Explainable Machine-Learning Model to Classify Culprit Calcified Carotid Plaque in Embolic Stroke of Undetermined Source.
Sakai Y, Kim J, Phi HQ, Hu AC, Balali P, Guggenberger KV, Woo JH, Bos D, Kasner SE, Cucchiara BL, Saba L, Huang Z, Haehn D, Song JW.
Sakai Y, et al.
J Neuroimaging. 2026 Jan-Feb;36(1):e70119. doi: 10.1111/jon.70119.
J Neuroimaging. 2026.
PMID: 41568918
Free PMC article.
SHAP identified plaque thickness and PVAT volume as the most influential features with potential thresholds of >2.6 mm and 112 mm(3), respectively.f CONCLUSIONS: ML model trained with noncalcified plaque and calcification features can classify culprit calcified carotid …
SHAP identified plaque thickness and PVAT volume as the most influential features with potential thresholds of >2.6 mm and 112 mm(3), re …