Abstract WP9: Improving Selection of Patients for Endovascular Treatment of Acute Ischemic Stroke:External Validation of a Clinical Decision Tool in Data from the Hermes Collaboration
Bibliographic record
Abstract
Background: Benefit of endovascular treatment (EVT) varies between individual patients with acute ischemic stroke. The MR PREDICTS decision tool, previously developed in the MR CLEAN trial, predicts outcome with and without EVT based on baseline patient characteristics and imaging characteristics (www.mrpredicts.com). We externally validated this model with data from recent EVT trials. Methods: Individual patient data was derived from the six other randomized controlled trials within the HERMES collaboration (ESCAPE, REVASCAT, SWIFT-PRIME, EXTEND-IA, THRACE and PISTE). Outcome of the ordinal logistic regression model was the modified Rankin Scale (mRS) at 90 days after stroke. Treatment benefit was defined as the difference between the predicted probability of achieving functional independence (mRS score 0-2) with and without EVT. Model performance was evaluated according to discrimination (measured with the c-statistic which ranges from 0.5 to 1) and calibration. Model coefficients were updated after calibration. Results: We included 1243 patients (633 assigned to EVT, 610 assigned to control). The c-statistic was 0.67 (95% confidence interval [CI] 0.65-0.69) for the ordinal mRS and 0.73 (95% CI 0.70-0.76) for functional independence, similar to previous performance. Outcomes were systematically better than predicted (calibration slope 0.89 and intercept 0.52). The observed probability of functional independence was higher than predicted for both treated patients (54% vs 40%) and controls (35% vs 26%), but the observed treatment benefit was similar (19% and 14%). Figure 1 shows a screenshot of the decision tool for use in clinical practice. Conclusion: Our model predicted outcome in a large representative trial population with discriminative value comparable to other well-known prediction tools. The decision tool can be used to support clinical decision making in ischemic stroke by selection of patients for EVT.
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 | 0.203 | 0.395 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
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".