{"doi":"10.1101/2024.10.25.24316081","title":"Explainable machine-learning model to classify culprit calcified carotid plaque in embolic stroke of undetermined source","abstract":"Background: 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 (LRNC), perivascular adipose tissue (PVAT), and calcification morphology. Machine-learning (ML) approaches in plaque classification are increasingly popular but often limited in clinical interpretability by black-box nature. We apply an explainable ML approach, using noncalcified plaque components and calcification features with SHapley Additive exPlanations (SHAP) framework to classify calcified carotid plaques as culprit/non-culprit. Methods: In this retrospective cross-sectional study, patients with unilateral anterior circulation ESUS who underwent neck CT angiography and had calcific carotid plaque were analyzed. Calcification-level features were derived from manual segmentations. Plaque-level features were assessed by a neuroradiologist blinded to stroke-side and by semi-automated software. Calcifications/plaques were classified as culprit if ipsilateral to stroke-side. Eight baseline ML models were compared. Three CatBoost models were trained: Plaque-level, Calcification-level, and Combined. SHAP was incorporated to explain model decisions. Results: 70 patients yielded 116 calcific carotid plaques (60 ipsilateral to stroke; 270 calcifications (146 ipsilateral)). 17 plaque-level and 15 calcification-level features were extracted. Baseline CatBoost model outperformed other models. Combined model achieved test AUC 0.77 (95% CI: 0.59-0.92), accuracy 0.82 (95% CI: 0.71 - 0.91), mean cross-validation AUC 0.78. Plaque-level and calcification-level models performed lower (AUC 0.41 95% CI: 0.15-0.68, 0.60 95% CI 0.44-0.76). Combined model utilized five features: plaque thickness, IPH/LRNC volume ratio, PVAT volume, calcification minimum density, and total calcification volume over mean density ratio. Plaque thickness was most important feature based on SHAP values, with potential threshold at >2.6 mm. Conclusions: ML model trained with noncalcified plaque and calcification features can classify culprit calcific carotid plaque with greater accuracy than models trained using only plaque-level or calcification-level features. Model using clinically interpretable features with SHAP framework provides explanations for its decisions and allows identification of potential thresholds for high-risk features.","journal":"medRxiv","year":2024,"id":487458,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":3,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9567,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1332174,"name":"Jiehyun Kim","orcid":null,"position":1,"is_corresponding":false},{"id":861650,"name":"Huy Q. Phi","orcid":"0000-0003-3705-9850","position":2,"is_corresponding":false},{"id":1331754,"name":"Anming Hu","orcid":"0000-0001-9794-0549","position":3,"is_corresponding":false},{"id":1315729,"name":"Pargol Balali","orcid":"0000-0002-5895-577X","position":4,"is_corresponding":false},{"id":1011474,"name":"Konstanze Guggenberger","orcid":"0000-0002-4840-0447","position":5,"is_corresponding":false},{"id":519558,"name":"John Woo","orcid":"0000-0002-5405-8537","position":6,"is_corresponding":false},{"id":560478,"name":"Daniël Bos","orcid":"0000-0001-8979-2603","position":7,"is_corresponding":false},{"id":246788,"name":"Scott E. Kasner","orcid":"0000-0003-0418-6917","position":8,"is_corresponding":false},{"id":287568,"name":"Brett Cucchiara","orcid":"0000-0002-5218-9015","position":9,"is_corresponding":false},{"id":669432,"name":"Luca Saba","orcid":"0000-0003-2870-3771","position":10,"is_corresponding":false},{"id":1331755,"name":"Zhi Huang","orcid":"0009-0001-0092-7792","position":11,"is_corresponding":false},{"id":462913,"name":"Daniel Haehn","orcid":"0000-0001-9144-3461","position":12,"is_corresponding":false},{"id":266525,"name":"Jae W. Song","orcid":"0000-0002-3127-6427","position":13,"is_corresponding":false},{"id":1331753,"name":"Yu Sakai","orcid":"0009-0002-0217-1631","position":0,"is_corresponding":true}],"reference_count":50,"raw_metadata":null,"created_at":"2026-07-19T02:08:10.215754Z","pmid":"39574846","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}