Related Experiment Video
Updated: Jun 14, 2025
Assessment of Vascular Function in Patients With Chronic Kidney Disease
Published on: June 16, 2014
Generalized Propensity Score Methods to Assess CKD-Associated Physiologic Factors and Risk of Kidney Failure in the
Julia J Scialla1,2, Indika Mallawaarachchi2, Nicholas Illenberger3
1Division of Nephrology, Department of Medicine, University of Virginia School of Medicine.
Insights
Biochemical factors linked to chronic kidney disease (CKD) progression are confirmed as significant risk factors for kidney failure. Advanced machine learning methods, including generalized propensity score weighting, strengthen these findings in CKD patients.
Area of Science:
- Nephrology
- Biostatistics
- Epidemiology
Background:
- Biochemical factors are linked to chronic kidney disease (CKD) progression.
- Distinguishing risk factors from risk markers for CKD progression remains challenging.
- Existing methods may not fully account for confounding in assessing these factors.
Purpose of the Study:
- To employ advanced machine learning and generalized propensity score (GPS) weighting to better control confounding.
- To investigate the association between CKD-associated physiologic factors and kidney failure risk.
- To compare GPS weighting with traditional multivariable models.
Main Methods:
- Utilized data from 3,052 adults in the Chronic Renal Insufficiency Cohort Study.
- Incorporated a 2-year run-in period and 90 variables characterizing physiologic factors and confounders.
- Applied SuperLearner for GPS creation and GPS-weighted Cox regressions, compared with traditional Cox models.
Main Results:
- Bicarbonate, calcium, potassium, hemoglobin, and parathyroid hormone (PTH) were associated with kidney failure risk using GPS weighting.
- The GPS approach identified non-linear associations for several factors, some missed by traditional models.
- Associations between CKD-associated physiologic factors and kidney outcomes remained robust after GPS weighting.
Conclusions:
- Many CKD-associated physiologic factors are confirmed as strong risk factors for kidney failure.
- Generalized propensity score weighting offers a more robust method for controlling confounding in CKD research.
- Advanced statistical approaches can reveal complex, non-linear relationships between biomarkers and disease progression.
Abstract:
Epidemiologic studies have identified many biochemical risk factors for chronic kidney disease (CKD) progression that are correlates of kidney function, termed here 'CKD-associated physiologic factors'. Uncertainty remains if these factors are risk factors or risk markers accounting for aspects of kidney function not otherwise captured. We aimed to use flexible machine learning, a dynamic covariate history including kidney function informative markers, and generalized propensity score (GPS) weighting, to better control confounding for such exposures. We studied 3,052 adults with CKD in the Chronic Renal Insufficiency Cohort Study. We established a 2-year run-in period and assembled 90 variables that characterize variability and trends of selected CKD-associated physiologic factors and confounders. Using SuperLearner, we created a GPS for each CKD-associated physiologic factor and performed GPS-weighted Cox regressions. For context, we also evaluated results from traditional multivariable Cox proportional hazards models as in prior studies. Similar to traditional approaches, bicarbonate, calcium, potassium, hemoglobin, and PTH were each associated with risk of kidney failure using GPS weighting. The GPS approach detected non-linear associations in many factors, some of which were not detected with traditional models. We conclude that many associations between CKD-associated physiologic factors and kidney outcomes remain strong after GPS weighting.
Related Concept Videos
01:17Factors Affecting Renal Clearance: Renal Impairment
One condition associated with renal failure is uremia. Uremia is characterized by impaired glomerular filtration and fluid accumulation in the body. This condition hinders the renal clearance of drugs, resulting in drug accumulation and potential...
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
01:11Renal Failure: Dose Adjustments
Reduced renal clearance and elimination rate are common outcomes of renal impairment. These alterations lead to a prolonged elimination half-life and an altered apparent volume of distribution for drugs. As a result, dosage adjustments are typically necessary to maintain optimal drug levels in the body.
However, dosage adjustments...
01:07Determination of Renal Drug Clearance: Graphical and Midpoint Methods
The graphical method involves plotting the rate of drug excretion in urine against the plasma drug concentration. By analyzing the graph, the clearance can be calculated and obtained. Drugs rapidly excreted by the kidneys exhibit a...
01:24Kaplan-Meier Approach