Multicenter Validation of Artificial Intelligence Predicting Anterior Circulation Large Vessel Occlusion Using Noncontrast Head CT
Bibliographic record
Abstract
Background To validate an artificial intelligence software (JLK CTL) for predicting anterior circulation large vessel occlusion (LVO) using noncontrast computed tomography (NCCT) and to investigate its clinical implications regarding both infarct volume and outcomes. Methods Between January 2021 and April 2023, we retrospectively included consecutive patients who concurrently underwent computed tomography angiography and NCCT within 24‐hour of last known well from 6 stroke centers. Additionally, 274 subjects without stroke were included in this study to evaluate the specificity of the software. The performance to identify LVO was evaluated based on the area under the receiver operating characteristic curve, as well as its sensitivity and specificity. The association between predicted JLK CTL LVO scores and infarct volumes and functional outcomes was assessed using Pearson correlation and logistic regression analyses, respectively. Results Among 534 (mean age 69.9±13.2 years, 58.4% men) included patients, the median time from last known well to NCCT was 3.8 hours (interquartile range 1.7–9.5), with 30.7% (n = 164) presenting with LVO. The software demonstrated area under the receiver operating characteristic curve of 0.859 (95% CI, 0.827–0.887), with a sensitivity of 0.787 (95% CI, 0.716–0.847) and a specificity of 0.832 (95% CI, 0.790–0.869) at the predefined threshold. In subjects without ischemic stroke, the software achieved a specificity of 0.898 (95% CI, 0.887–0.922). The predicted JLK CTL LVO scores showed a correlation with infarct volumes on follow‐up diffusion‐weighted imaging (r = 0.54; P <0.001). After adjusting covariates, 1‐point increment of JLK CTL LVO score was associated with 2% increase of unfavorable 3‐month outcome ( P = 0.011). Conclusion In this multicenter study, we validated the performance of artificial intelligence software in predicting LVO on NCCT. Furthermore, the associations between JLK CTL LVO score and follow‐up infarct volume, as well as functional outcomes, support its clinical utility beyond merely screening patients who require rapid decision‐making.
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 | 0.010 | 0.022 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".