Journal article
Explainable Machine-Learning Model to Classify Culprit Calcified Carotid Plaque in Embolic Stroke of Undetermined Source
Journal of neuroimaging, v 36(1), 70119
01 Jan 2026
PMID: 41568918
Abstract
Background and Purpose: Embolic stroke of undetermined source (ESUS) may be associated with carotid artery plaques with <50% stenosis. Plaque vulnerability is multifactorial, possibly related to intraplaque hemorrhage (IPH), lipid-rich necrotic core, perivascular adipose tissue (PVAT), and calcifications. Machine learning (ML)-based plaque classification is increasingly popular but often limited in clinical interpretability by black-box nature. We applied an explainable ML approach, using noncalcified plaque components and calcification features with the SHapley Additive exPlanations (SHAP) framework to classify plaques as culprit or nonculprit. Methods: This was a retrospective, cross-sectional study. Patients with unilateral anterior circulation ESUS with calcified carotid plaques in neck computed tomography (CT) angiography were analyzed. Calcification-level features were derived from manual segmentations. Plaque-level features were assessed by a neuroradiologist and by semi-automated software. Plaques were classified as culprit if ipsilateral to stroke side. Eight classifiers were benchmarked, and a gradient-boosted decision tree (CatBoost) was further tuned. SHAP explained model decisions. Results: Seventy patients yielded 116 calcified plaques (270 calcifications). Model based on five plaque- and calcification-level features achieved ROC-AUC (receiver operating characteristic area under the curve) 0.79 and precision-recall-AUC 0.86, outperforming classification based on plaque thickness >= 3 mm (ROC-AUC 0.59, p = 0.04) and IPH presence (ROC-AUC 0.51, p = 0.003). 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 plaque better than conventional criteria. Using clinically interpretable features with SHAP, the model explained its decisions and suggested hypothesis-generating thresholds.
Metrics
Details
- Title
- Explainable Machine-Learning Model to Classify Culprit Calcified Carotid Plaque in Embolic Stroke of Undetermined Source
- Creators
- Yu Sakai (Corresponding Author) - University of PennsylvaniaJiehyun Kim - University of Massachusetts BostonHuy Q. Phi - Drexel UniversityAndrew C. Hu - University of PennsylvaniaPargol Balali - University of PennsylvaniaKonstanze V. Guggenberger - University of WürzburgJohn H. Woo - University of PennsylvaniaDaniel Bos - Erasmus MCScott E. Kasner - University of PennsylvaniaBrett L. Cucchiara - University of PennsylvaniaLuca Saba - University of CagliariZhi Huang - University of PennsylvaniaDaniel Haehn - University of Massachusetts BostonJae W. Song - University of Pennsylvania
- Publication Details
- Journal of neuroimaging, v 36(1), 70119
- Publisher
- Wiley
- Number of pages
- 13
- Grant note
- 938082 / American Heart Association 2024 Foundation of ASNR Trainee Research Grant / Foundation of the American Society of Neuroradiology NIH/NINIB T-32 grant (EB004311) / National Institute of Biomedical Imaging and Bioengineering; United States Department of Health & Human Services; National Institutes of Health (NIH) - USA; NIH National Institute of Biomedical Imaging & Bioengineering (NIBIB) 938082 / American Heart Association (AHA); American Heart Association
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- College of Medicine
- Web of Science ID
- WOS:001701701700003
- Scopus ID
- 2-s2.0-105028227098
- Other Identifier
- 991022200097504721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
Source: SDGs in the Output