GP with DM and GP without DM subjects (log rank p = 0.1). In the competitive risk time to event analysis where death is considered the competing event, diabetic nephropathy subjects had worse kidney survival than GP with DM subjects [CIF 2.3 vs. 1.3, p&amp;lt;0.001], while GP with DM had similar survival with GP without DM (CIF 1,3; p = 0.2) (Fig. 2). After adjusting for the risk factors for CKD progression, DM was not associated with an increased risk of RRT (HR = 0.98, p = 0.9). Predictors for RRT were diabetic nephropathy on KB, along with younger age, lower serum albumin, and lower baseline eGFR. Conclusion In this large cohort of subjects with glomerulopathies, diabetes mellitus complicated with diabetic nephropathy seem to have a worse kidney outcome, while DM in subjects with glomerulopathies other than DN doesn't seem to influence the progression to RRT.

#3559 THE IMPACT OF OBESITY ON CLINICAL OUTCOMES IN VARIOUS LEVELS OF CO-MORBIDITY OF NON-DIALYSIS CHRONIC KIDNEY DISEASE PATIENTS

Abstract Background and Aims Obesity is a major issue with an estimated prevalence of 1.9 billion adults worldwide. Obesity is an important risk factor for premature death and the development of non-communicable diseases such as diabetes mellitus (DM), heart diseases, and chronic kidney disease (CKD). However, mounting evidence in the literature describes a reverse association whereby obesity may have a protective effect on mortality; this is sometimes referred to as the “obesity paradox”. Several reports question the concept of obesity paradox claiming methodology flaws such as collider stratification bias. In this study, we aimed to examine the effects of obesity on the combined outcomes of all-cause mortality (ACM) and renal replacement therapy (RRT) incidence in a cohort of patients with non-dialysis dependent CKD (NDD-CKD) by correcting for major risk factors to reduce the risk of bias. Method This retrospective study was undertaken on all patients with a documented body mass index (BMI) in the Salford Kidney Study database from October 2002 until December 2016. Patients were grouped according to their BMI into normal weight [BMI 18.5-24.9 kg/m2], overweight [BMI 25–29.9 kg/m2 and obese [BMI&amp;gt; 30 kg/m2]. Patients were also grouped according to their level of co-morbidity into 4 groups: group 1 had CKD only; group 2 had CKD and heart failure (HF); group 3 had CKD and DM; and group 4 had CKD, DM, and HF. Univariate Cox regression as well as three stepwise models of multivariate analysis were performed to study the strength of association between BMI categories and combined outcomes (incidence of RRT and ACM) across the 4 groups of different clusters of co-morbidity. Results A total of 2416 patients were included in the analysis. The median age of the cohort was 67.3 years [IQR 55.9-75.6], 61.8% were male, and 96.4% were of white ethnicity. The median BMI was 28.1 kg/m2 [IQR 24.7-32.6] and the median estimated glomerular filtration rate (eGFR) was 30.7 ml/min/1.73m2 [IQR 20.4-43.5]. At baseline, patients with increasing level of co-morbidity tended to be older with higher prevalence of hypertension (HTN), angina, myocardial infarction (MI), and stroke with lower baseline eGFR. The risk of combined outcomes followed the same trend in the three BMI groups, risk is higher with higher index of co-morbidity (p &amp;lt;0.001). Further analysis of four subgroups of co-morbidity was undertaken. A univariate Cox regression analysis for group 1 [CKD only, n = 1351], and group 2 [CKD and HF, n = 227] showed that patients with obesity had significant lower rates of combined outcomes compared to patients with normal BMI (HR 0.75; 95%CI = 0.63-0.89; p = 0.001 and HR 0.56; 95%CI = 0.38-0.82; p = 0.003 for group 1 and group 2 respectively). In multivariate models, obesity consistently proved to be a strong protective factor against combined outcomes (HR 0.77; 95%CI = 0.65-0.92; p = 0.005 for group 1 and HR 0.53; 95%CI = 0.34-0.83; p = 0.005 for group 2). This was independent of age, gender, HTN, angina, stroke, MI, and prescription of statins and angiotensin converting enzyme inhibitors. For group 3 [CKD and DM, n = 614], and group 4 [CKD, DM, and HF, n = 190], there was no significant difference in the combined outcomes between the different BMI groups when using univariate Cox regression analysis (for patients with obesity: HR 0.78; 95%CI = 0.61-1.01; p = 0.060 and HR 0.70; 95%CI = 0.43-1.16; p = 0.166 for both groups respectively). There was no significant difference in the incidence of RRT in any of the four groups. Conclusion In our largely white NDD-CKD cohort of patients, there was evidence of increasing risk of RRT or ACM as comorbidity increased irrespective of BMI. This is not surprising as ACM would be expected to increase as the burden of disease increases. However, when comparing the effect of BMI within groups, obesity was protective against combined outcomes in group 1 (CKD only) and group 2 (CKD+HF). This ‘protective’ effect was not seen in patients who had concomitant diabetes. These data suggest that diabetes is a potent predictor of outcomes irrespective of BMI, however, in patients without diabetes, obesity may play a protective role.

Effect of Nonsupplemented Low-Protein Diet on the Initiation of Renal Replacement Therapy in Stage 4 and 5 Chronic Kidney Disease: A Retrospective Multicenter Cohort Study in Japan

In subjects with chronic kidney disease (CKD), the effect of low-protein diet (LPD) is expected to alleviate uremic symptoms. However, whether LPD is effective in preventing loss of kidney function is controversial. The aim of this study was to evaluate the association between LPD and renal outcomes. We conducted a multicenter cohort study of 325 patients who suffered CKD stage 4 and 5 with eGFR ≥ 10ml/min/1.73m2, between January 2008 and December 2014. The primary diseases of the patients were chronic glomerulonephritis (47.7%), nephrosclerosis (16.9%), diabetic nephropathy (26.2%) and others (9.2%). The patients were divided into four groups, based on the mean protein intake (PI) /day, group 1 (n =76): PI < 0.5 g/kg ideal body weight/day, group 2 (n=56): 0.5 ≤ PI < 0.6 g/kg/day, group 3 (n=110): 0.6 ≤ PI < 0.8 g/kg/day, group 4 (n=83): PI ≥ 0.8 g/kg/day. Dietary supplementation with essential amino acids and ketoanalogues was not used. The outcome measure was occurrence of renal replacement therapy (RRT) (hemodialysis, peritoneal dialysis, renal transplantation (excluding preemptive transplantation)) and all-cause mortality until December 2018. Cox regression models were used to examine whether LPD was associated with the risk of outcomes. During a mean follow-up of 4.1 ± 2.2 years. 33 patients (10.2%) died of all causes, 163 patients (50.2%) needed to start RRT and 6 patients (1.8%) received a renal transplant. LPD therapy of 0.5 g/kg/day or less was significantly related to a lower risk of RRT and all-cause mortality [Hazard ratio = 0.656; 95% confidence interval, 0.438 to 0.984, p=0.042]. These results suggest that non-supplemented LPD therapy of 0.5 g/kg/day or less may prolong the initiation of RRT in stage 4 and 5 CKD patients.

SuPAR links a dysregulated immune response to tissue inflammation and sepsis-induced acute kidney injury.

Acute kidney injury (AKI) secondary to sepsis results in poor outcomes and conventional kidney function indicators lack diagnostic value. Soluble urokinase plasminogen activator receptor (suPAR) is an innate immune-derived molecule implicated in inflammatory organ damage. We characterized the diagnostic ability of longitudinal serum suPAR levels to discriminate severity and course of sepsis-induced AKI (SI-AKI) in 200 critically ill patients meeting Sepsis-3 criteria. The pathophysiologic relevance of varying suPAR levels in SI-AKI was explored in a polymicrobial sepsis model in WT, (s)uPAR-knockout, and transgenic suPAR-overexpressing mice. At all time points studied, suPAR provided a robust classification of SI-AKI disease severity, with improved prediction of renal replacement therapy (RRT) and mortality compared with established kidney biomarkers. Patients with suPAR levels of greater than 12.7 ng/mL were at highest risk for RRT or death, with an adjusted odds ratio of 7.48 (95% CI, 3.00-18.63). suPAR deficiency protected mice against SI-AKI. suPAR-overexpressing mice exhibited greater kidney damage and poorer survival through inflamed kidneys, accompanied by local upregulation of potent chemoattractants and pronounced kidney T cell infiltration. Hence, suPAR allows for an innate immune-derived and kidney function-independent staging of SI-AKI and offers improved longitudinal risk stratification. suPAR promotes T cell-based kidney inflammation, while suPAR deficiency improves SI-AKI.

Should RAAS blockade therapy be continued in patients with advanced renal disease?

Probably. Renin-angiotensin-aldosterone system (RAAS) blockade therapy should be continued in most patients with advanced renal disease and comorbid conditions; however, individualized treatment is warranted as data on the benefits and harms in all-cause mortality, cardiovascular mortality, and risk for renal replacement therapy are inconclusive (strength of recommendation [SOR]: B, based on observational studies, systematic reviews, and meta-analyses of randomized controlled trials [RCTs]). Certain patient populations, such as patients with diabetes or those with cardiovascular risk or history, may benefit most from continued RAAS blockade therapy (SOR: A, based on systematic reviews and meta-analyses of RCTs).

Association and prediction of red blood cell distribution width to albumin ratio in all-cause mortality of acute kidney injury in critically ill patients.

The progression of acute kidney injury (AKI) might be associated with systemic inflammation. Our study aims to explore the association and predictive value of the red blood cell distribution width (RDW) to human serum albumin (ALB) ratio (RDW/ALB ratio), an inflammation-related indicator, in the risk of all-cause mortality and renal replacement therapy (RRT) in AKI patients admitted in intensive care units (ICU). A retrospective cohort study was designed, and data were extracted from the Medical Information Mart for Intensive Care III (MIMIC-III). The primary outcome was the risk of all-cause mortality (1-month, 3-month, and 12-month), and the secondary outcome was the risk of RRT. The association between the RDW/ALB ratio and the risk of all-cause mortality and RRT was assessed using the Cox regression analysis, with results shown as hazard ratio (HR) and 95% confidence intervals (CIs). The relationship between the RDW/ALB ratio and crude probability of all-cause mortality or RRT was assessed using restricted cubic splines (RCS). The concordance index (C-index) was used to assess the discrimination of the prediction model. A total of 13,856 patients were included in our study. In the fully adjusted Cox regression model, we found that a high RDW/ALB ratio was associated with an increased risk of 1-month, 3-month, and 12-month all-cause mortality and RRT (all p < 0.05). Moreover, RCS curves showed the linear relationship between the RDW/ALB ratio and the probability of all-cause mortality and RRT, and the probability was elevated with the increase of the ratio. In addition, the RDW/ALB ratio showed a good predictive performance in the risk of 1-month all-cause mortality, 3-month all-cause mortality, 12-month all-cause mortality, and RRT, with a C-index of 0.728 (95%CI: 0.719-0.737), 0.728 (95%CI: 0.721-0.735), 0.719 (95%CI: 0.713-0.725), and 0.883 (95%CI: 0.876-0.890), respectively. The RDW/ALB ratio performed well to predict the risk of all-cause mortality and RRT in critically ill patients with AKI, indicating that this combined inflammatory indicator might be effective in clinical practice.

Development and Validation of a Renal Replacement after Trauma Scoring Tool.

Stress on the healthcare system requires careful allocation of resources such as renal replacement therapy (RRT). The COVID-19 pandemic generated difficulty securing access to RRT for trauma patients. We sought to develop a renal replacement after trauma (RAT) scoring tool to help identify trauma patients who may require RRT during their hospitalization. The 2017 to 2020 TQIP database was divided into a derivation (2017 to 2018 data) and validation (2019 to 2020 data) set. A 3-step methodology was used. Adult trauma patients admitted from the emergency department to the operating room or ICU were included. Patients with chronic kidney disease, transfers from another hospital, and emergency department death were excluded. Multiple logistic regression models were created to determine the risk for RRT in trauma patients. The weighted average and relative impact of each independent predictor was used to derive a RAT score, which was validated using area under receiver operating characteristic curve (AUROC). From 398,873 patients in the derivation and 409,037 patients in the validation set, 11 independent predictors of RRT were included in the RAT score derived with scores ranging from 0 to 11. The AUROC for the derivation set was 0.85. The rate of RRT increased to 1.1%, 3.3%, and 20% at scores of 6, 8, and 10, respectively. The validation set AUROC was 0.83. RAT is a novel and validated scoring tool to help predict the need for RRT in trauma patients. With future improvements including baseline renal function and other variables, the RAT tool may help prepare for the allocation of RRT machines/staff during times of limited resources.

A Risk Prediction Score for Renal Replacement Therapy in Critically Ill Septic – Acute Kidney Injury Patients

Introduction: Acute kidney injury (AKI) is a major complication in critically ill septic patients and is associated with increased morbidity and mortality. A recent study suggested a risk score based on patient’s chronic comorbidities and acute events at intensive care unit (ICU) admission as a reliable tool for predicting AKI in critically ill adult population. The aim of this study was to adapt this score to septic-AKI patients and evaluate its prognostic value as predictor of the need for renal replacement therapy (RRT) at ICU admission. Methods: This is a retrospective analysis of 399 septic-AKI patients admitted to the Division of Intensive Medicine of the Centro Hospitalar Universitário Lisboa Norte between January 2008 and December 2014. The Kidney Disease Improving Global Outcomes (KDIGO) classification was used to define AKI. The Renal Replacement Therapy Risk Score was adapted from the AKI risk prediction score proposed by Malhotra et al (Nephrol Dial Transplant. 2017;32:814-22). Results: Fifty two percent of patients were KDIGO stage 3, 25.8% KDIGO stage 2 and 22.3% KDIGO stage 1. Twenty seven percent of patients required RRT. Patients requiring RRT had higher risk score than those who did not (6.6±2.5 vs 5.1 ±2.6, p&lt;0.001). An optimal cut-off value of ≥ 6 in this score predicted the need for RRT with sensitivity 0.630 and specificity 0.391. Conclusion: The RRT risk score at ICU admission was independently associated with the requirement of RRT septic-AKI patients. The assessment of this ratio is simple and can prove useful in identifying patients at risk for need of RRT.

How useful is kidney biopsy for the management of glomerulopathies in the elderly?

The use of kidney biopsy in elderly individuals is still matter of discussion. The purpose of this study isto assess the utility of kidney biopsy for the management of glomerulopathies in an Eastern European cohort, targetingpatients older than 65years. This retrospective study included 875 adults (147 older than 65years), with biopsy-proven glomerulopathies, followed up for 71.1 (95% CI 68.2-73.9) months. The primary endpoint was chronic renal replacement therapy initiation.Statistical evaluation wasperformed with IBM SPSS software version 20, Analyse-it, and SAS Studio. The Kaplan-Meier method was used to estimate the time to death and the log-rank test was used for comparisons. The multivariate Cox proportional hazard analysis was used to evaluate the risk of death. Secondary glomerulopathies were more frequent in patients aged > 65years (52.4% vs. 41.9%, p = 0.004). Membranous nephropathy and amyloidosis were the most frequent primary and secondary glomerulopathies in this age group. Kidney biopsy complications were low (< 4%) in both age groups. In 42% of the elderly, the result of biopsy guided the immunosuppressive therapy. While the all-cause mortality rate was higher (OR 4.2; 95% CI 2.7-6.7; p < 0.0001) in elderly individuals, the rate of renal replacement therapy initiation was similar (31.3 vs 26%; p = 0.1) in both age groups. In the competitive risk analysis, kidney survival was similar irrespective of age [CIF 0.4 (95% CI 0.26-0.53) vs. 0.34 (95% CI 0.28-0.39), p = 0.08]. However, after adjusting for the confounding factors, younger age was associated with an increased risk of renal replacement therapy (HR = 1.57, p = 0.01), along with secondary glomerulopathies. The diagnosis of an underlying glomerulopathy guided the therapy in almost one-half of the elderlypatients who underwent a kidney biopsy, provided important prognostic information and had a low complications rate; kidney biopsy may therefore be considered a safe, reliable procedure in the management of glomerulopathies, even in patients over 65years of age.

Renal Replacement Therapy in Patients With Acute Decompensated Pulmonary Hypertension Admitted to the Intensive Care Unit.

Background: Pulmonary arterial hypertension and chronic thromboembolic pulmonary hypertension (PH) are characterized hemodynamically by pre-capillary PH. Acute worsening of systemic congestion and/or reduced right ventricular flow output in patients with pre-capillary PH characterizes an episode of acute decompensated PH. Acute kidney injury (AKI) is a common complication in this population and those patients frequently use renal replacement therapy (RRT). Predictors and timing for RRT in acute decompensated PH are unknown and mortality of patients who require this therapy is high. We hypothesize that AKI and hypervolemia are associated with use of RRT during episodes of acute decompensated PH in patients with pre-capillary PH requiring intensive care unit (ICU) admission.Aim: Explore variables associated with RRT use, develop a decision tree model to predict use of RRT in acute decompensated PH and analyze ICU, in-hospital and 90-days mortality in this population.Materials and methods: Multicenter retrospective cohort study including patients with pulmonary arterial hypertension and chronic thromboembolic PH with unplanned admission in the ICU for acute decompensated PH. Acute decompensated PH was defined by acute right ventricular failure leading to low cardiac output and elevated right ventricle filling pressures. We employed two multivariable logistic regression models using directed acyclic graphs to identify confounders. Unadjusted and adjusted odds ratios and 95% confidence intervals were used to measure the association between variables and RRT use.Results: Some 73 patients were included, 16.4% (n=12) of patients required RRT during ICU stay. In the univariate analysis, right atrial pressure (RAP) on last right heart catheterization, and creatinine upon ICU admission were associated with use of RRT and were included in the multivariable model and in the decision tree model. The decision tree model based on RAP and creatinine showed sensitivity of 58.3% and specificity of 100% with area under the receiver operating characteristic curve of 0.81 for predicting RRT use in the ICU. In-hospital mortality and 90-days mortality of patients who used RRT were higher than in patients that did not use RRT (75.0% vs. 34.4%, p < 0.01 and 83.3% vs. 42.6%, p = 0.01, respectively).Conclusion: The decision tree model based on creatinine upon admission and RAP, which is a surrogate of hypervolemia, can identify patients at risk for RRT. Increased ICU, in-hospital, and 90-days mortality were observed in patients with acute decompensated PH who used RRT in the ICU.

SINGLE-CENTER EXPERIENCE WITH THE USE OF THE SERAPH-100 MICROBIND AFFINITY BLOOD FILTER IN-PARALLEL WITH EXTRACORPOREAL MEMBRANE OXYGENATION CIRCUIT IN SEPTIC PATIENTS

TYPE: Late Breaking Case Report TOPIC: Critical Care INTRODUCTION: Patients who require extracorporeal membrane oxygenation (ECMO) have a high mortality if they develop septic shock. With the emergence of novel and resistant pathogens, new therapies are needed to treat septic patients. The Seraph–100 Microbind Affinity Blood Filter was granted Emergency Use Authorization by the FDA to treat severe COVID-19. The Seraph-100 filter contains microbeads that can bind bacteria, fungi, viruses and cytokines. Recommended configurations for the Seraph–100 utilize hemodialysis or continuous renal replacement therapy (CRRT) machines in a stand-alone fashion or in-combination with a hemodialysis filter. In this series, we explore a new configuration for the Seraph-100 for patients requiring ECMO. CASE PRESENTATION: Five septic patients underwent treatment with the Seraph-100 in-parallel with ECMO. This configuration allowed for pressures generated by the ECMO circuit to drive blood flow through the Seraph-100. All five patients were on multiple high dose vasopressors prior to therapy with the Seraph-100. Within 12-24 hours of treatment, vasopressor support significantly decreased and repeat blood cultures showed clearance of pathogens. DISCUSSION: All our patients treated with Seraph–100 in-parallel with ECMO had significant reduction in vasopressor support. Benefits of this configuration include limiting need for additional vascular access and need for dialysis circuits, along with the associated risks of renal replacement therapy. CONCLUSIONS: The Seraph-100 represents an innovative solution for the treatment of septic patients. This case series demonstrated the effectiveness and safety of a new configuration for the Seraph-100 in patients requiring ECMO. Further studies are needed to elucidate the optimal use of the Seraph-100 blood filter. DISCLOSURE: Nothing to declare. KEYWORD: Seraph-100 Blood Filter

MO515: Mortality Differences Between Men and Women With Chronic Kidney Disease in the Irish Health System: The National Kidney Disease Surveillance Programme

Abstract BACKGROUND AND AIMS Chronic kidney disease is associated with higher mortality compared with the general population, but mortality differences between men and women with CKD are poorly understood. Although the prevalence of CKD is consistently higher in women than in men, emerging studies suggest that men experience poorer survival. The primary goal of this study was to compare mortality rates between men and women in the Irish health system and determine whether kidney function influenced these sex-specific risks. METHOD We created a cohort of 125 890 patients from the National Kidney Disease Surveillance System (NKDSS) to compare mortality rates between men and women. Patients were recruited from 1 January 2005 to 31 December 2010 and followed until 31 December 2013. Kidney function was determined using the CKD-EPI equation, generating estimated glomerular filtration rate (mL/min/1.73 m2) (eGFR). The primary outcome was all-cause mortality from national records provided by the Central Statistics Office (CSO). The principal exposure was participant sex, classified as men or women. Patients were censored at the date of initiation of dialysis or kidney transplantation, death, loss to follow-up or end of follow-up 31 December 2013. Mortality risks were compared using the Fine-Gray approach, which accounted for the competing risks of renal replacement therapy. Adjustments were made for baseline age, kidney function and blood biomarkers, which indicated the presence and severity of clinical disease. RESULTS Of the 125 890 participants, 55.1% were women, with a mean age of 54.1 (SD: 17.7) years. The median follow-up was 7.75 years (IQR: 6.33–8.55), 243 patients (0.19%) patients progressed to RRT and 14 179 patients (11.26%) died. Overall, mortality rates were significantly higher in men than in women (18.4 versus 16.6 deaths/1000 pyrs, respectively). Compared with women, men with CKD experienced significantly higher rates of death and RRT, P &amp;lt; .001 (Figure 1a). With each worsening GFR category, crude mortality rates increased by 18-fold in women compared with 9-fold in men. The P-value for the interaction of sex and GFR with mortality was &amp;lt;0.001. In stratified analyses, the magnitude of the sHR for men versus women decreased with each descending eGFR category from a peak of 2.17 (1.88–2.49) for eGFR &amp;gt;90 mL/min down to 1.21 (0.98–1.49) for eGFR &amp;lt;29 mL/min/1.72 m2 (Table 1) and was no longer significant in the eGFR &amp;lt;29 mL/min/1.72 m² category. CONCLUSION Although women have a higher burden of CKD than men in the Irish health system, the overall risks of death and RRT were far greater in men than in women. However, the excess risk in men diminished with increasing severity of kidney disease such that mortality risks for women approached those of men with advanced kidney disease. While these findings may have a biologic basis, fundamental disparities in care delivery, quality or accessibility between men and women is a far more likely explanation.

MO240: The Evolution and Epidemiology of Membranous Nephropathy at a Single Centre Over Two Decades

Abstract BACKGROUND AND AIMS Membranous nephropathy (MN) commonly presents with nephrotic syndrome and carries significant risk of progression to end-stage kidney disease (ESKD) (33% without treatment, 10%–20% with). Patients may spontaneously remit (up to 40%), but are also at risk of relapse. A total of 80% of cases are primary (kidney-specific) and the majority of these are associated with antibodies to the M-type phospholipase A2 receptor (anti-PLA2R) or thrombospondin type 1 domain containing 7A antibodies (THS7DA). Treatment ranges from supportive care with renin–angiotensin system (RAS) blockade through to immunosuppression. Here we assessed the epidemiology of MN over 20 years at our centre (Salford Royal Hospital, UK) with particular reference to treatment administered and key clinical outcomes. METHOD A total of 238 patients with kidney biopsy-proven MN were identified from the local database between January 2000 and December 2020. Twenty-one were excluded (see Fig. 1) resulting in a total of 217 patients in whom demographic data, co-morbidities, remission and relapse rates, baseline laboratory values, treatment given, and outcomes were collected. Analyses compared effects of (i) immunosuppressed versus non-immunosuppressed, (ii) effect of modified Ponticelli versus other forms of immunosuppression and (iii) rates of remission. Univariate and multivariate cox regression determined factors that were associated with increased risk of renal replacement therapy (RRT) or death. RESULTS A total of 63.6% of the cohort were male, 88% Caucasian, 10.1% diabetic, 50.2% hypertensive and 15.2% had coexisting cardiovascular disease (Table 1). A total of 82.0% had primary MN. Median baseline eGFR was 72.7 mL/min/1.73 m2 and median baseline uPCR was 664 g/mol. A total of 157 patients (72.4%) went into remission (either spontaneous—75 (47.8%) or with treatment—85 (52.2%)), and of these 41.4% subsequently relapsed. A total of 89.4% received RAS blockade and 48.8% received immunosuppression. The median follow-up period was 56 months; 9.7% progressed to ESKD and 32.3% died. Patients who received immunosuppression had significantly more proteinuria than those who did not (765 g/mol versus 514 g/mol, P ≤ 0.001), were more likely to relapse (53.7% versus 28.0%, p ≤0.001) and were more likely to require RRT (15.1% versus 4.9%, P = .028). Those who received modified Ponticelli were less likely to relapse than those who received other forms of immunosuppression (34% versus 46%, P = .019), less likely to require RRT (3% versus 22%, P = .018) and less likely to die (11% versus 38%). Multivariate cox regression showed that pre-existing cardiovascular disease was a risk factor for death (HR 2.47, P &amp;lt; .001) and higher baseline eGFR and use of RAS blockade was associated with reduced risk of death (HR 0.98, P &amp;lt; .001 and HR 0.34, P = .012, respectively). CONCLUSION Despite advances in knowledge of underlying pathogenesis and increased treatment options, MN continues to pose a significant risk of progression to ESKD and death. This real-world study suggests that immunosuppression with modified Ponticelli is associated with lower rates of progressive CKD compared with MMF and calcineurin-inhibitor based therapy. Whilst many patients respond to treatment and can achieve remission, a significant proportion of these subsequently relapse. Identifying these patients early with judicial use of appropriate immunosuppression is key.

MO431: Estimation of the Risk of Progression and Renal Substitution Treatment in Patients With Chronic Kidney Disease Using an Artificial Intelligence Model

Abstract BACKGROUND AND AIMS The use of tools that allow to estimate the probability of progression of chronic kidney disease (CKD) to advanced stages, has not yet gained a notable space in our clinical practice. The aim of this study was to develop and validate a model to predict disease progression, and the need for renal replacement therapy, based on machine learning, for patients with CKD grades 3 to 5. This is the first model of its kind to be implemented in Colombia. METHOD This is an observational retrospective closed cohort study. We included patients with CKD from a primary care program and followed them for 5 years. Demographic, clinical and laboratory predictors were included. The outcomes were CKD stage progression, &amp;gt;25% reduction in baseline glomerular filtration rate (eGFR) and the need for renal replacement therapy (RRT), dialysis, or kidney transplantation. We designed two prediction models, one time-independent, based on logistic regression, neural networks and random forest; and a second model, a survival analysis (time to event), by Cox regression, random forest and gradient boosting. Finally, we conducted an internal validation with bootstrapping for the first model, and external validation for the second model in a second real cohort. As a result, we designed a risk calculator. RESULTS Time-independent model included 2619 patients, 62.7% female, 92.6% with hypertension, 23.5% diabetics, with a baseline eGFR 51.06 mL/min/1.73m2 (40–61.9). An estimated performance for predicting RRT risk of F1: 0.61 and Kappa: 0.60 (113 events) was detected; stage progression of F1: 0.4 and Kappa: 0.25; reduction in eGFR F1: 0.29 and Kappa: 0.21. For this first model, the most relevant predictors were: initial eGFR, hemoglobin, sex, central region, total cholesterol and socioeconomic status. The second, a 5-year Time-to-Event prediction model, included data from 1803 patients, had good accuracy with a C-Index assessed performance for RRT risk of 0.96, grade progression of 0.71 and eGFR reduction of 0.69 respectively. The most relevant predictors were initial eGFR, mean heart rate, hemoglobin, hospitalizations, sex, hypertension, diabetes, total cholesterol and central region. The validation cohort, with 658 patients with CKD, 63.9% male, 39% diabetics, with a mean eGFR of 34.9 mL/min/1.73m2, showed good accuracy with a C-Index for RRT risk of 0.935, grade progression of 0.69 and eGFR reduction of 0.0.62 respectively. CONCLUSION Our study demonstrated the utility of novel tools to predict renal outcomes in a CKD population in Colombia. This is the first study conducted with our local population. The resulted risk calculator is intended to be part of the electronic medical history in our hospitals.

A prediction model with lifestyle factors improves the predictive ability for renal replacement therapy: a cohort of 442 714 Asian adults.

ABSTRACTBackgroundThere are limited renal replacement therapy (RRT) prediction models with good performance in the general population. We developed a model that includes lifestyle factors to improve predictive ability for RRT in the population at large.MethodsWe used data collected between 1996 and 2017 from a medical screening in a cohort comprising 442 714 participants aged 20 years or over. After a median follow-up of 13 years, we identified 2212 individuals with end-stage renal disease (RRT, n: 2091; kidney transplantation, n: 121). We built three models for comparison: model 1: basic model, Kidney Failure Risk Equation with four variables (age, sex, estimated glomerular filtration rate and proteinuria); model 2: basic model + medical history + lifestyle risk factors; and model 3: model 2 + all significant clinical variables. We used the Cox proportional hazards model to construct a points-based model and applied the C statistic.ResultsAdding lifestyle factors to the basic model, the C statistic improved in model 2 from 0.91 to 0.94 (95% confidence interval: 0.94, 0.95). Model 3 showed even better C statistic value i.e., 0.95 (0.95, 0.96). With a cut-off score of 33, model 3 identified 3% of individuals with RRT risk in 10 years. This model detected over half of individuals progressing to RRT, which was higher than the sensitivity of cohort participants with stage 3 or higher chronic kidney disease (0.53 versus 0.48).ConclusionsOur prediction model including medical history and lifestyle factors improved the predictive ability for end-stage renal disease in the general population in addition to chronic kidney disease population.