Prognostic Enrichment Using the Klinrisk Model: Insights from Landmark Kidney Disease Clinical Trials
Bibliographic record
Abstract
Background: Patients with macroalbuminuria (KDIGO stage A3) experience high rates of CKD progression and cardiovascular events. Identifying patients with lesser degrees of albuminuria who also experience high kidney and cardiovascular event rates could enhance access to, and improve efficiency of, CKD-focused clinical trials. Methods: We applied the Klinrisk model, a validated machine learning model incorporating routinely collected laboratory data, to patients with uACR ≥30 mg/g who were evaluated for participation in the CANVAS Program, CREDENCE, FIDELIO, FIGARO and DAPA-CKD trials but who failed screening due to albuminuria levels below the randomization threshold. We examined 2-year incidence of CKD progression (40% decline in eGFR or kidney failure) in different uACR categories, stratified by Klinrisk score (low, intermediate, and high risk indicating <2%, 2–10%, and >10% 2-year risk of CKD progression, respectively). We subsequently reviewed screen failure data from the CREDENCE, FIDELIO and DAPA-CKD trials to determine what proportion of individuals with uACR 30–300 mg/g could have been enrolled using a Klinrisk-informed approach. Results: Across the included trials, the incidence of CKD progression among participants with uACR 30–300mg/g (KDIGO stage A2) was highly variable across risk categories, ranging from 1.1 to 9.7% in those classified as low vs. high risk by the Klinrisk model, respectively. Compared to participants with uACR 300-1000 mg/g, event rates were similar or higher for participants with uACR 30-300mg/g classified as high-risk based on the Klinrisk model. 24 to 36% of participants who screen failed due to A2 albuminuria in the CREDENCE, FIDELIO and DAPA-CKD trials were classified as high risk with the Klinrisk model. Conclusion: Extending recruitment to patients with uACR 30-300mg/g at high-risk based on the Klinrisk algorithm could facilitate recruitment for CKD progression trials without affecting event rates. Prognostic enrichment using Klinrisk has the potential to accelerate drug development in CKD by enabling more inclusive and efficient clinical trials.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".