Ability of Radiomics Versus Humans in Predicting First-Pass Effect After Endovascular Treatment in the ESCAPE-NA1 Trial

• Authors: BALA Fouzi; QIU Wu; ZHU Kairan; KAPPELHOF Manon; CIMFLOVÁ Petra; KIM Beom Joon; MCDONOUGH Rosalie; SINGH Nishita; KASHANI Nima; ZHANG Jianhai; NAJM Mohamed; OSPEL Johanna M; WADHWA Ankur; NOGUEIRA Raul G; MCTAGGART Ryan A; DEMCHUK Andrew M; POPPE Alexandre Y; ZERNA Charlotte; JOSHI Manish; ALMEKHLAFI Mohammed A; GOYAL Mayank; HILL Michael D; MENON Bijoy K
• Year of publication: 2023
• Type: Article in Periodical
• Magazine / Source: Stroke: Vascular and Interventional Neurology
• MU Faculty or unit: Faculty of Medicine
• Web: https://www.ahajournals.org/doi/10.1161/SVIN.122.000525
• Doi: http://dx.doi.org/10.1161/SVIN.122.000525
• Keywords: deep learning; endovascular therapy; ischemia; machine learning; stroke; thrombus
• Description: BACKGROUND: First-pass effect (FPE), that is, achieving reperfusion with a single thrombectomy device pass, is associated with better clinical outcomes in patients with acute stroke. FPE is therefore increasingly used as a marker of device and procedural efficacy. We aimed to evaluate the ability of thrombus-based radiomics models to predict FPE in patients undergoing endovascular thrombectomy and compare performance with experts and nonradiomics thrombus characteristics.