Evaluation of the biomarker-based ABC-AF-bleeding risk score and clinically based bleeding scores in 31,605 patients with atrial fibrillation treated with oral anticoagulation
Bibliographic record
Abstract
Abstract Background International guidelines recommend a systematic evaluation of bleeding risk in patients with atrial fibrillation (AF) to guide oral anticoagulation. However, it remains challenging to accurately predict bleeding risk. The biomarker-based ABC-AF-bleeding risk score to predict bleeding in anticoagulated patients with AF has shown promise. Purpose To evaluate the performance of the biomarker-based ABC-AF-bleeding risk score and compare its performance with other bleeding risk scores in 31,605 patients randomized to direct oral anticoagulant or warfarin using individual patient data from three randomized clinical trials. Methods The COMBINE AF biomarker data set contains individual patient data from three pivotal randomized trials (ARISTOTLE, ENGAGE AF-TIMI 48, and RE-LY) comparing apixaban, edoxaban or dabigatran with warfarin, in patients with AF at increased risk of stroke. The ABC-AF-bleeding biomarkers were analyzed in plasma samples collected at baseline (hemoglobin, troponin T high-sensitivity, and GDF-15) using Roche Diagnostics Elecsys assays. The biomarker-based ABC-AF-bleeding risk score (Age, Biomarkers, Clinical history of prior bleeding) was calculated as previously published. The discrimination was assessed by Harrell’s c index and compared with three clinically based bleeding risk scores; HASBLED, ORBIT, and DOAC. Results During a median follow-up time of 2.0 years, a total of 1,572 ISTH major bleeding events occurred (incidence rate per 100 person-years of 2.79) including 593 gastrointestinal (1.04) and 270 intracranial (0.47) bleeding events. The biomarker-based ABC-AF-bleeding score was well calibrated for major bleeding in the total material (Figure). The c indices for major bleeding were 0.68 (95% confidence interval 0.67-0.70), for gastrointestinal bleeding 0.70 (0.68-0.72), and for intracranial bleeding 0.66 (0.63-0.69). The biomarker-based ABC-AF-bleeding risk score provided superior discrimination compared with the clinically based risk scores in the full cohort (Table). The ABC-AF-bleeding risk score also provided superior discrimination for major bleeding in clinically relevant subgroups based on age, sex, body mass index, coronary artery disease, diabetes, heart failure, kidney function, and irrespective of DOAC or VKA use. Conclusions In patients with AF treated with different types of OAC the biomarker-based ABC-AF-bleeding score provide better discrimination of the risk för major bleeding than risk scores based only on clinical factors. The results were consistent for different types of bleeding and across multiple subgroups. There was good calibration when comparing predicted vs observed rate of major bleeding. These findings support the utility of the biomarker-based ABC-AF-bleeding risk score for advancing precision medicine in patients with AF.Calibration of ABC-AF-bleeding scoreTable
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".