A Predictive Model for Progression of CKD to Kidney Failure Based on Routine Laboratory Tests

Zacharias, Helena U.; Altenbuchinger, Michael; Schultheiß, Ulla T.; Raffler, Johannes; Kotsis, Fruzsina; Ghasemi, Sahar; Ali, Ibrahim; Kollerits, Barbara; Metzger, Marie; Steinbrenner, Inga; Sekula, Peggy; Massy, Ziad A.; Combe, Christian; Kalra, Philip A.; Kronenberg, Florian; Stengel, Bénédicte; Eckardt, Kai‐Uwe; Köttgen, Anna; Schmid, Matthias; Gronwald, Wolfram; Oefner, Peter J.

doi:10.1053/j.ajkd.2021.05.018

Cited by 37 publications

(34 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, Zacharias et al . [ 34 ] recently developed a predictive model based on six routine biomarkers and demonstrated its high predictive performance among a large cohort of patients with CKD. Among our cohort, we found that patients with suPAR ≥6 ng/mL at index admission (8.6% of patients) had a particularly high rate of eGFR decline, but risk stratification models are needed to determine the most appropriate suPAR cutoff values.…”

Section: Discussionmentioning

confidence: 99%

Soluble urokinase plasminogen activator receptor and decline in kidney function among patients without kidney disease

Iversen

Kallemose

Hornum

et al. 2022

Clinical Kidney Journal

View full text Add to dashboard Cite

Background Hospitalized patients are at elevated risk of developing kidney disease after discharge, often despite the absence of any clinical indicators during hospitalization. Soluble urokinase plasminogen activator receptor (suPAR) is a marker of systemic chronic inflammation that can be measured from routine blood samples. We determined whether elevated suPAR during hospitalization is associated with decline in estimated glomerular filtration rate (eGFR) after discharge. Methods This was a retrospective longitudinal cohort study of patients without detectable kidney disease presenting to the emergency department on two separate occasions during a 3-year period. Association between suPAR and decline in eGFR was assessed by linear mixed models for repeated measures adjusting for age, sex, C-reactive protein, sodium, diabetes, hypertension, and cardiovascular disease. Results In total, 5,124 patients (median age 65.9 years, 51.0% female) were included. Median suPAR was 2.9 ng/mL, median time to readmission was 144 days, and expected rate of eGFR decline over this period was 5.1 mL/min/1.73m2 per year. Adjusting for other risk factors, patients with suPAR <3, 3–6, or ≥6 ng/mL had an expected eGFR decline of 4.3, 5.2, or 9.0 mL/min/1.73m2 per year, respectively. Similarly, patients with suPAR in the lowest (<2.4 ng/mL), middle (2.4–3.6 ng/mL), or highest (≥3.6 ng/mL) tertile had an expected eGFR decline of 4.2, 4.6, or 6.5 mL/min/1.73m2 per year, respectively. In both cases, higher suPAR level was significantly and independently associated with higher rate of eGFR decline (P<0.001). Conclusions Higher suPAR level was associated with accelerated eGFR decline among patients presenting to the emergency department, suggesting that routine suPAR measurements may have utility for the early detection of kidney disease.

show abstract

Section: Discussionmentioning

confidence: 99%

Soluble urokinase plasminogen activator receptor and decline in kidney function among patients without kidney disease

Iversen

Kallemose

Hornum

et al. 2022

Clinical Kidney Journal

View full text Add to dashboard Cite

show abstract

“…In addition to the previously described variables, we also evaluated the utility of additional laboratory results from chemistry panels, liver enzymes, and complete blood cell count panels for inclusion in the random forest model based on associations found in previous studies of models predicting CKD progression. 11 , 12 , 13 The closest value within 1 year of the index date was selected (before or after) for inclusion. Distributional transformations were applied when needed.…”

Section: Methodsmentioning

confidence: 99%

Development and External Validation of a Machine Learning Model for Progression of CKD

Ferguson

Ravani

Sood

et al. 2022

Kidney International Reports

View full text Add to dashboard Cite

“…On the other end of the GFR spectrum, a novel prediction model including individuals with more preserved kidney function was developed in 4915 participants from the German Chronic Kidney Disease study, of whom 1063 (22%) had an eGFR at least 60 ml/min [5 ▪ ]. During an average follow-up duration of 3.7 years, 200 patients (4.1%) developed kidney failure requiring dialysis or transplantation.…”

Section: What Risk Prediction Models Are Available?mentioning

confidence: 99%

Contemporary risk prediction models in chronic kidney disease: when less is more

Canney

Sood

Hundemer

2022

Current Opinion in Nephrology &Amp; Hypertension

View full text Add to dashboard Cite

Purpose of reviewClinicians have an ever-increasing number of prediction tools at their disposal for estimating the risk of kidney failure in their patients. This review aims to summarize contemporary evidence for chronic kidney disease (CKD) risk prediction models across the spectrum of kidney function, and explore nuances in the interpretation of risk estimates.Recent findingsA European study using predominantly laboratory data has extended kidney failure prediction to patients with more preserved estimated glomerular filtration rate. For older patients with advanced CKD, prediction tools that censor for death (such as the Kidney Failure Risk Equation) overestimate the risk of kidney failure, especially over time horizons longer than 2 years. This problem can be addressed by accounting for the competing risk of death, as shown in well designed validation studies. The clinical utility of kidney failure risk prediction tools is being increasingly tested at a population level to inform policy and referral guidelines.SummaryThere is welcome trend to validate existing prediction tools in diverse clinical settings and identify their role in clinical practice. Clinicians should be cognizant of overestimating kidney failure risk in older patients with advanced CKD due to the competing risk of death. For moderate CKD and for short-term predictions, the Kidney Failure Risk Equation remains the most widely validated prediction tool.

show abstract

A Predictive Model for Progression of CKD to Kidney Failure Based on Routine Laboratory Tests

Cited by 37 publications

References 34 publications

Soluble urokinase plasminogen activator receptor and decline in kidney function among patients without kidney disease

Soluble urokinase plasminogen activator receptor and decline in kidney function among patients without kidney disease

Development and External Validation of a Machine Learning Model for Progression of CKD

Contemporary risk prediction models in chronic kidney disease: when less is more

Contact Info

Product

Resources

About