The Kidney Failure Risk Equation as a Predictor of Healthcare Costs
Bibliographic record
Abstract
Background: The Kidney Failure Risk Equations (KFRE) are accurate and validated to predict the risk of kidney failure in individuals with CKD, but little is known about their potential to predict healthcare costs. We assessed the 4- and 8-variable 2-year KFRE models as independent predictors of monthly healthcare costs in patients with CKD stages 3-4. Methods: Optum's de-identified Integrated Claims-Clinical dataset of US patients (2007-2017) was queried to identify patients with non-dialysis CKD stages 3-4 (90-day average eGFR ≥15 to <60 mL/min/1.73 m2) followed by 2 consecutive serum bicarbonate 12 to <30 mEq/L, 28-365 days apart, with 6 months pre-index data and ≥2 years of post-index or death within 2 years, plus concurrent medical claims. The first qualifying serum bicarbonate test established the index date. KFRE elements were evaluated during the pre-index period and predicted risk scores of 2-year kidney failure were computed for each patient. Monthly medical costs were calculated for each patient from individual healthcare insurance claims and log-transformed due to skew. Patients were also stratified by index CKD stage. Generalized linear regression models were used to examine the association of KFRE score and costs. The individual components of the KFRE were similarly analyzed. Results: 1721 patients qualified for this observational study (1475 and 246 with CKD stage 3 and 4 at index, respectively). Both the 4- and 8-variable KFRE assessments were associated with log monthly medical costs. Per 1% increased risk for 2-year kidney failure risk predicted by KFRE, costs were increased significantly: for CKD stage 3 (parameter estimates: 0.065 [P=0.016] and 0.126 [P<0.0001]) and for CKD stage 4 (parameter estimates: 0.029 [P=0.001] and 0.040 [P<0.0001]). Of the individual components, lower serum albumin and lower serum bicarbonate were consistently associated with higher monthly medical costs. Conclusions: Both the 4- and 8-variable KFRE were associated with higher medical costs for patients with CKD stages 3 or 4, with monthly medical cost increases of 6.7% - 13.5% for CKD stage 3 and 2.9% - 4.1% for CKD stage 4, respectively, for each 1% increase in 2-year kidney failure risk. The KFRE may be a useful tool to anticipate medical costs for patients at risk of kidney failure. Funding: Commercial Support - Tricida, Inc.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.014 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".