{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T15:03:41Z","timestamp":1779203021780,"version":"3.51.4"},"reference-count":41,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"vor","delay-in-days":21,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100000968","name":"American Heart Association","doi-asserted-by":"publisher","award":["938082"],"award-info":[{"award-number":["938082"]}],"id":[{"id":"10.13039\/100000968","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["NIH\/NINIB T\u201032 grant (EB004311)"],"award-info":[{"award-number":["NIH\/NINIB T\u201032 grant (EB004311)"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100003193","name":"Foundation of the American Society of Neuroradiology","doi-asserted-by":"publisher","award":["2024 Foundation of ASNR Trainee Research Grant"],"award-info":[{"award-number":["2024 Foundation of ASNR Trainee Research Grant"]}],"id":[{"id":"10.13039\/100003193","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Neuroimaging"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background and Purpose<\/jats:title>\n                    <jats:p>Embolic stroke of undetermined source (ESUS) may be associated with carotid artery plaques with &lt;50% stenosis. Plaque vulnerability is multifactorial, possibly related to intraplaque hemorrhage (IPH), lipid\u2010rich necrotic core, perivascular adipose tissue (PVAT), and calcifications. Machine learning (ML)\u2010based plaque classification is increasingly popular but often limited in clinical interpretability by black\u2010box 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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This was a retrospective, cross\u2010sectional study. Patients with unilateral anterior circulation ESUS with calcified carotid plaques in neck computed tomography (CT) angiography were analyzed. Calcification\u2010level features were derived from manual segmentations. Plaque\u2010level features were assessed by a neuroradiologist and by semi\u2010automated software. Plaques were classified as culprit if ipsilateral to stroke side. Eight classifiers were benchmarked, and a gradient\u2010boosted decision tree (CatBoost) was further tuned. SHAP explained model decisions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Seventy patients yielded 116 calcified plaques (270 calcifications). Model based on five plaque\u2010 and calcification\u2010level features achieved ROC\u2010AUC (receiver operating characteristic area under the curve) 0.79 and precision\u2010recall\u2010AUC 0.86, outperforming classification based on plaque thickness \u22653\u00a0mm (ROC\u2010AUC 0.59,\n                      <jats:italic>p<\/jats:italic>\n                      = 0.04) and IPH presence (ROC\u2010AUC 0.51,\n                      <jats:italic>p<\/jats:italic>\n                      = 0.003). SHAP identified plaque thickness and PVAT volume as the most influential features with potential thresholds of &gt;2.6\u00a0mm and \u2265112 mm\n                      <jats:sup>3<\/jats:sup>\n                      , respectively.f\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>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\u2010generating thresholds.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/jon.70119","type":"journal-article","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T13:29:48Z","timestamp":1769088588000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Explainable Machine\u2010Learning Model to Classify Culprit Calcified Carotid Plaque in Embolic Stroke of Undetermined Source"],"prefix":"10.1111","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0217-1631","authenticated-orcid":false,"given":"Yu","family":"Sakai","sequence":"first","affiliation":[{"name":"Department of Radiology University of Pennsylvania  Philadelphia Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiehyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science University of Massachusetts Boston  Boston Massachusetts USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3705-9850","authenticated-orcid":false,"given":"Huy Q.","family":"Phi","sequence":"additional","affiliation":[{"name":"Drexel University College of Medicine  Philadelphia Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew C.","family":"Hu","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine University of Pennsylvania  Philadelphia Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pargol","family":"Balali","sequence":"additional","affiliation":[{"name":"Department of Neurology University of Pennsylvania  Philadelphia Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstanze V.","family":"Guggenberger","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Wuerzburg  Wuerzburg Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John H.","family":"Woo","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pennsylvania  Philadelphia Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Bos","sequence":"additional","affiliation":[{"name":"Department of Epidemiology Erasmus MC University Medical Center  Rotterdam the Netherlands"},{"name":"Department of Radiology and Nuclear Medicine Erasmus MC University Medical Center  Rotterdam the Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott E.","family":"Kasner","sequence":"additional","affiliation":[{"name":"Department of Neurology University of Pennsylvania  Philadelphia Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brett L.","family":"Cucchiara","sequence":"additional","affiliation":[{"name":"Department of Neurology University of Pennsylvania  Philadelphia Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Saba","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Cagliari  Cagliari Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine University of Pennsylvania  Philadelphia Pennsylvania US"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Haehn","sequence":"additional","affiliation":[{"name":"Department of Computer Science University of Massachusetts Boston  Boston Massachusetts USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3127-6427","authenticated-orcid":false,"given":"Jae W.","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pennsylvania  Philadelphia Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,1,22]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(13)70310-7"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.116.016414"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvssci.2021.03.001"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2023.09.005"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A6613"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.122.028525"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A4765"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2022.02.026"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.21037\/qims-23-280"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13172760"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2020.09.005"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-82760-w"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCIMAGING.123.016274"},{"key":"e_1_2_8_15_1","first-page":"2266","article-title":"A Machine Learning Model for the Identification of High Risk Carotid Atherosclerotic Plaques","volume":"2021","author":"Kigka V. I.","year":"2021","journal-title":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/e23010018"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.39335.541782.AD"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020200029"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jstrokecerebrovasdis.2019.07.005"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.120.020143"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1161\/ATVBAHA.121.315969"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvs.2018.11.050"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics9040125"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2021.104484"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-020-00369-8"},{"key":"e_1_2_8_26_1","unstructured":"G.Ke Q.Meng T.Finley et\u00a0al. \u201cLightGBM: A Highly Efficient Gradient Boosting Decision Tree \u201d inProceedings of the 31st International Conference on Neural Information Processing Systems(Curran Associates Inc. 2017)."},{"key":"e_1_2_8_27_1","doi-asserted-by":"crossref","unstructured":"T.ChenandC.Guestrin \u201cXGBoost: A Scalable Tree Boosting System \u201d inProceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(Association for Computing Machinery 2016).","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1201\/9780429246593"},{"key":"e_1_2_8_29_1","unstructured":"S.Lundberg A Unified Approach to Interpreting Model Predictions. arXiv preprint arXiv:1705.07874(2017)."},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-022-01505-5"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.atherosclerosis.2022.11.013"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000002978"},{"issue":"10","key":"e_1_2_8_33_1","first-page":"1731","article-title":"Carotid Intraplaque\u2010Hemorrhage Volume and Its Association With Cerebrovascular Events","volume":"40","author":"Saba L.","year":"2019","journal-title":"American Journal of Neuroradiology"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.21037\/atm-20-1974"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1111\/bph.13705"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2021.765962"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2021.09.018"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(21)00252-0"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2013.282535"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2017.04.018"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01672-z"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241280126"}],"container-title":["Journal of Neuroimaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/jon.70119","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/jon.70119","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/jon.70119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T17:23:34Z","timestamp":1772990614000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/jon.70119"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1111\/jon.70119"],"URL":"https:\/\/doi.org\/10.1111\/jon.70119","archive":["Portico"],"relation":{},"ISSN":["1051-2284","1552-6569"],"issn-type":[{"value":"1051-2284","type":"print"},{"value":"1552-6569","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-10-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70119"}}