Abstract WMP51: Outcome Prediction In Late-Window Endovascular Treatment - Application Of MR PREDICTS To Patients Treated Beyond 6 Hours
Bibliographic record
Abstract
Introduction: Outcome prediction tools for large vessel occlusion (LVO) stroke patients receiving endovascular treatment (EVT) focus on patients treated within 6h from onset. We aimed to apply a validated tool to EVT-treated patients in the late window (beyond 6h from onset) and to investigate any outcome differences according to the imaging paradigm used for selection. Methods: MR PREDICTS is a prediction tool of the effect and benefit of EVT on functional outcome based on MR CLEAN and HERMES data sets. We applied the algorithm to patients treated with late-window EVT from three multicenter international trials (ESCAPE, ESCAPE-NA1, and ProVe-IT). We assessed the model performance by calculating its discrimination and calibration for the overall patient sample and for the subset of patients who underwent CTP. Results: We included 152 patients: 93 (61.2%) from the control arm of ESCAPE-NA1, 35 (23.0%) from ProVe-IT, and 24 (15.8%) from ESCAPE. Median age was 68.0 years (IQR: 58.0 - 77.2), median baseline NIHSS was 16 (IQR: 12 - 20) and 72.4% had M1-occlusions. Median time from onset to groin puncture was 592min (IQR: 496 - 666). Good functional outcome (mRS 0-2) at 3 months was achieved in 72/152 patients (47.4%). The averaged predicted probability of mRS 0-2 was 47.6%. In the CTP-subgroup 44/94 patients (46.8%) achieved mRS 0-2, the averaged predicted probability of mRS 0-2 was 46.5%. Evaluation of model performance resulted in a reasonable discriminative ability (Harrel’s c-statistic: overall 0.75, 95%CI 0.67 - 0.82, CTP-subgroup: 0.73, 95%CI 0.62 - 0.82, figure 1). Conclusions: The outcome-prediction model performed reasonably well when applied to EVT patients in the late time window. Our data supports the use of available prediction tools in patients treated beyond 6h of symptom onset until specific models are developed for late-window patients.
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 | 0.004 | 0.008 |
| 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 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".