Preprocedural determination of an occlusion pathomechanism in endovascular treatment of acute stroke: a machine learning-based decision.

Abstract

To evaluate whether an occlusion pathomechanism can be accurately determined by common preprocedural findings through a machine learning-based prediction model (ML-PM). A total of 476 patients with acute stroke who underwent endovascular treatment were retrospectively included to derive an ML-PM. For external validation, 152 patients from another tertiary stroke center were additionally included. An ML algorithm was trained to classify an occlusion pathomechanism into <i>embolic</i> or <i>intracranial atherosclerosis</i>. Various common preprocedural findings were entered into the model. Model performance was evaluated based on accuracy and area under the receiver operating characteristic curve (AUC). For practical utility, a decision flowchart was devised from an ML-PM with a few key preprocedural findings. Accuracy of the decision flowchart was validated internally and externally. An ML-PM could determine an occlusion pathomechanism with an accuracy of 96.9% (AUC=0.95). In the model, CT angiography-determined occlusion type, atrial fibrillation, hyperdense artery sign, and occlusion location were top-ranked contributors. With these four findings only, an ML-PM had an accuracy of 93.8% (AUC=0.92). With a decision flowchart, an occlusion pathomechanism could be determined with an accuracy of 91.2% for the study cohort and 94.7% for the external validation cohort. The decision flowchart was more accurate than single preprocedural findings for determining an occlusion pathomechanism. An ML-PM could accurately determine an occlusion pathomechanism with common preprocedural findings. A decision flowchart consisting of the four most influential findings was clinically applicable and superior to single common preprocedural findings for determining an occlusion pathomechanism.