Screening, identifying, and treating chronic kidney disease: why, who, when, how, and what?

1 in 7 American adults have chronic kidney disease (CKD); a disease that increases risk for CKD progression, cardiovascular events, and mortality. Currently, the US Preventative Services Task Force does not have a screening recommendation, though evidence suggests that screening can prevent progression and is cost-effective. Populations at risk for CKD, such as those with hypertension, diabetes, and age greater than 50 years should be targeted for screening. CKD is diagnosed and risk stratified with estimated glomerular filtration rate utilizing serum creatinine and measuring urine albumin-to-creatinine ratio. Once identified, CKD is staged according to C-G-A classification, and managed with lifestyle modification, interdisciplinary care and the recently expanding repertoire of pharmacotherapy which includes angiotensin converting enzyme inhibitors or angiotensin-II receptor blockers, sodium-glucose-cotransporter-2 inhibitors, and mineralocorticorticoid receptor antagonists. In this paper, we present the why, who, when, how, and what of CKD screening.

Cystatin C as a GFR Estimation Marker in Acute and Chronic Illness: A Systematic Review.

Rationale & Objective: Creatinine-based GFR estimating (eGFRcr) equations may be inaccurate in populations with acute or chronic illness. The accuracy of GFR equations that use cystatin C (eGFRcys) or creatinine-cystatin C (eGFRcr-cys) is not well studied in these populations. Study Design: A systematic review of original articles identified from PubMed and expert sources. Two reviewers screened articles independently and identified those meeting inclusion criteria. Setting & Study Populations: Adults and children with acute or chronic illness. Selection Criteria for Studies: Studies published since 2011 that compared performance of eGFRcr, eGFRcys, and eGFRcr-cys relative to measured GFR (mGFR), used standardized assays for creatinine or cystatin C, and used eGFR equations developed using such assays. Studies of ambulatory clinical populations or research studies in populations with only CKD, kidney transplant recipients, only diabetes, kidney donor candidates, and community-based cohorts were excluded. Data Extraction: Data extracted from full text. Analytical Approach: Bias and percentages of estimates within 30% of mGFR (P30) of eGFR compared with mGFR were evaluated. Results: Of the 179 citations, 26 studies met the inclusion criteria: 24 in adults and 2 in children in clinical populations with cancer (n=5), HIV (n=5), cirrhosis (n=3), liver transplant (n=3), heart failure (n=2), neuromuscular diseases (n=1) critical illness (n=5), and obesity (n=2). In general, eGFRcr-cys had greater accuracy than eGFRcr or eGFRcys equations among study populations with cancer, HIV, and obesity, but did not perform consistently better in cirrhosis, liver transplant, heart failure, neuromuscular disease, and critical illness. Limitations: Participants were selected because of concern for inaccurate eGFRcr, which may bias results. Most studies had small sample sizes, limiting generalizability. Conclusions: eGFRcr-cys improves GFR estimation in populations with a variety of acute and chronic illnesses, providing indications for cystatin C measurement. Performance was poor in many studies, suggesting the need for more frequent mGFR. Plain-Language Summary: Kidney function, specifically glomerular filtration rate (GFR), estimated using creatinine (eGFRcr) is often inaccurate in people with acute and chronic illness. The accuracy of estimates using cystatin C alone (eGFRcys) or together with creatinine (eGFRcr-cys) is not well studied in these populations. We conducted a systematic review to address the knowledge gap. Of the 179 papers reviewed, we identified 26 studies in clinical populations with cancer (n=5); HIV (n=5); cirrhosis (n=3); liver transplant (n=3); heart failure (n=2); neuromuscular disease (n=1); critical illness (n=5); and obesity (n=2). In general, eGFRcr-cys improved the GFR estimation in HIV, cancer, and obesity, providing indications for cystatin C measurement. Performance was poor in many studies, suggesting the need for more frequent measured GFR.

Fulfillment and Validity of the Kidney Health Evaluation Measure for People with Diabetes.

Objective: To evaluate the fulfillment and validity of the kidney health evaluation for people with diabetes (KED) Healthcare Effectiveness Data Information Set (HEDIS) measure. Patients and Methods: Optum Labs Data Warehouse (OLDW) was used to identify the nationally distributed US population aged 18 years and older, with diabetes, between January 1, 2017, and December 31, 2017. The OLDW includes deidentified medical, pharmacy, laboratory, and electronic health record (EHR) data. The KED fulfillment was defined in 2017 as both estimated glomerular filtration rate (eGFR) and urinary albumin-creatinine ratio testing within the measurement year. The KED validity was assessed using bivariate analyses of KED fulfillment with diabetes care measures in 2017 and chronic kidney disease (CKD) diagnosis and evidence-based kidney protective interventions in 2018. Results: Among eligible 5,635,619 Medicare fee-for-service beneficiaries, 736,875 Medicare advantage (MA) beneficiaries, and 660,987 commercial patients, KED fulfillment was 32.2%, 38.7%, and 37.7%, respectively. Albuminuria testing limited KED fulfillment with urinary albumin-creatinine ratio testing (<40%) and eGFR testing (>90%). The KED fulfillment was positively associated with receipt of diabetes care in 2017, CKD diagnosis in 2018, and evidence-based kidney protective interventions in 2018. The KED fulfillment trended lower for Black race, Medicare-Medicaid dual eligibility status, low neighborhood income, and low education status. Conclusion: Less than 40% of adults with diabetes received guideline-recommended testing for CKD in 2017. Routine KED was associated with diabetes care and evidence-based CKD interventions. Increasing guideline-recommended testing for CKD among people with diabetes should lead to timely and equitable CKD detection and treatment.

CKD and Rapid Kidney Function Decline During the COVID-19 Pandemic.

Rationale & Objective: The direct and indirect effects of the coronavirus disease 2019 (COVID-19) pandemic on kidney function in the chronic kidney disease (CKD) population are not well understood. Study Design: Cohort study. Setting & Participants: Retrospective study of kidney function trajectories using deidentified administrative claims and laboratory data for Medicare Advantage and commercially insured enrollees with CKD stages G3-4 between 2018 and 2021. Predictors: COVID-19 infection. Outcome: Rapid kidney function decline defined as annual estimated glomerular filtration rate (eGFR) decline of ≥40%. Analytical Approach: Propensity score matching was used to identify individuals without COVID-19 infection matched 1:1 to a COVID-19 infected cohort and indexed on the date of diagnosing COVID-19 infection, age, sex, race or ethnicity, and Charlson comorbidity index score. Outpatient kidney function was compared during the prepandemic period (January 1, 2018, to February 29, 2020) with the pandemic period (March 1, 2020, to August 31, 2021). Two creatinine measurements, after the infection date and ≥60 days apart, were required to reduce correlation with acute infection. Results: Of 97,203 enrollees with CKD G3-4, 9% experienced a COVID-19 infection. Characteristics of 8,901 propensity matched enrollees include mean age 74 years, 58% women, 67% White, and 63% CKD G3a, 28% CKD G3b, and 9% CKD G4. Median overall annual eGFR change was -2.65 ml/min/1.73m2, with 76% of the cohort experiencing worsened eGFR in the pandemic period. Rapid kidney function decline was observed in 1.9% and 2.0% of enrollees in the prepandemic and pandemic periods, respectively. Rapid kidney function decline was observed in 2.5% of those with COVID-19 infection and 1.5% of those without COVID-19 infection (P < 0.05). Factors associated with increased odds of rapid kidney function decline during pandemic included Asian race, higher Charlson comorbidity index, advancing CKD stage, prepandemic rapid kidney function decline, and COVID-19 infection. Limitations: Retrospective study design with potential bias. Conclusions: COVID-19 infection increased odds of rapid kidney function decline during the pandemic. The downstream impact of pandemic-related eGFR decline on health outcomes, such as kidney failure or mortality, requires further study. Plain-Language Summary: We used a cohort of insured individuals with moderate-to-severe chronic kidney disease (CKD) to compare the rates of rapid kidney function decline in prepandemic and pandemic periods and to evaluate the impact of the coronavirus disease 19 (COVID-19) on kidney function decline. We found that overall rates of rapid kidney function decline did not change during the prepandemic and pandemic periods but were significantly higher in both periods among individuals with a COVID-19 infection. As CKD severity increased, rates of both rapid kidney function decline and COVID-19 increased. Advancing CKD, higher comorbid condition, Asian race, prepandemic rapid kidney function decline, and COVID-19 were all associated with higher odds of rapid kidney function decline in the pandemic. These findings suggest close monitoring is warranted for individuals with CKD and COVID-19.

A kidney diagnostic's impact on physician decision-making in diabetic kidney disease.

OBJECTIVES: Estimated glomerular filtration rate (eGFR) and albuminuria, the current standard-of-care tests that predict risk of kidney function decline in early-stage diabetic kidney disease (DKD), are only modestly useful. We evaluated the decision-making impact of an artificial intelligence-enabled prognostic test, KidneyIntelX, in the management of DKD by primary care physicians (PCPs). STUDY DESIGN: This was a prospective web-based survey administered among PCPs in the United States. METHODS: We used conjoint analysis with multivariable logit models to estimate PCP preferences. The survey included hypothetical patient profiles with 6 attributes: albuminuria, eGFR, age, blood pressure (BP), hemoglobin A1c (HbA1c), and KidneyIntelX result. Each PCP viewed 8 patient profiles randomly selected from 42 unique profiles having 1 level from each attribute. For each patient, PCPs were asked to indicate whether they would prescribe a sodium-glucose cotransporter-2 (SGLT2) inhibitor, increase angiotensin receptor blocker (ARB) dose, and/or refer to a nephrologist. RESULTS: A total of 401 PCPs completed the survey (response rate, 8.8%). The relative importance of the top 2 attributes for each decision were HbA1c (52%) and KidneyIntelX result (23%) for prescribing SGLT2 inhibitors, BP (62%) and KidneyIntelX result (13%) for increasing ARB dose, and eGFR (42%) and KidneyIntelX result (27%) for nephrologist referral. A high-risk KidneyIntelX result was associated with significantly higher odds of PCPs prescribing SGLT2 inhibitors (odds ratio [OR], 1.64; 95% CI, 1.29-2.08), increasing ARB dose (OR, 1.49; 95% CI, 1.17-1.89), and referring to a nephrologist (OR, 2.47; 95% CI, 1.99-3.08) compared with no test. CONCLUSIONS: The KidneyIntelX test had greater relative importance than albuminuria and eGFR to PCPs in making treatment decisions and was second only to eGFR for nephrologist referrals. Because of its significant impact on decision-making, KidneyIntelX has high clinical utility in DKD management.

Usability Testing of the Kidney Score Platform to Enhance Communication About Kidney Disease in Primary Care Settings: Qualitative Think-Aloud Study.

BACKGROUND: Patient awareness of chronic kidney disease (CKD) is low in part due to suboptimal testing for CKD among those at risk and lack of discussions about kidney disease between patients and clinicians. To bridge these gaps, the National Kidney Foundation developed the Kidney Score Platform, which is a web-based series of tools that includes resources for health care professionals as well as an interactive, dynamic patient-facing component that includes a brief questionnaire about risk factors for kidney disease, individualized assessment of risk for developing CKD, and self-management tools to manage one's kidney disease. OBJECTIVE: The aim of this study is to perform usability testing of the patient component of the Kidney Score platform among veterans with and at risk for kidney disease and among clinicians working as primary care providers in Veterans Affairs administration. METHODS: Think-aloud exercises were conducted, during which participants (veterans and clinicians) engaged with the platform while verbalizing their thoughts and making their perceptions, reasonings, and decision points explicit. A usability facilitator observed participants' behaviors and probed selectively to clarify their comprehension of the tool's instructions, content, and overall functionality. Thematic analysis on the audio-recording transcripts was performed, focusing on positive attributes, negative comments, and areas that required facilitator involvement. RESULTS: Veterans (N=18) were 78% (14/18) male with a mean age of 58.1 years. Two-thirds (12/18) were of non-White race/ethnicity, 28% (5/18) had laboratory evidence of CKD without a formal diagnosis, and 50% (9/18) carried a diagnosis of hypertension or diabetes. Clinicians (N=19) were 29% (5/17) male, 30% (5/17) of non-White race/ethnicity, and had a mean of 17 (range 4-32) years of experience. Veterans and clinicians easily navigated the online tool and appreciated the personalized results page as well as the inclusion of infographics to deliver key educational messages. Three major themes related to content and communication about risk for CKD emerged from the think-aloud exercises: (1) tension between lay and medical terminology when discussing kidney disease and diagnostic tests, (2) importance of linking general information to concrete self-management actions, and (3) usefulness of the tool as an adjunct to the office visit to prepare for patient-clinician communication. Importantly, these themes were consistent among interviews involving both veterans and clinicians. CONCLUSIONS: Veterans and clinicians both thought that the Kidney Score Platform would successfully promote communication and discussion about kidney disease in primary care settings. Tension between using medical terminology that is used regularly by clinicians versus lay terminology to promote CKD awareness was a key challenge, and knowledge of this can inform the development of future CKD educational materials.

Missing Care: the Initial Impact of the COVID-19 Pandemic on CKD Care Delivery.

BACKGROUND: Chronic kidney disease (CKD) is a common condition with adverse health outcomes addressable by early disease management. The impact of the COVID-19 pandemic on care utilization for the CKD population is unknown. OBJECTIVE: To examine pandemic CKD care and identify factors associated with a high care deficit. DESIGN: Retrospective observational study PARTICIPANTS: 248,898 insured individuals (95% Medicare Advantage, 5% commercial) with stage G3-G4 CKD in 2018 MAIN MEASURES: Predicted (based on the pre-pandemic period of January 1, 2019-February 28, 2020) to observed per-member monthly face-to-face and telehealth encounters, laboratory testing, and proportion of days covered (PDC) for medications, evaluated during the early (March 1, 2020-June 30, 2020), pre-vaccine (July 1, 2020-December 31, 2020), and late (January 2021-August 2021) periods and overall. KEY RESULTS: In-person encounters fell by 24.1% during the pandemic overall; this was mitigated by a 14.2% increase in telehealth encounters, resulting in a cumulative observed utilization deficit of 10% relative to predicted. These reductions were greatest in the early pandemic period, with a 19.8% cumulative deficit. PDC progressively decreased during the pandemic (range 9-20% overall reduction), with the greatest reductions in hypertension and diabetes medicines. CKD laboratory monitoring was also reduced (range 11.8-43.3%). Individuals of younger age (OR 1.63, 95% CI 1.16, 2.28), with commercial insurance (1.43, 95% CI 1.25, 1.63), residing in the Southern US (OR 1.17, 95% CI 1.14, 1.21), and with stage G4 CKD (OR 1.21, 95% CI 1.17, 1.26) had greater odds of a higher care deficit overall. CONCLUSIONS: The early COVID-19 pandemic resulted in a marked decline of healthcare services for individuals with CKD, with an incomplete recovery during the later pandemic. Increased telehealth use partially compensated for this deficit. The downstream impact of CKD care reduction on health outcomes requires further study, as does evaluation of effective care delivery models for this population.

Multiple Stakeholder Perspectives on the Reinvigorated Case for Kidney Disease Screening.

The United States Preventive Services Task Force has no current recommendation to guide primary care physician screening for chronic kidney disease (CKD). This is misaligned with the scope of the CKD public health emergency, recommendations from clinical practice guidelines, health spending on CKD, the changing landscape of CKD detection and treatment, and the focus by policymakers on identifying tangible approaches to improving health equity. This review summarizes patient, clinician, health equity, and health system perspectives in support of screening adults with risk factors for CKD. This review concludes with the assessment that the United States Preventive Services Task Force should revisit targeted CKD screening specifically for adults with diabetes and/or hypertension.

Integrating CKD Into US Primary Care: Bridging the Knowledge and Implementation Gaps.

Chronic kidney disease (CKD) affects 37 million American adults who experience high rates of cardiovascular events and are at risk of kidney failure and mortality. Routine primary care case finding for CKD with estimated glomerular filtration rate (eGFR) and urine albumin-creatinine ratio (uACR) should focus on risk conditions, particularly diabetes, hypertension, and cardiovascular disease, as recommended by clinical practice guidelines. The diagnosis of CKD is associated with many important aspects of care, including patient awareness, patient engagement, and improved implementation of evidence-based interventions. Individualized care that tailors CKD interventions proportional to the adverse outcome risk or the eGFR and uACR heat map is a major challenge for primary CKD care, because the condition is heterogeneous in terms of both the cause and the severity. The coordinated care approach to CKD management is necessary to deploy best practice in chronic disease management that engages the interdisciplinary team. An integrated system supports the time-constrained primary clinician with CKD registry functions, clinical decision support tools, quality improvement initiatives, and payment model incentives to drive reduction in adverse outcomes and containment of expenditures. A CKD population health strategy can be built to address primary care education and implementation gaps from the perspectives of testing, detection of disease, interventions, and coordinated system-integrated care. Registry function and data monitoring of the burden of CKD, delivery interventions, and outcomes are key features. Implementation of the Race-free 2021 CKD-(Epidemiology Collaboration) EPI eGFR reporting recommendations by engaging local nephrology, administrative, clinical laboratory, and health equity leaders should help drive the population health design strategy and the data assessment.

National Kidney Foundation Laboratory Engagement Working Group Recommendations for Implementing the CKD-EPI 2021 Race-Free Equations for Estimated Glomerular Filtration Rate: Practical Guidance for Clinical Laboratories.

Recognizing that race is a social and not a biological construct, healthcare professionals and the public have called for removal of race in clinical algorithms. In response, the National Kidney Foundation and the American Society of Nephrology created the Task Force on Reassessing the Inclusion of Race in Diagnosing Kidney Diseases to examine the issue and provide recommendations. The final report from the Task Force recommends calculating estimated glomerular filtration rate (eGFR) without a race coefficient using the recently published CKD-EPI 2021 creatinine (cr) and creatinine-cystatin C (cr-cys) equations. The Task Force recommends immediately replacing older eGFRcr equations (MDRD Study and CKD-EPI 2009) with the new CKD-EPI 2021 equation. In a 2019 survey by the College of American Pathologists, 23% of 6200 laboratories reporting eGFRcr used an incorrect equation that is not suitable for use with standardized creatinine measurements, 34% used the CKD-EPI 2009 equation and 43% used the MDRD Study 2006 equation re-expressed for standardized creatinine measurement. Rapid transition to using the CKD-EPI 2021 equation is an opportunity for laboratories to standardize to a single equation to eliminate differences in eGFRcr due to different equations used by different laboratories, and to report eGFR without use of race. We provide guidance to laboratories for implementing the CKD-EPI 2021 equations for both eGFRcr and eGFRcr-cys.

Chronic Kidney Disease Testing Among At-Risk Adults in the U.S. Remains Low: Real-World Evidence From a National Laboratory Database.

OBJECTIVE: An estimated 37 million Americans have chronic kidney disease (CKD). Nearly 90% do not know about their condition because of low awareness about the importance of CKD testing and diagnosis among practitioners and people at risk for CKD. This study uses data from a national clinical laboratory to identify guideline-recommended CKD testing rates across the U.S. RESEARCH DESIGN AND METHODS: Patients with Laboratory Corporation of America Holdings (Labcorp) testing between 2013 and 2019 were defined as at risk for CKD if they had any testing ordered with diagnosis codes for diabetes and/or hypertension. Guideline-concordant CKD assessment was defined by estimated glomerular filtration rate (eGFR) and urine albumin-to-creatinine ratio (uACR) testing within the study year. RESULTS: We identified 28,295,982 at-risk patients (mean age 60.6 ± 14.8 years; 53.6% women): 16.2% had diabetes, 63.8% had hypertension, and 20.1% had both comorbidities. Of these, 80.3% did not receive guideline-concordant assessment during the study period. Furthermore, only 21.0% had uACR testing versus 89.6% with eGFR. CKD assessment occurred at least once in 28.7% of patients with diabetes, 10.5% of patients with hypertension, and 41.4% of patients with both conditions. In a state-by-state comparison, annual testing rates ranged from 5 to 30%. The nationwide rate increased modestly each year between 2013 and 2018 (from 10.7% to 15.2%). CONCLUSIONS: Despite guideline recommendations, testing for CKD with uACR and eGFR in U.S. adults with diabetes and hypertension is low in routine clinical care. These data highlight the need for strategies to improve routine CKD assessment nationwide.

Reverse pseudohyperkalemia is more than leukocytosis: a retrospective study.

BACKGROUND: Hyperkalemia is a potentially life-threatening electrolyte abnormality that often requires urgent treatment. Clinicians should distinguish true hyperkalemia from pseudohyperkalemia and reverse pseudohyperkalemia (RPK). RPK has exclusively been described in case reports of patients with hematologic malignancies (HMs) and extreme leukocytosis [white blood cell (WBC) count >200 × 103/mL]. METHODS: This single-center retrospective study analyzed laboratory data from the Mount Sinai Data Warehouse between 1 January 2010 and 31 December 2016 for plasma potassium and serum potassium samples drawn within 1 h of each other, with plasma potassium ≥1 mEq/L of the serum potassium. Only plasma potassium ≥5 mEq/L were included. Samples that were documented to be hemolyzed or contaminated were excluded. Clinical history and laboratory data were collected from the identified cases. RESULTS: After applying the inclusion/exclusion criteria to 485 potential cases, the final cohort included 45 cases from 41 patients. There were 24 men and 17 women with a mean age of 52 years. The median plasma potassium was 6.1 mEq/L and serum potassium was 4.4 mEq/L. The median WBC count was 9.35 × 103/mL (interquartile range 6.5-19.7 × 103/mL). Only 44% of the samples had leukocytosis, defined as WBC >11 × 103/mL.Seven patients had a HM and comprised 11 of the cases (24%) with a median WBC of 181.8 × 103µL. There was no difference in their plasma and serum potassium levels when compared with the total cohort, despite a higher median WBC count. Thirty-eight percent of the cases required medical management. CONCLUSIONS: The literature on RPK is limited to case reports and series associated with extreme leukocytosis. This is the first study characterizing RPK predominantly associated with normal leukocyte counts. Further investigation is required to more precisely characterize factors associated with RPK and to elucidate RPK mechanisms.

Chronic Kidney Disease Testing Among Primary Care Patients With Type 2 Diabetes Across 24 U.S. Health Care Organizations.

OBJECTIVE: Clinical guidelines for people with diabetes recommend chronic kidney disease (CKD) testing at least annually using estimated glomerular filtration rate (eGFR) and urinary albumin-to-creatinine ratio (uACR). We aimed to understand CKD testing among people with type 2 diabetes in the U.S. RESEARCH DESIGN AND METHODS: Electronic health record data were analyzed from 513,165 adults with type 2 diabetes receiving primary care from 24 health care organizations and 1,164 clinical practice sites. We assessed the percentage of patients with both one or more eGFRs and one or more uACRs and each test individually in the 1, 2, and 3 years ending September 2019 by health care organization and clinical practice site. Elevated albuminuria was defined as uACR ≥30 mg/g. RESULTS: The 1-year median testing rate across organizations was 51.6% for both uACR and eGFR, 89.5% for eGFR, and 52.9% for uACR. uACR testing varied (10th-90th percentile) from 44.7 to 63.3% across organizations and from 13.3 to 75.4% across sites. Over 3 years, the median testing rate for uACR across organizations was 73.7%. Overall, the prevalence of detected elevated albuminuria was 15%. The average prevalence of detected elevated albuminuria increased linearly with uACR testing rates at sites, with estimated prevalence of 6%, 15%, and 30% at uACR testing rates of 20%, 50%, and 100%, respectively. CONCLUSIONS: While eGFR testing rates are uniformly high among people with type 2 diabetes, testing rates for uACR are suboptimal and highly variable across and within the organizations examined. Guideline-recommended uACR testing should increase detection of CKD.

A qualitative study documenting unmet needs in the management of diabetic kidney disease (DKD) in the primary care setting.

BACKGROUND: A majority of diabetic kidney disease (DKD) patients receive medical care in the primary care setting, making it an important opportunity to improve patient management. There is limited evidence evaluating whether primary care physicians (PCPs) are equipped to effectively manage these patients in routine clinical practice. The present study was undertaken to identify gaps in primary care and unmet needs in the diagnosis and monitoring of DKD in type 2 diabetes (T2D) patients among PCPs. METHODS: This was a qualitative analysis based on 30-45-min interviews with PCPs treating T2D patients. PCPs were recruited via email and were board-certified, in practice for more than 3 years, spent most of their time in direct clinical care, and provided care for more than three T2D patients in a week. Descriptive data analysis was conducted to identify and examine themes that were generated by interviews. Two reviewers evaluated interview data to identify themes and developed consensus on the priority themes identified. RESULTS: A total of 16 PCPs satisfying the inclusion criteria were recruited for qualitative interviews. Although the PCPs recognized kidney disease as an important comorbidity in T2D patients, testing for kidney disease was not consistently top of mind, with 56% reportedly performing kidney function testing in their T2D patients. PCPs most frequently reported using estimated glomerular filtration rate (eGFR) alone to monitor and stage DKD; only 25% PCPs reported testing for albuminuria. Most PCPs incorrectly believed that a majority of DKD patients are diagnosed in early stages. Also, early stages of DKD emerged as ambiguous areas of decision-making, wherein treatments prescribed greatly varied among PCPs. Lastly, early and accurate risk stratification of DKD patients emerged as the most important unmet need; which, if it could be overcome, was consistently identified by PCPs as a key to monitoring, appropriate nephrologist referrals, and intervening to improve outcomes in patients with DKD. CONCLUSIONS: Our study highlights important unmet needs in T2D DKD testing, staging, and stratification in the PCP setting that limit effective patient care. Health systems and insurers in the U.S. should prioritize the review and approval of new strategies that can improve DKD staging and risk stratification.

Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease.

AIM: Predicting progression in diabetic kidney disease (DKD) is critical to improving outcomes. We sought to develop/validate a machine-learned, prognostic risk score (KidneyIntelX™) combining electronic health records (EHR) and biomarkers. METHODS: This is an observational cohort study of patients with prevalent DKD/banked plasma from two EHR-linked biobanks. A random forest model was trained, and performance (AUC, positive and negative predictive values [PPV/NPV], and net reclassification index [NRI]) was compared with that of a clinical model and Kidney Disease: Improving Global Outcomes (KDIGO) categories for predicting a composite outcome of eGFR decline of ≥5 ml/min per year, ≥40% sustained decline, or kidney failure within 5 years. RESULTS: In 1146 patients, the median age was 63 years, 51% were female, the baseline eGFR was 54 ml min-1 [1.73 m]-2, the urine albumin to creatinine ratio (uACR) was 6.9 mg/mmol, follow-up was 4.3 years and 21% had the composite endpoint. On cross-validation in derivation (n = 686), KidneyIntelX had an AUC of 0.77 (95% CI 0.74, 0.79). In validation (n = 460), the AUC was 0.77 (95% CI 0.76, 0.79). By comparison, the AUC for the clinical model was 0.62 (95% CI 0.61, 0.63) in derivation and 0.61 (95% CI 0.60, 0.63) in validation. Using derivation cut-offs, KidneyIntelX stratified 46%, 37% and 17% of the validation cohort into low-, intermediate- and high-risk groups for the composite kidney endpoint, respectively. The PPV for progressive decline in kidney function in the high-risk group was 61% for KidneyIntelX vs 40% for the highest risk strata by KDIGO categorisation (p < 0.001). Only 10% of those scored as low risk by KidneyIntelX experienced progression (i.e., NPV of 90%). The NRIevent for the high-risk group was 41% (p < 0.05). CONCLUSIONS: KidneyIntelX improved prediction of kidney outcomes over KDIGO and clinical models in individuals with early stages of DKD.