Abstract WP97: Derivation and Validation of the Get with the Guidelines®-Stroke Endovascular Thrombectomy Risk Scores
Bibliographic record
Abstract
Introduction: Prior attempts to assess risk of symptomatic intracranial hemorrhage (sICH) after endovascular thrombectomy have been limited by reliance on information obtained after thrombectomy (such as TICI reperfusion) and lack of generalizability to routine clinical practice. Methods: Patients presenting to GWTG-Stroke participating hospitals between July 2021 and June 2023 with last known well within six hours prior to presentation, who received endovascular thrombectomy were included. The primary outcome was sICH; secondary outcomes included in-hospital mortality, mRS at discharge, and length of stay. The study population was divided into a derivation and validation cohort with 70:30 partition. According to a pre-specified statistical analysis plan, a full model of 31 candidate variables and subsequently a highly parsimonious model including only variables measured before EVT deployment was fit for each endpoint, with variable retention guided by multiple factor analysis (MFA). Models were then externally validated in the HERMES clinical trial population. Results: 31,668 patients (median age 71 [Q1: 61, Q3: 81]) were included, of whom 1,799 (5.7%) developed sICH. In the validation cohort, the area under the receiver operating characteristics curve (AUC) for the full model was 0.649 (Table 1), and the AUC for the simplified points score was 0.589 (Table 2). At the conference, we will present results of external validation and secondary endpoints, details of model calibration, and direct comparisons to existing risk scores. Conclusions: A risk score for sICH after thrombectomy for acute stroke devised using routinely collected data known prior to intervention had good performance compared to existing approaches.
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 | 0.030 | 0.087 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".