Machine learning for prediction of chronic kidney disease progression: Validation of the Klinrisk model in the CANVAS Program and CREDENCE trial.

AIM: To validate the Klinrisk machine learning model for prediction of chronic kidney disease (CKD) progression in patients with type 2 diabetes in the pooled CANVAS/CREDENCE trials. MATERIALS AND METHODS: We externally validated the Klinrisk model for prediction of CKD progression, defined as 40% or higher decline in estimated glomerular filtration rate (eGFR) or kidney failure. Model performance was assessed for prediction up to 3 years with the area under the receiver operating characteristic curve (AUC), Brier scores and calibration plots of observed and predicted risks. We compared performance of the model with standard of care using eGFR (G1-G4) and urine albumin-creatinine ratio (A1-A3) Kidney Disease Improving Global Outcomes (KDIGO) heatmap categories. RESULTS: The Klinrisk model achieved an AUC of 0.81 (95% confidence interval [CI] 0.78-0.83) at 1 year, and 0.88 (95% CI 0.86-0.89) at 3 years. The Brier scores were 0.020 (0.018-0.022) and 0.056 (0.052-0.059) at 1 and 3 years, respectively. Compared with the KDIGO heatmap, the Klinrisk model had improved performance at every interval (P < .01). CONCLUSIONS: The Klinrisk machine learning model, using routinely collected laboratory data, was highly accurate in its prediction of CKD progression in the CANVAS/CREDENCE trials. Integration of the model in electronic medical records or laboratory information systems can facilitate risk-based care.

A Predictive Model for Kidney Failure After Nephrectomy for Localized Kidney Cancer: The Kidney Cancer Risk Equation.

RATIONALE & OBJECTIVE: Nephrectomy is the mainstay of treatment for individuals with localized kidney cancer. However, surgery can potentially result in the loss of kidney function or in kidney failure requiring dialysis/kidney transplantation. There are currently no clinical tools available to preoperatively identify which patients are at risk of kidney failure over the long term. Our study developed and validated a prediction equation for kidney failure after nephrectomy for localized kidney cancer. STUDY DESIGN: Population-level cohort study. SETTING & PARTICIPANTS: Adults (n=1,026) from Manitoba, Canada, with non-metastatic kidney cancer diagnosed between January 1, 2004, and December 31, 2016, who were treated with either a partial or radical nephrectomy and had at least 1 estimated glomerular filtration rate (eGFR) measurement before and after nephrectomy. A validation cohort included individuals in Ontario (n=12,043) with a diagnosis of localized kidney cancer between October 1, 2008, and September 30, 2018, who received a partial or radical nephrectomy and had at least 1 eGFR measurement before and after surgery. NEW PREDICTORS & ESTABLISHED PREDICTORS: Age, sex, eGFR, urinary albumin-creatinine ratio, history of diabetes mellitus, and nephrectomy type (partial/radical). OUTCOME: The primary outcome was a composite of dialysis, transplantation, or an eGFR<15mL/min/1.73m2 during the follow-up period. ANALYTICAL APPROACH: Cox proportional hazards regression models evaluated for accuracy using area under the receiver operating characteristic curve (AUC), Brier scores, calibration plots, and continuous net reclassification improvement. We also implemented decision curve analysis. Models developed in the Manitoba cohort were validated in the Ontario cohort. RESULTS: In the development cohort, 10.3% reached kidney failure after nephrectomy. The final model resulted in a 5-year area under the curve of 0.85 (95% CI, 0.78-0.92) in the development cohort and 0.86 (95% CI, 0.84-0.88) in the validation cohort. LIMITATIONS: Further external validation needed in diverse cohorts. CONCLUSIONS: Our externally validated model can be easily applied in clinical practice to inform preoperative discussions about kidney failure risk in patients facing surgical options for localized kidney cancer. PLAIN-LANGUAGE SUMMARY: Patients with localized kidney cancer often experience a lot of worry about whether their kidney function will remain stable or will decline if they choose to undergo surgery for treatment. To help patients make an informed treatment decision, we developed a simple equation that incorporates 6 easily accessible pieces of patient information to predict the risk of reaching kidney failure 5 years after kidney cancer surgery. We expect that this tool has the potential to inform patient-centered discussions tailored around individualized risk, helping ensure that patients receive the most appropriate risk-based care.

Metabolic acidosis is undertreated and underdiagnosed: a retrospective cohort study.

BACKGROUND: Guidelines recommend treatment of metabolic acidosis (MA) in patients with chronic kidney disease (CKD), but the diagnosis and treatment rates in real-world settings are unknown. We investigated the frequency of MA treatment and diagnosis in patients with CKD. METHODS: In this retrospective cohort study, we examined administrative health data from two US databases [Optum's de-identified Integrated Claims + Clinical Electronic Health Record Database (US EMR cohort; 1 January 2007 to 30 June 2019) and Symphony Health Solutions IDV® (US claims cohort; 1 May 2016 to 30 April 2019)] and population-level databases from Manitoba, Canada (1 April 2006 to 31 March 2018). Patients who met laboratory criteria indicative of CKD and chronic MA were included: two consecutive estimated glomerular filtration results <60 mL/min/1.73 m2 and two serum bicarbonate results 12 to <22 mEq/L over 28-365 days. Outcomes included treatment of MA (defined as a prescription for oral sodium bicarbonate) and a diagnosis of MA (defined using administrative records). Outcomes were assessed over a 3-year period (1 year pre-index, 2 years post-index). RESULTS: A total of 96 184 patients were included: US EMR, 6179; Manitoba, 3223; US Claims, 86 782. Sodium bicarbonate treatment was prescribed for 17.6%, 8.7% and 15.3% of patients, and a diagnosis was found for 44.7%, 20.9% and 20.9% of patients, for the US EMR, Manitoba and US Claims cohorts, respectively. CONCLUSIONS: This analysis of 96 184 patients with laboratory-confirmed MA from three independent cohorts of patients with CKD and MA highlights an important diagnosis and treatment gap for this disease-modifying complication.

Practical Utilization of Prediction Equations in Chronic Kidney Disease.

Chronic kidney disease (CKD) is common and can lead to kidney failure, cardiovascular complications, and early mortality. While nephrologists can provide valuable insights for patients at all stages of CKD, these scarce resources should be targeted at patients with the highest risk of progression and adverse outcomes. Prediction models are tools that can help providers risk stratify patients if they are effectively implemented into the clinical workflow. We believe these equations should demonstrate (1) clinical utility: where they can provide useful information to the physician and patients; and (2) clinical usability: where they are able to be easily integrated into clinical workflow and do not result in unnecessary costs or visits. CKD often remains unrecognized until later stages when a large window of opportunity to delay progression has already passed. Models to determine progression of CKD using thresholds such as a 40% decline in eGFR can provide clinical utility in risk stratifying patients at all stages of CKD, an endpoint that has been recommended by the FDA for the evaluation of drug approvals for disease-modifying therapies. For patients at more advanced stages of CKD with a greater risk of kidney failure, tools such as the kidney failure risk equation can be implemented to help guide most costly decisions, such as referral to multidisciplinary care, commencing dialysis modality education, or planning for vascular access placement surgery. In addition, models focused on determining outcomes following dialysis initiation can help inform shared decision-making between patient and provider to better inform decisions around conservative care. To ensure widespread adoption of these tools, it is important to ensure that they are broadly generalizable to many health settings and easily implemented into existing clinic workflows with minimum disruption.

The Comparative Outcomes of Radical Prostatectomy versus Radiotherapy for Nonmetastatic Prostate Cancer: A Longitudinal, Population-Based Analysis.

PURPOSE: The comparative effectiveness of radical prostatectomy (RP) versus radiation therapy (RT) for prostate cancer remains a largely debated topic. Utilizing a provincial population-based linked data set from an equal-access, universal health care system, we sought to compare outcomes among patients treated with either radiation or prostatectomy for nonmetastatic prostate cancer. MATERIALS AND METHODS: We performed a retrospective cohort study by linking several administrative data sets to identify patients who were diagnosed with prostate cancer between 2004 and 2016 in Manitoba, Canada and who were subsequently treated with either RP or RT. Cox proportional hazard models with inverse probability of treatment weighting were used to compare rates of all-cause mortality, as well as prostate cancer specific mortality (PCSM) between patients who underwent RP vs RT. RESULTS: During the study period, 2,540 patients underwent RP and 1,895 underwent RT for prostate cancer. Unadjusted overall survival was higher for RP vs RT (5-year overall survival 95.52% for RP compared with 84.55% for RT, p <0.0001). In inverse probability of treatment weighting-adjusted Cox regression analysis, compared to patients in the RP groups, patients in the RT group had an increased rate of all-cause mortality (HR 1.93, 95% CI 1.65-2.26, p <0.0001), and PCSM (HR 3.98, 95% CI 2.89-5.49; p <0.0001). CONCLUSIONS: RT was associated with higher all-cause mortality and PCSM rates compared with RP. These findings highlight the importance of comparative effectiveness research to identify treatment disparities and warrant further investigation.

Role of artificial intelligence in the diagnosis and management of kidney disease: applications to chronic kidney disease and acute kidney injury.

PURPOSE OF REVIEW: Chronic kidney disease (CKD) and acute kidney injury (AKI) are global public health problems associated with a significant burden of morbidity, healthcare resource use, and all-cause mortality. This review explores recently published studies that take a machine learning approach to the diagnosis, management, and prognostication in patients with AKI or CKD. RECENT FINDINGS: The release of novel therapeutics for CKD has highlighted the importance of accurately identifying patients at the highest risk of progression. Many models have been constructed with reasonable predictive accuracy but have not been extensively externally validated and peer reviewed. Similarly, machine learning models have been developed for prediction of AKI and have found sufficient accuracy. There are issues to implementing these models, however, with conflicting results with respect to the relationship between prediction of an AKI outcome and improvements in the occurrence of other adverse events, and in some circumstances potential harm. SUMMARY: Artificial intelligence models can help guide management of CKD and AKI, but it is important to ensure that they are broadly applicable and generalizable to various settings and associated with improved clinical decision-making and outcomes.

Effects of a Knowledge-Translation Intervention on Early Dialysis Initiation: A Cluster Randomized Trial.

BACKGROUND: The Initiating Dialysis Early and Late (IDEAL) trial, published in 2009, found no clinically measurable benefit with respect to risk of mortality or early complications with early dialysis initiation versus deferred dialysis start. After these findings, guidelines recommended an intent-to-defer approach to dialysis initiation, with the goal of deferring it until clinical symptoms arise. METHODS: To evaluate a four-component knowledge translation intervention aimed at promoting an intent-to-defer strategy for dialysis initiation, we conducted a cluster randomized trial in Canada between October 2014 and November 2015. We randomized 55 clinics, 27 to the intervention group and 28 to the control group. The educational intervention, using knowledge-translation tools, included telephone surveys from a knowledge-translation broker, a 1-year center-specific audit with feedback, delivery of a guidelines package, and an academic detailing visit. Participants included adults who had at least 3 months of predialysis care and who started dialysis in the first year after the intervention. The primary efficacy outcome was the proportion of patients who initiated dialysis early (at eGFR >10.5 ml/min per 1.73 m2). The secondary outcome was the proportion of patients who initiated in the acute inpatient setting. RESULTS: The analysis included 3424 patients initiating dialysis in the 1-year follow-up period. Of these, 509 of 1592 (32.0%) in the intervention arm and 605 of 1832 (33.0%) in the control arm started dialysis early. There was no difference in the proportion of individuals initiating dialysis early or in the proportion of individuals initiating dialysis as an acute inpatient. CONCLUSIONS: A multifaceted knowledge translation intervention failed to reduce the proportion of early dialysis starts in patients with CKD followed in multidisciplinary clinics. CLINICAL TRIAL REGISTRY NAME AND REGISTRATION NUMBER: ClinicalTrials.gov, NCT02183987. Available at: https://clinicaltrials.gov/ct2/show/NCT02183987.

The Association between Income Status and Treatment Selection for Prostate Cancer in a Universal Health Care System: A Population-Based Analysis.

PURPOSE: Treatment selection for localized prostate cancer is guided by risk stratification and patient preferences. While socioeconomic status (SES) disparities exist for access to care, less is known about the effect of SES on treatment decision-making. We sought to evaluate whether income status was associated with the treatment selected (radical prostatectomy [RP] vs radiation therapy [RT]) for nonmetastatic prostate cancer in a universal health care system. MATERIALS AND METHODS: All men from Manitoba, Canada who were diagnosed with nonmetastatic prostate cancer between 2005 and 2016 and subsequently treated with RP or RT were identified using a provincial cancer database. SES was defined as neighborhood income by postal code and divided into income quintiles (Q1-Q5, with Q1 the lowest quintile and Q5 the highest). Multivariable logistic regression nested models were used to compare whether SES was associated with treatment type received. RESULTS: We identified 3,966 individuals who were diagnosed with nonmetastatic prostate cancer and were treated with RP (2,354) or RT (1,612). After adjusting for demographic and clinicopathological characteristics, as income quintile increased, men were incrementally more likely to undergo RP than RT (range Q2 vs Q1: adjusted OR 1.40, 95% CI 1.01-1.93; Q5 vs Q1: adjusted OR 2.30, 95% CI 1.70-3.12). CONCLUSIONS: As income levels increased there was a stepwise incremental increase in the odds of receiving RP over RT for localized prostate cancer. These results may inform initiatives to better understand the values, priorities and barriers that patients experience when making treatment decisions in a universal health care system.

Impact of a screen, triage and treat program for identifying chronic disease risk in Indigenous children.

BACKGROUND: The First Nations Community Based Screening to Improve Kidney Health and Prevent Dialysis project was a point-of-care screening program in rural and remote First Nations communities in Manitoba that aimed to identify and treat hypertension, diabetes and chronic kidney disease. The program identified chronic disease in 20% of children screened. We aimed to characterize clinical screening practices before and after intervention in children aged 10-17 years old and compare outcomes with those who did not receive the intervention. METHODS: This observational, prospective cohort study started with community engagement and followed the principles of ownership, control, access and possession (OCAP). We linked participant data to administrative data at the Manitoba Centre for Health Policy to assess rates of primary care and nephrology visits, disease-modifying medication prescriptions and laboratory testing (i.e., glycosylated hemoglobin [HbA1c], estimated glomerural filtration rate [eGFR] and urine albumin- or protein-to-creatinine ratio). We analyzed the differences in proportions in the 18 months before and after the intervention. We also conducted a 1:2 propensity score matching analysis to compare outcomes of children who were screened with those who were not. RESULTS: We included 324 of 353 children from the screening program (43.8% male; median age 12.3 yr) in this study. After the intervention, laboratory testing increased by 5.8% (95% confidence interval [CI] 1.1% to 10.1%) for HbA1c, by 9.9% (95% CI 4.2% to 15.5%) for eGFR and by 6.2% (95% CI 2.3% to 10.0%) for the urine albumin- or protein-to-creatinine ratio. We observed significant improvements in laboratory testing in screened patients in the group who were part of the program, compared with matched controls. INTERPRETATION: Chronic disease surveillance and care increased significantly in children after the implementation of a point-of-care screening program in rural and remote First Nation communities. Interventions such as active surveillance programs have the potential to improve the chronic disease care being provided to First Nations children.

Metabolic acidosis is associated with increased risk of adverse kidney outcomes and mortality in patients with non-dialysis dependent chronic kidney disease: an observational cohort study.

BACKGROUND: Management of chronic kidney disease (CKD) requires the management of risk factors, such as hypertension and albuminuria, that affect CKD progression. Identification of additional modifiable risk factors is necessary to develop new treatment strategies for CKD. We sought to quantify the association of metabolic acidosis with CKD progression and mortality in a large U.S. community-based cohort. METHODS: In this longitudinal, retrospective cohort study we identified non-dialysis-dependent patients with stage 3‒5 CKD from Optum's de-identified integrated electronic health records. We selected cohorts of patients with confirmed metabolic acidosis or normal serum bicarbonate levels based on 2 consecutive serum bicarbonate values: 12 to < 22 mEq/L or 22-29 mEq/L, respectively, 28‒365 days apart. The primary composite outcome was ≥ 40 % decline in estimated glomerular filtration rate (eGFR), renal replacement therapy (chronic dialysis or kidney transplant), or all-cause mortality (DD40). Secondary outcomes included each component of the composite outcome. Cox proportional hazards models were used for the DD40 outcome and secondary outcomes, while logistic regression models were used for the DD40 outcome at 2 years. RESULTS: A total of 51,558 patients qualified for the study. The unadjusted 2-year incidence of adverse renal and fatal outcomes was significantly worse among patients in the metabolic acidosis group vs. those who had normal serum bicarbonate levels: 48 % vs. 17 % for DD40, 10 % vs. 4 % for ≥ 40 % decline in eGFR, 20 % vs. 6 % for renal replacement therapy, and 31 % vs. 10 % for all-cause mortality (all P < 0.001). Over a ≤ 10-year period, for each 1-mEq/L increase in serum bicarbonate, the adjusted hazard ratio for DD40 was 0.926 (95 % confidence interval [CI], 0.922-0.930; P < 0.001); over a ≤ 2-year period, the adjusted odds ratio for DD40 was 0.873 (95 % CI, 0.866-0.879; P < 0.001). CONCLUSIONS: In this large community cohort of patients with stage 3‒5 CKD, the presence of metabolic acidosis was a significant, independent risk factor for the composite adverse outcome of CKD progression, renal replacement therapy, and all-cause mortality (DD40).

Peripheral Artery Disease: Its Adverse Consequences With and Without CKD.

RATIONALE & OBJECTIVES: Chronic kidney disease (CKD) is a potent risk factor for macrovascular disease and death. Peripheral artery disease (PAD) is more common in patients with CKD and is associated with lower-limb complications and mortality. We sought to compare the prevalence of PAD in and outside the setting of kidney disease and examine how PAD affects the risk for adverse health outcomes, specifically lower-limb complications, cardiovascular events, and survival. STUDY DESIGN: Retrospective cohort study. SETTING & PARTICIPANTS: 453,573 adult residents of Manitoba with at least 1 serum creatinine measurement between 2007 and 2014. EXPOSURE: PAD defined by hospital discharge diagnosis codes and medical claims. OUTCOMES: All-cause mortality, cardiovascular events, and lower-limb complications, including foot ulcers and nontraumatic amputations. ANALYTICAL APPROACH: Survival analysis using Cox proportional hazards models. RESULTS: The prevalence of PAD in our study population was 4.5%, and patients with PAD were older, were more likely to be male, and had a higher burden of comorbid conditions, including diabetes and CKD. PAD was associated with higher risks for all-cause mortality, cardiovascular events, and lower-limb complications in patients with estimated glomerular filtration rate (eGFR) ≥ 60mL/min/1.73m2, those with CKD GFR categories 3 to 5 (G3-G5), and those treated by dialysis (CKD G5D). Although HRs for PAD were lower in the CKD population, event rates were higher as compared with those with eGFR≥60mL/min/1.73m2. In particular, compared with patients with eGFR≥60mL/min/1.73m2 and without PAD, patients with CKD G5D had 10- and 12-fold higher risks for lower-limb complications, respectively (adjusted HRs of 10.36 [95% CI, 8.83-12.16] and 12.02 [95% CI, 9.58-15.08] for those without and with PAD, respectively), and an event rate of 75/1,000 patient-years. LIMITATIONS: Potential undercounting of PAD and complications using administrative codes and the limited ability to examine quality-of-care indicators for PAD. CONCLUSIONS: PAD is more common in patients with CKD G3-G5 and G5D compared with those with eGFR≥60mL/min/1.73m2 and frequently leads to lower-limb complications. Medical interventions and care pathways specifically designed to slow or prevent the development of lower-limb complications in this population are urgently needed.

Screening for kidney disease in Indigenous Canadian children: The FINISHED screen, triage and treat program.

BACKGROUND: Indigenous populations are disproportionately affected by kidney failure at younger ages than other ethnic groups in Canada. As symptoms do not occur until disease is advanced, early kidney disease risk is often unrecognized. OBJECTIVES: We sought to evaluate the yield of community-based screening for early risk factors for kidney disease in youth from rural Indigenous communities in Canada. METHODS: The FINISHED project screened 11 rural First Nations communities in Manitoba, Canada after community and school engagement. The results for the 10- to 17-year olds are reported here. Body mass index (BMI), blood pressure, estimated glomerular filtration rate (eGFR), hemoglobin A1c's (HbA1c) and urine albumin-to-creatinine ratios (ACR) were assessed. All children were triaged and referred to either primary or tertiary care, depending on risk. RESULTS: A total of 353 were screened (estimated 22.4% of population). The median age was 12 years (IQR 10 to 13), 55% were female and 55% were overweight or obese. Overall, 21.8% of children had at least one abnormality. Hypertension was identified in 5.4% and 11.9% had prehypertension. None of the children had an eGFR < 60 ml/min/1.73 m2 however 10.5% had an ACR > 3 mg/mmol and 6.2% had an eGFR < 90 ml/min/1.73 m2 suggestive of early kidney disease. Diabetes was identified in 1.4%, and 1.4% had HbA1c's between 6.1% and 6.49%. CONCLUSIONS: Risk factors for chronic kidney disease are highly prevalent in rural Indigenous children. More research is required to confirm the persistence of these findings, and to evaluate the efficacy of screening children to prevent or delay progression to kidney failure.

Screening for chronic kidney disease in Canadian indigenous peoples is cost-effective.

Canadian indigenous (First Nations) have rates of kidney failure that are 2- to 4-fold higher than the non-indigenous general Canadian population. As such, a strategy of targeted screening and treatment for CKD may be cost-effective in this population. Our objective was to assess the cost utility of screening and subsequent treatment for CKD in rural Canadian indigenous adults by both estimated glomerular filtration rate and the urine albumin-to-creatinine ratio. A decision analytic Markov model was constructed comparing the screening and treatment strategy to usual care. Primary outcomes were presented as incremental cost-effectiveness ratios (ICERs) presented as a cost per quality-adjusted life-year (QALY). Screening for CKD was associated with an ICER of $23,700/QALY in comparison to usual care. Restricting the model to screening in communities accessed only by air travel (CKD prevalence 34.4%), this ratio fell to $7,790/QALY. In road accessible communities (CKD prevalence 17.6%) the ICER was $52,480/QALY. The model was robust to changes in influential variables when tested in univariate sensitivity analyses. Probabilistic sensitivity analysis found 72% of simulations to be cost-effective at a $50,000/QALY threshold and 93% of simulations to be cost-effective at a $100,000/QALY threshold. Thus, targeted screening and treatment for CKD using point-of-care testing equipment in rural Canadian indigenous populations is cost-effective, particularly in remote air access-only communities with the highest risk of CKD and kidney failure. Evaluation of targeted screening initiatives with cluster randomized controlled trials and integration of screening into routine clinical visits in communities with the highest risk is recommended.

Change in estimated glomerular filtration rate and outcomes in chronic kidney disease.

PURPOSE OF REVIEW: Estimated glomerular filtration rate (eGFR) is important in the diagnosis and prognostication of chronic kidney disease (CKD). The current standards for CKD progression in clinical trials are kidney failure and the doubling of serum creatinine (∼57% decline in eGFR). These endpoints have limitations as they are only applicable to patients with later stages of CKD and often require large sample sizes to achieve adequate power. RECENT FINDINGS: Lesser declines in eGFR (30% and 40%) have been evaluated as potential endpoints in recent studies. These endpoints are more common and show a strong association with the risk of end-stage renal disease and mortality. These findings have been shown to be consistent across different causes of CKD and for different interventions. A particular limitation of reduced thresholds is an elevated risk of type I errors in the presence of acute treatment effects, particularly with a 30% eGFR decline cut off. SUMMARY: Surrogate endpoints for kidney failure and mortality are needed in clinical trials to allow for the reasonable management of timelines and resources, and the achievement of adequate sample sizes. Lesser eGFR decline thresholds should be considered to aid in the design and conduct of more randomized controlled trials in nephrology.

The Prevalence of CKD in Rural Canadian Indigenous Peoples: Results From the First Nations Community Based Screening to Improve Kidney Health and Prevent Dialysis (FINISHED) Screen, Triage, and Treat Program.

BACKGROUND: Indigenous Canadians have high rates of risk factors for chronic kidney disease (CKD), in particular diabetes. Furthermore, they have increased rates of complications associated with CKD, such as kidney failure and vascular disease. Our objective was to describe the prevalence of CKD in this population. STUDY DESIGN: Cross-sectional cohort. SETTING & PARTICIPANTS: Indigenous (First Nations) Canadians 18 years or older screened as part of the First Nations Community Based Screening to Improve Kidney Health and Prevent Dialysis (FINISHED) project, an initiative completed in 2015 that accomplished community-wide screening in 11 rural communities in Manitoba, Canada. PREDICTORS: Indigenous ethnicity and geographic location (communities accessible by road compared with those accessible only by air). OUTCOME: Prevalence of CKD, presumed based on a single ascertainment of urine albumin-creatinine ratio (UACR) ≥ 30mg/g and/or estimated glomerular filtration rate (eGFR)<60mL/min/1.73m(2). MEASUREMENTS: Kidney function measured by eGFR (CKD-EPI creatinine equation) and UACR. RESULTS: 1,346 adults were screened; 25.5% had CKD, defined as UACR≥30mg/g or eGFR<60mL/min/1.73m(2). Communities accessible by road had a lower prevalence of CKD (17.6%) than more remote communities accessible only by air (34.4%). Of those screened, 3.3% had reduced kidney function (defined as eGFR<60mL/min/1.73m(2)). Severely increased albuminuria was present in 5.0% of those screened. LIMITATIONS: Presumption of chronicity based on a single ascertainment. There is a possibility of sampling bias, the net direction of which is uncertain. CONCLUSIONS: We found a 2-fold higher prevalence of CKD in indigenous Canadians in comparison to the general population and a prevalence of severely increased albuminuria that was 5-fold higher. This is comparable to patients with diabetes and/or hypertension. Public health strategies to screen, triage, and treat all Canadian indigenous peoples with CKD should be considered.

Cystatin C as a biomarker for estimating glomerular filtration rate.

PURPOSE OF REVIEW: Glomerular filtration rate (GFR) is rarely measured in clinical practice because of the complexity of the measurement. As such, kidney function is typically estimated using validated study equations, which use readily available data including age, sex, race, and serum creatinine as filtration marker. Contemporary research suggests that cystatin C may be an improved alternative to creatinine for inclusion in GFR estimating equations. The purpose of this article is to evaluate the benefits and limitations of using cystatin C as a biomarker of filtration. RECENT FINDINGS: Cystatin C has fewer non-GFR determinants, when compared with serum creatinine. Use of serum cystatin C avoids the limitations related to both diet and muscle mass that affect serum creatinine. Cystatin C may be more accurate than serum creatinine in estimating GFR, and is more strongly associated with all-cause mortality and cardiovascular events. SUMMARY: Cystatin C has some advantages over serum creatinine in estimating GFR. The use of cystatin C as a confirmatory biomarker in deciding medication dosages or as a confirmatory test in patients with an uncertain diagnosis of chronic kidney disease may be beneficial.

Cost-effectiveness of primary screening for CKD: a systematic review.

BACKGROUND: Chronic kidney disease (CKD) is a major health problem with an increasing incidence worldwide. Data on the cost-effectiveness of CKD screening in the general population have been conflicting. STUDY DESIGN: Systematic review. SETTING & POPULATION: General, hypertensive, and diabetic populations. No restriction on setting. SELECTION CRITERIA FOR STUDIES: Studies that evaluated the cost-effectiveness of screening for CKD. INTERVENTION: Screening for CKD by proteinuria or estimated glomerular filtration rate (eGFR). OUTCOMES: Incremental cost-effectiveness ratio of screening by proteinuria or eGFR compared with either no screening or usual care. RESULTS: 9 studies met criteria for inclusion. 8 studies evaluated the cost-effectiveness of proteinuria screening and 2 evaluated screening with eGFR. For proteinuria screening, incremental cost-effectiveness ratios ranged from $14,063-$160,018/quality-adjusted life-year (QALY) in the general population, $5,298-$54,943/QALY in the diabetic population, and $23,028-$73,939/QALY in the hypertensive population. For eGFR screening, one study reported a cost of $23,680/QALY in the diabetic population and the range across the 2 studies was $100,253-$109,912/QALY in the general population. The incidence of CKD, rate of progression, and effectiveness of drug therapy were major drivers of cost-effectiveness. LIMITATIONS: Few studies evaluated screening by eGFR. Performance of a quantitative meta-analysis on influential assumptions was not conducted because of few available studies and heterogeneity in model designs. CONCLUSIONS: Screening for CKD is suggested to be cost-effective in patients with diabetes and hypertension. CKD screening may be cost-effective in populations with higher incidences of CKD, rapid rates of progression, and more effective drug therapy.

Expanding Access to High KDPI Kidney Transplant for Recipients Aged 60 y and Older: Cost Utility and Survival.

Background: Modern organ allocation systems are tasked with equitably maximizing the utility of transplanted organs. Increasing the use of deceased donor organs at risk of discard may be a cost-effective strategy to improve overall transplant benefit. We determined the survival implications and cost utility of increasing the use of marginal kidneys in an older adult Canadian population of patients with end-stage kidney disease. Methods: We constructed a cost-utility model with microsimulation from the perspective of the Canadian single-payer health system for incident transplant waitlisted patients aged 60 y and older. A kidney donor profile index score of ≥86 was considered a marginal kidney. Donor- and recipient-level characteristics encompassed in the kidney donor profile index and estimated posttransplant survival scores were used to derive survival posttransplant. Patients were followed up for 10 y from the date of waitlist initiation. Our analysis compared the routine use of marginal kidneys (marginal kidney scenario) with the current practice of limited use (status quo scenario). Results: The 10-y mean cost and quality-adjusted life-years per patient in the marginal kidney scenario were estimated at $379 485.33 (SD: $156 872.49) and 4.77 (SD: 1.87). In the status quo scenario, the mean cost and quality-adjusted life-years per patient were $402 937.68 (SD: $168 508.85) and 4.37 (SD: 1.87); thus, the intervention was considered dominant. At 10 y, 62.8% and 57.0% of the respective cohorts in the marginal kidney and status quo scenarios remained alive. Conclusions: Increasing the use of marginal kidneys in patients with end-stage kidney disease aged 60 y and older may offer cost savings, improved quality of life, and greater patient survival in comparison with usual care.

A Machine Learning Model to Predict Diuretic Resistance.

BACKGROUND: Volume overload is a common complication encountered in hospitalized patients, and the mainstay of therapy is diuresis. Unfortunately, the diuretic response in some individuals is inadequate despite a typical dose of loop diuretics, a phenomenon called diuretic resistance. An accurate prediction model that predicts diuretic resistance using predosing variables could inform the right diuretic dose for a prospective patient. METHODS: Two large, deidentified, publicly available, and independent intensive care unit (ICU) databases from the United States were used-the Medical Information Mart for Intensive Care III (MIMIC) and the Philips eICU databases. Loop diuretic resistance was defined as <1400 ml of urine per 40 mg of diuretic dose in 24 hours. Using 24-hour windows throughout admission, commonly accessible variables were obtained and incorporated into the model. Data imputation was performed using a highly accurate machine learning method. Using XGBoost, several models were created using train and test datasets from the eICU database. These were then combined into an ensemble model optimized for increased specificity and then externally validated on the MIMIC database. RESULTS: The final ensemble model was composed of four separate models, each using 21 commonly available variables. The ensemble model outperformed individual models during validation. Higher serum creatinine, lower systolic blood pressure, lower serum chloride, higher age, and female sex were the most important predictors of diuretic resistance (in that order). The specificity of the model on external validation was 92%, yielding a positive likelihood ratio of 3.46 while maintaining overall discrimination (C-statistic 0.69). CONCLUSIONS: A diuretic resistance prediction model was created using machine learning and was externally validated in ICU populations. The model is easy to use, would provide actionable information at the bedside, and would be ready for implementation in existing electronic medical records. This study also provides a framework for the development of future machine learning models.

Association of the Kidney Failure Risk Equation With High Health Care Costs.

Introduction: The Kidney Failure Risk Equations (KFRE) are accurate and validated to predict the risk of kidney failure in individuals with chronic kidney disease (CKD), but their potential to predict health care costs in the US health care system is unknown. We assessed the association of kidney failure risk from the 4-variable and 8-variable 2-year KFRE models with monthly health care costs in US patients with CKD stages G3 and G4. Methods: This was an ancillary study to a larger observational, retrospective cohort study examining the association between serum bicarbonate and adverse kidney outcomes. Monthly medical costs were calculated from individual health care insurance claims. Generalized linear regression models were used to examine the association of KFRE score with health care costs. Results: A total of 1721 patients qualified for the study (1475 and 246 with CKD stages G3 and G4, respectively). For 8-variable KFRE, each 1% (absolute) increase in risk was associated with 13.5% (P < 0.001) and 4.1% (P < 0.001) higher monthly costs for patients with CKD stage G3 and G4, respectively. For 4-variable KFRE, a 1% increase in risk was associated with 6.7% (P = 0.016) and 2.9% (P= 0.014) increase in monthly costs for patients with CKD stage G3 and G4, respectively. Conclusion: Higher risks of kidney failure as predicted by the 4-variable or 8-variable KFRE were associated with higher 2-year medical costs for patients with CKD stages G3 and G4. The KFRE may be a useful tool to anticipate medical costs and target cost-reducing interventions for patients at risk of kidney failure.