Abstract WMP16: Eloquence-Weighted Imaging Improves Clinical Outcomes Prediction in Endovascular Stroke Therapy
Bibliographic record
Abstract
Background: Larger infarct size at presentation as determined by ASPECTS is associated with reduced likelihood of good outcome in acute ischemic stroke. However, infarct volume alone explains only a modest fraction (∼30%) of the variation in stroke outcome. Incorporating the relative eloquence of each ASPECTS region may improve the predictive power. Methods: In the combined database of the SWIFT and STAR trials, we identified patients treated with the Solitaire stent retriever. Using the 24hr CT scan, a multivariate linear regression was used to determine the relative contribution of each ASPECTS region, separately in each hemisphere, to freedom from disability (mRS 0-2) at 90 days. The coefficients from the regression were used to create an Eloquence-weighted ASPECTS score (EL-ASPECTS), which was compared against the original in predicting outcome based on the presentation CT scan. Results: Among 254 patients treated with ET, average age was 68, 64% were female, and NIHSS was mean 16 (SD +/- 5). Mean ASPECTS at presentation was 8.2 and 6.4 at 24 hrs. The most commonly involved ASPECTS regions were the lentiform nuclei (70%), insula (55%), and caudate (52%). In multivariate analysis, for the right hemisphere on 24hr CT, preservation of M1 (OR 1.6) and M4 (OR 1.2) regions were most strongly predictive of good outcome. For the left hemisphere on 24 hr CT, preservation of M3 (OR 2.6), and M5 (OR 2.5) and involvement of M2 (OR -1.9) were most predictive. Eloquence weights were assigned to all 20 R/L ASPECTS regions to create EL-ASPECTS. EL-ASPECTS, compared with original ASPECTS, demonstrated improved discrimination for independent functional outcome for right hemisphere (C-statistic 0.78 vs. 0.69), left hemisphere (0.78 vs. 0.72), and all stroke patients (0.76 vs. 0.70). On presentation CTs, multivariate analyses including age and presentation NIHSS demonstrated EL-ASPECTS but not original ASPECTS was predictive of good clinical outcome (OR 1.65, p<.01). Higher C-statistic values were seen with EL-ASPECTS in analysis of presentation CT scans. Conclusions: Incorporation of regional weighting into ASPECTS improves the ability to predict who will achieve independent functional outcomes with endovascular therapy in acute ischemic stroke.
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 | 0.002 | 0.005 |
| 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 | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".