Diagnostic accuracy of decision-support software for the detection of intracranial large-vessel occlusion in CT angiography

Aims: To investigate the real-world clinical performance of the decision-support software “e-CTA” (e-Stroke Suite, Brainomix Limited, Oxford UK) for the detection of acute intracranial large-vessel occlusion (LVO) on CT angiography at a UK district general hospital.

Materials and Methods: The retrospective study included 300 consecutive CT angiograms of the head and neck performed between 8 March 2021 and 20 May 2021. e-CTA findings were compared with the radiologist report, and disagreements were reviewed by a sub-specialist vascular radiologist as the reference standard.

Results: The incidence of intracranial LVO was 7%. e-CTA correctly identified 18 of 21 intracranial proximal LVOs (86%), with 34 false positives. Sensitivity was 0.86, specificity 0.88, positive predictive value 0.35, and negative predictive value 0.99.

Conclusion: Sensitivity, specificity, and negative predictive values were similar to those reported in the literature; however, the positive predictive value for e-CTA was significantly lower, meaning over half of reported occlusions were false positives. Radiologists should weight software findings accordingly, and local validation testing may provide accuracy metrics more relevant to individual institutions.