Health System Economic Burden in Patients with CKD: Insights from the Klinrisk Model
Bibliographic record
Abstract
Background: CKD is associated with substantial economic burden. Early identification of at-risk CKD can facilitate appropriate and timely intervention and reduce CKD-related medical costs. This study assessed the association between CKD progression risk and healthcare burden. Methods: A retrospective observational study was conducted in 1,050,552 adult patients with CKD from Optum’s electronic health records database (1/1/2007 - 9/30/2022). A previously published and validated machine learning model, Klinrisk (Tangri N, et al Clin Kidney J. 2024 Mar 6;17(4)) was applied to classify patients into 3 groups based on their risk of CKD progression (low, medium, and high). All-cause inpatient (IP) admissions, emergency room (ER) visits, outpatient (OP) visits were evaluated in each risk group during the 1 year after CKD. Average medical costs (2023 USD) were calculated as the average length of stay for IP admissions, average number of ER and OP visits multiplied by the corresponding unit costs as estimated from a prior study. Results: Patients with higher predicted CKD progression risk had higher healthcare utilization (HRU). High-risk patients averaged 1.49 IP admissions, 0.83 ER visits, and 35.75 OP visits per year compared with 0.31 IP admissions, 0.63 ER visits, and 24.45 OP visits among low-risk patients. The total annual medical costs for low-, medium-, and high-risk patients were $16,018, $22,090, and $50,218, respectively (Figure). IP costs were the major cost driver for high-risk patients. Conclusion: Patients at high risk of CKD progression as predicted by Klinrisk were associated with high HRU and medical costs and may benefit from early intervention with guideline-directed therapies, to reduce economic burden.Annualized all-cause medical costs stratified by CKD progression risk
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 | 0.005 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".