Abstract WP421: Optimization of Risk Stratification for Anticoagulation-Associated Intracerebral Hemorrhage
Bibliographic record
Abstract
Introduction: With more widespread anticoagulant use, anticoagulation-associated intracerebral hemorrhage (ICH) represents an increasing proportion of all ICH. We hypothesized that c ombining ischemic and hemorrhagic stroke risk estimation can guide treatment decisions, with more precision than ischemic risk estimation alone. Methods: We enrolled consecutive patients with anticoagulation-associated ICH in 15 centers in USA, Europe and Asia from 2015-2017. Each patient was assigned annual baseline ischemic stroke and hemorrhage risk based on their CHA 2 DS 2 -VASc and HAS-BLED scores without and with index ICH taken into account. We computed a net risk by subtracting the hemorrhagic from the ischemic risk. If the sum was positive the patient was assigned a “Favorable” indication for anticoagulation; if negative an “Unfavorable”. We compared clinical and neuroimaging characteristics between the two groups. Results: Our cohort comprised 357 patients (59% male, median age 76 [68-82] years). 69% used vitamin-K antagonists (VKA), 31 % Non vitamin K antagonist (NOAC). 191 (53.5%) of patients had a favorable indication for anticoagulation prior to their ICH event; the rest 166 (46.5%) had an unfavorable indication. Those with an unfavorable indication were younger (72[66-80] vs 78[73-84] years, p=0.001, had a lower CHA 2 DS 2 -VASc score (3[3-4] vs 5[4-6], p<0.001) and higher HAS-BLED score (3[2-4] vs 2[2-3], p=0.025). Those with favorable indication had a significantly higher prevalence of all major cardiovascular risk factors and were more likely to use NOAC (35% vs 25%, p=0.045). After including ICH into the HAS-BLED score estimation, 77 of the 191 patients with favorable profile were rendered unfavorable; leaving 114 patients (32% of the cohort) with favorable profile. Conclusions: In this anticoagulation-associated ICH cohort, baseline hemorrhage risk exceeded ischemic risk in ~50% of patients. This finding highlights the need for careful consideration of risk/benefit ratio prior to anticoagulation decisions. The remaining ~ 50% suffered an ICH although their baseline risk of ischemia exceeded that of hemorrhage which stresses the need for imaging, serum or other biomarkers to allow more precise estimation of hemorrhagic complication risk.
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 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".