Abstract WP134: Door to Angiography in Large Vessel Occlusions Pre and Post Implementation of Automated Image Interpretation and Sharing Platform: A Single Center Study
Bibliographic record
Abstract
Background: Viz LVO is an FDA approved software that uses artificial intelligence to identify large vessel occlusions (LVOs) on computed tomography angiography (CTA) and facilitate communication between providers in a hub-and-spoke network. Whether this software expedites patient evaluation for treatment is unexplored. Methods: A single center retrospective registry was queried for patients with LVO of the internal carotid, proximal middle cerebral, or basilar artery in a stroke network (8 spokes, 1 hub). Eligible patients were in a 6-month period before (pre-Viz) and following implementation (post-Viz) of Viz LVO. Descriptive statistics and robust regression modeling were used to describe time from first contact to angiography (primary outcome) and other intervals between pre-Viz and post-Viz study groups. Results: Of 132 included patients (n=58 pre-Viz), small differences were found in demographics and non-significantly fewer patients underwent endovascular therapy (EVT) in the post-Viz period (73.0% vs. 86.2%, p=0.07). Time from spoke arrival to hub arrival among transferred patients was non-significantly shorter post-Viz (median 124 vs. 147 min, p=0.15). In patients who received EVT, there was a non-significant reduction in time from first contact to angiography (median 116 vs. 155 min, p=0.10) with shorter intervals for transferred patients (median 142 vs. 169 min, p=0.05) but not hub arrivals (p=0.81). For transferred patients, shorter intervals from initial contact to angiography were observed in adjusted robust regression, accounting for stroke severity, age, Alberta Stroke Program Early Computed Tomography Scale score, and use of perfusion imaging (β -32.4, 95% confidence interval -61.6 to -3.26, p=0.03). Conclusions: Implementation of the Viz LVO platform was associated with shorter intervals between initial hospital contact and neurointervention among transferred patients. Larger datasets are needed to validate these observations.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".