Optimizing the timing of nephrology referral for patients with diabetic kidney disease

Epidemiology and referral patterns of patients living with chronic kidney disease in Johannesburg, South Africa: A single centre experience

Chronic kidney disease (CKD) is a significant contributor to the global burden of non-communicable disease. Early intervention may facilitate slowing down of progression of CKD; recognition of at-risk patient groups may improve detection through screening. We retrospectively reviewed the clinical records of 960 patients attending a specialist nephrology outpatient clinic during the period 1 January 2011-31 December 2021. A significant proportion (47.8%) of patients were referred with established CKD stage G4 or G5. Non-national immigration status, previous diagnosis with diabetes, and advancing age were associated with late referral; antecedent diagnosis with HIV reduced the odds of late referral. Black African patients comprised most of the sample cohort and were younger at referral and more frequently female than other ethnicities; non-nationals were younger at referral than South Africans. Hypertension-associated kidney disease was the leading ascribed aetiological factor for CKD (40.7% of cases), followed by diabetic kidney disease (DKD) (19%), glomerular disease (12.5%), and HIV-associated kidney disease (11.8%). Hypertension-related (25.9%) and diabetic (10.7%) kidney diseases were not uncommon in people living with HIV. Advancing age and male sex increased the likelihood of diagnosis with hypertensive nephropathy, DKD and obstructive uropathy; males were additionally at increased risk of HIV-associated kidney disease and nephrotoxin exposure, as were patients of Black African ethnicity. In summary, this data shows that hypertension, diabetes, and HIV remain important aetiological factors in CKD in the South African context. Despite the well-described risk of CKD in these disorders, referral to nephrology services occurs late. Interventions and policy actions targeting at-risk populations are required to improve referral practices.

Multicentre external validation of the prognostic model kidney failure risk equation in patients with CKD stages 3 and 4 in Peru: a retrospective cohort study

OBJECTIVES

To externally validate the four-variable kidney failure risk equation (KFRE) in the Peruvian population for predicting kidney failure at 2 and 5 years.

DESIGN

A retrospective cohort study.

SETTING

17 primary care centres from the Health's Social Security of Peru.

PARTICIPANTS

Patients older than 18 years, diagnosed with chronic kidney disease stage 3a-3b-4 and 3b-4, between January 2013 and December 2017. Patients were followed until they developed kidney failure, died, were lost, or ended the study (31 December 2019), whichever came first.

PRIMARY AND SECONDARY OUTCOME MEASURES

Performance of the KFRE model was assessed based on discrimination and calibration measures considering the competing risk of death.

RESULTS

We included 7519 patients in stages 3a-4 and 2798 patients in stages 3b-4. The estimated cumulative incidence of kidney failure, accounting for competing event of death, at 2 years and 5 years, was 1.52% and 3.37% in stages 3a-4 and 3.15% and 6.86% in stages 3b-4. KFRE discrimination at 2 and 5 years was high, with time-dependent area under the curve and C-index >0.8 for all populations. Regarding calibration in-the-large, the observed to expected ratio and the calibration intercept indicated that KFRE underestimates the overall risk at 2 years and overestimates it at 5 years in all populations.

CONCLUSIONS

The four-variable KFRE models have good discrimination but poor calibration in the Peruvian population. The model underestimates the risk of kidney failure in the short term and overestimates it in the long term. Further research should focus on updating or recalibrating the KFRE model to better predict kidney failure in the Peruvian context before recommending its use in clinical practice.

Machine Learning Models to Predict the Risk of Rapidly Progressive Kidney Disease and the Need for Nephrology Referral in Adult Patients with Type 2 Diabetes

Early detection of rapidly progressive kidney disease is key to improving the renal outcome and reducing complications in adult patients with type 2 diabetes mellitus (T2DM). We aimed to construct a 6-month machine learning (ML) predictive model for the risk of rapidly progressive kidney disease and the need for nephrology referral in adult patients with T2DM and an initial estimated glomerular filtration rate (eGFR) ≥ 60 mL/min/1.73 m2. We extracted patients and medical features from the electronic medical records (EMR), and the cohort was divided into a training/validation and testing data set to develop and validate the models on the basis of three algorithms: logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost). We also applied an ensemble approach using soft voting classifier to classify the referral group. We used the area under the receiver operating characteristic curve (AUROC), precision, recall, and accuracy as the metrics to evaluate the performance. Shapley additive explanations (SHAP) values were used to evaluate the feature importance. The XGB model had higher accuracy and relatively higher precision in the referral group as compared with the LR and RF models, but LR and RF models had higher recall in the referral group. In general, the ensemble voting classifier had relatively higher accuracy, higher AUROC, and higher recall in the referral group as compared with the other three models. In addition, we found a more specific definition of the target improved the model performance in our study. In conclusion, we built a 6-month ML predictive model for the risk of rapidly progressive kidney disease. Early detection and then nephrology referral may facilitate appropriate management.

Referral patterns, disease progression and impact of the kidney failure risk equation (KFRE) in a Queensland Chronic Kidney Disease Registry (CKD.QLD) cohort: a study protocol

INTRODUCTION

Chronic kidney disease (CKD) is a rapidly increasing and global phenomenon which carries high morbidity and mortality. Although timely referral from primary care to secondary care confers favourable outcomes, it is not possible for every patient with CKD to be managed at secondary care. With 1 in 10 Australians currently living with markers of CKD against a workforce of about 600 nephrology specialists, a risk stratification strategy is required that will reliably identify individuals whose kidney disease is likely to progress.

METHODS AND ANALYSIS

This study will undertake a retrospective secondary analysis of the Chronic Kidney Disease Queensland Registry (CKD.QLD) data of consented adults to examine the referral patterns to specialist nephrology services from primary care providers and map the patient trajectory and outcomes to inform the optimal referral timing for disease mitigation. Patient data over a 5-year period will be examined to determine the impact of the kidney failure risk equation-based risk stratification on the referral patterns, disease progression and patient outcomes. The results will inform considerations of a risk stratification strategy that will ensure adequate predialysis management and add to the discussion of the time interval between referral and initiation of kidney replacement therapy or development of cardiovascular events.

ETHICS AND DISSEMINATION

This protocol was approved by the Ethics Committee of the Royal Brisbane and Women's Hospital in January 2021 (LNR/2020/QRBW/69707 14/01/2021). The HREC waived the requirement for patient consent as all patients had consented for the use of their data for the purpose of research on recruitment into CKD.QLD Registry. The results will be presented as a component of a PhD study with The University of Queensland. It is anticipated that the results will be presented at health-related conferences (local, national and possibly international) and via publication in peer-reviewed academic journals.

Kidney Disease in Diabetic Patients: From Pathophysiology to Pharmacological Aspects with a Focus on Therapeutic Inertia

Diabetes mellitus represents a growing concern, both for public economy and global health. In fact, it can lead to insidious macrovascular and microvascular complications, impacting negatively on patients' quality of life. Diabetic patients often present diabetic kidney disease (DKD), a burdensome complication that can be silent for years. The average time of onset of kidney impairment in diabetic patients is about 7-10 years. The clinical impact of DKD is dangerous not only for the risk of progression to end-stage renal disease and therefore to renal replacement therapies, but also because of the associated increase in cardiovascular events. An early recognition of risk factors for DKD progression can be decisive in decreasing morbidity and mortality. DKD presents patient-related, clinician-related, and system-related issues. All these problems are translated into therapeutic inertia, which is defined as the failure to initiate or intensify therapy on time according to evidence-based clinical guidelines. Therapeutic inertia can be resolved by a multidisciplinary pool of healthcare experts. The timing of intensification of treatment, the transition to the best therapy, and dietetic strategies must be provided by a multidisciplinary team, driving the patients to the glycemic target and delaying or overcoming DKD-related complications. A timely nephrological evaluation can also guarantee adequate information to choose the right renal replacement therapy at the right time in case of renal impairment progression.