Predicting in a predicament: Stroke and hemorrhage risk prediction in dialysis patients with atrial fibrillation
Bibliographic record
Abstract
Whether to anticoagulate dialysis patients with atrial fibrillation is a common clinical dilemma with limited high-quality data to inform decision-making. While the efficacy and safety of anticoagulation for stroke prevention in dialysis patients with atrial fibrillation has long been debated and remains unclear, the more upstream issue of stroke risk assessment from atrial fibrillation has received relatively little attention. In the general population, a handful of risk scores to help predict stroke and hemorrhage risk in the setting of atrial fibrillation are widely validated and applied in clinical practice. But are they applicable to the dialysis population? The most commonly used stroke risk scores, CHADS2 and CHA2DS2-VASC, have limited validation in the dialysis population, and when validated, have shown poor performance (c-statistics <0.70). Stroke risk scores derived in the general atrial fibrillation population may perform poorly in dialysis patients for a number of reasons. Dialysis patients have unique stroke risk factors, such as chronic inflammation and vascular calcification, and a much higher competing risk of death, none of which are accounted for in current risk scores. Further complicating the dilemma of anticoagulation is hemorrhage risk, which is known to be exceedingly high in dialysis patients. Currently available hemorrhage risk scores, such as HAS-BLED, have not been validated in dialysis patients and will likely underestimate hemorrhage risk. Moving forward, risk tools specific to the dialysis population are needed to accurately assess and balance stroke and hemorrhage risks in dialysis patients with atrial fibrillation.
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 | 0.015 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".