Predicting All-Cause Mortality in Patients with Advanced CKD
Bibliographic record
Abstract
Background: Patients with advanced CKD are at high risk of mortality, kidney failure and cardiovascular events. Accurately identifying patients that are at a higher risk for mortality may aid in clinical decision making and preventing unnecessary dialysis therapies that may cause more harm. We developed and externally validated a risk prediction tool using commonly collected clinical measurements to predict all-cause mortality among patients with advanced CKD. Methods: We developed a prediction model using demographic, clinical and laboratory data in adult patients (≥ 18 years) with advanced CKD (eGFR <30 mL/min/1.73m2) from Manitoba, Canada, between January 2012, and September 2020, with external validation from Ontario, Canada. Our primary outcome was time to all-cause mortality. If dialysis was initiated in follow-up, we ascertained all-cause mortality within 1 year of dialysis initiation. We assessed model discrimination using the area under the receiver operating characteristic curve (AUC) and calibration using plots of observed and predicted risks. Results: The development cohort included 397 patients (mean age 65.4 ± 13.9) with 121 events. The final model included age, sex, estimated GFR, hemoglobin, serum albumin and congestive heart failure and achieved a 2-year and 5-year AUC of 74.3 (CI: 68.4 - 80.1) and 80.2 (CI: 75.3 - 85.1), respectfully. Discrimination and calibration were adequate in the external validation data set with 2-year and 5-year AUC scores of 71.4 (CI: 70.8 - 72.0) and 73.0 (CI: 72.5 - 73.5). Conclusions: We developed a simple prediction model that included commonly measured variables that can accurately predict all-cause mortality in patients with advanced CKD. This equation may aid as a support tool for nephrologists in dialysis decision making, especially in patients who are at high risk of mortality.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 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 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".