EUVIMEDEUVIMED entdecken
Multizentrische Studie

An Interpretable Machine Learning Model Based on Metabolomics for Predicting Plaque Burden in Cryptogenic Stroke

Zi-Miao Liu, Yin-Yu Zi, Xiao-Yu Cheng, Ning-Yuan Liu, Zhong Ji, Yi-Hua He, Ling Li, Meng-Jia Yang, Chao Dang, Ming Yi, Ying-Xin He, Xin-Guang Yang und 9 weitere

The FASEB Journal · 2025

DOI: 10.1096/fj.202503352r ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift The FASEB Journal, 2025. Verfasst von Zi-Miao Liu und 20 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, P.R. China. Hauptthemen laut MEDLINE: Ischemic Stroke, Machine Learning, Metabolomics, Plaque, Atherosclerotic. Die Arbeit nennt 34 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province ().

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cryptogenic stroke represents 25%–40% of ischemic strokes, with many cases harboring unrecognized large artery atherosclerosis (LAA) requiring specific secondary prevention. In this multicenter pilot study, we developed a metabolomics‐based machine learning model to identify LAA and predict plaque burden in cryptogenic stroke patients. Plasma metabolites from 572 acute ischemic stroke patients across three hospitals were analyzed using untargeted metabolomics. A two‐stage machine learning approach was developed: Model 1 distinguished cardioembolic (CE) from non‐CE stroke, and Model 2 separated LAA from small vessel occlusion (SVO). Models were integrated to directly predict LAA among all subtypes. Model 1 achieved exceptional performance distinguishing CE from non‐CE (AUC = 0.998, accuracy = 97.9%), with pyruvate and glutamine as key discriminators. Model 2 differentiated LAA from SVO with AUC = 0.949, identifying pyroglutamate and 2‐hydroxybutyrate as primary markers. The combined model predicted LAA with AUC = 0.821. Critically, cryptogenic stroke patients predicted as LAA showed significantly higher plaque burden than those predicted as CE/SVO (23.9% vs. 10.9%, p = 0.014), with increased neovascularization and ulcerative features. This metabolomics‐based approach accurately identifies LAA in cryptogenic stroke patients and predicts atherosclerotic plaque burden, offering a novel diagnostic tool to guide personalized antithrombotic therapy selection. Trial Registration: Chinese Clinical Trial Registry registration number: ChiCTR1800015956

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Ischemic StrokeMachine LearningMetabolomicsPlaque, AtheroscleroticStrokeAgedFemaleHumansMaleMiddle AgedBiomarkersPilot ProjectsCase-Control Studies

Stichwörter der Autor:innen

acute ischemic strokemachine learningplasma metabolites

Substanzen

Biomarkers

Autor:innen und Institutionen

  • Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, P.R. China.
  • Department of Neurology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, P.R. China.
  • Department of Neurology, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, P.R. China.

ORCID-Profile: Zhen Deng

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Basic and Applied Basic Research Foundation of Guangdong Province ()

Zitieren

APA

Liu, Z. M., Zi, Y. Y., Cheng, X. Y., Liu, N. Y., Ji, Z., He, Y. H., Li, L., Yang, M. J., Dang, C., Yi, M., He, Y. X., Yang, X. G., Xu, Y. T., Lin, Z. Z., Zhu, J. J., Yin, J., Wu, Y. M., Zhou, L., Zeng, J. S., …, & Deng, Z. (2025). An Interpretable Machine Learning Model Based on Metabolomics for Predicting Plaque Burden in Cryptogenic Stroke. The FASEB Journal. https://doi.org/10.1096/fj.202503352r

Vancouver

Liu ZM, Zi YY, Cheng XY, Liu NY, Ji Z, He YH, et al. An Interpretable Machine Learning Model Based on Metabolomics for Predicting Plaque Burden in Cryptogenic Stroke. The FASEB Journal. 2025. doi:10.1096/fj.202503352r

BibTeX
@article{Liu2025,
  author = {Liu, Zi-Miao and Zi, Yin-Yu and Cheng, Xiao-Yu and Liu, Ning-Yuan and Ji, Zhong and He, Yi-Hua and Li, Ling and Yang, Meng-Jia and Dang, Chao and Yi, Ming and He, Ying-Xin and Yang, Xin-Guang and Xu, Yong-Teng and Lin, Zhen-Zhou and Zhu, Jia-Jia and Yin, Jia and Wu, Yong-Ming and Zhou, Liang and Zeng, Jin-Sheng and Pan, Su-Yue and Deng, Zhen},
  title = {An Interpretable Machine Learning Model Based on Metabolomics for Predicting Plaque Burden in Cryptogenic Stroke},
  journal = {The FASEB Journal},
  year = {2025},
  doi = {10.1096/fj.202503352r}
}
Kostenlos starten →