The FAST VAN for Field Identification of Large Vessel Occlusion in Acute Stroke
Bibliographic record
Abstract
BACKGROUND: There is definitive evidence for effectiveness of thrombectomy for acute stroke with large vessel occlusion (LVO). A clinical tool to identify patients with LVO is therefore required for effective triage and prehospital decision making. We developed the FAST VAN tool, which follows from the Heart and Stroke Foundation FAST stroke screen, with the addition of cortical features of vision, aphasia, and neglect, to differentiate from lacunar syndromes. METHODS: Consecutive acute stroke alerts initiated by emergency medical services (EMS) were prospectively analyzed from April 2017 to Jan 2021. FAST VAN signs were recorded by first responders who had received online education about the tool. These findings were compared to the presence or absence of LVO on CT angiography. Analysis was also performed by appropriateness for comprehensive stroke centers (CSC) transfer if no LVO was present. EMS providers were surveyed regarding ease of use in terms of learning the tool and using in real-world practice. RESULTS: Data from 1080 consecutive acute strokes included 440 patients considered to have VAN signs by EMS. Fifty-four percent of VAN-positive patients showed LVO on CTA. Sensitivity, specificity, and accuracy were 86%, 75%, and 77%, respectively. In 204 false-positive cases, 143 (70%) were considered appropriate for evaluation at the CSC. EMS providers reported high satisfaction with learning and using the tool. DISCUSSION: The FAST VAN tool for identification of LVO meets desired characteristics of an effective screening tool in ease of use, efficiency, and accuracy. Aphasia remains the most challenging cortical feature to identify accurately.
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 | 0.016 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 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".