Multicenter Validation of Artificial Intelligence Predicting Anterior Circulation Large Vessel Occlusion Using...

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.

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.

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).

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.