Improving the Quality of CKD Care with Risk Prediction and Personalized Recommendations: 1-Year Results from the GEMINI-RAPA Study
Bibliographic record
Abstract
Background: CKD is associated with cardiovascular disease, progression to kidney failure and early mortality. Clinical guidelines recommend (ACEi, SGLT2i, non-steroidal MRA) to slow CKD progression and prevent heart failure in CKD-T2D patients Unfortunately, most patients are recognized late and use of guideline testing and therapies remain low. We implemented Klinrisk, a highly accurate risk prediction algorithm for CKD progression, with clinical decision support (CDS) to identify patients at risk with the goal of improving quality of CKD care in a large nephrology practice. Methods: Patients >18 years and not on dialysis were included. Data for estimated glomerular filtration rate, albuminuria, demographics, other laboratory tests and comorbid conditions was extracted from the electronic health record (EHR). Individuals were risk stratified using an externally validated risk prediction equation (Klinrisk1), deployed on Khure Health’s CDS platform Reports are generated quarterly to inform and educate physicians. One year data on changes in guideline directed care are presented here. Results: Of 16,099 patients that were risk-stratified, 29% were at high risk of CKD progression. Higher risk individuals were similar in age, but more likely to have diabetes, hypertension and heart failure. At one year, UACR testing increased 3 fold from 12.3 to 38.8 %, and UACR/PCR values were available in 83 % of individuals. Among high risk patients (> 10 % risk of progression over 2 years) there was a 19% increase in prescription of RAASi, 96 % increase in prescription of SGLT2i and an 65 % increase in prescription of ns-MRAs. Conclusion: Integration of a highly accurate machine model for CKD progression when paired with EHR linked clinical decision support improves guideline-recommended testing and therapy in high -risk patients with CKD. Longer follow up and periodic assessment is planned to observe changes in quality metrics and patient outcomes. Funding: Commercial Support - Bayer
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 | 0.013 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".