EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY-NC-ND 4.0

3D Cardiac Magnetic Resonance Substrate Features-Based Machine Learning Model for Post-myocardial Infarction Risk Stratification: a Multicenter Study

Lujing Wang, Xiaoying Zhao, Yuhong Fan, Liang Peng, Yu Cui, Jiayan Peng, Guihua Li, Xingyu Li, Yixin Chen, Li Wang, Xiuxian Gong, Yanli Li und 5 weitere

Canadian Journal of Cardiology · 2026

DOI: 10.1016/j.cjca.2026.01.064 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Canadian Journal of Cardiology, 2026. Verfasst von Lujing Wang und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, The Second Affiliated Hospital of Kunming Medical University, Kunming, China. Hauptthemen laut MEDLINE: Myocardial Infarction, Machine Learning, Magnetic Resonance Imaging, Cine, Imaging, Three-Dimensional. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Accurate risk stratification postmyocardial infarction (MI) remains challenging. In this study we aimed to develop interpretable machine-learning (ML) models integrating 3-dimensional (3D) cardiac magnetic resonance (CMR) substrate features to predict major adverse cardiovascular events (MACEs) after MI. METHODS: This retrospective study included MI patients who underwent CMR between May 2015 and October 2024. The primary endpoint was MACE. External validation used multicenter datasets. 3D features (core scar, border zone, abnormal corridors) were extracted via ADAS 3D. Feature selection involved univariate logistic regression and the Boruta algorithm. Eight ML models were trained; the top performer, the tabular prior-data-fitted network (TabPFN), was used to build multimodal models. Shapely Additive Explantations (SHAP) analysis provided interpretability. RESULTS: Two hundred ninety-two MI patients were finally enrolled. During 35-month median follow-up, 91 experienced MACEs. Nine key predictors were identified: 3 clinical (high-density lipoprotein, chronic kidney disease, tricuspid regurgitation), 2 functional (left ventricular ejection fraction, left ventricular circumferential strain), and 4 3D substrate features (border zone mass, corridor mass, burden, length). Model 4 (clinical + 3D features) showed strong performance across training (area under the curve [AUC] = 0.91), internal (AUC = 0.82), and external (AUC = 0.89) sets. Model 3 (only 3D features) had an external AUC = 0.90, surpassing clinical (AUC = 0.63) and functional (AUC = 0.49) models. Decision curve analysis highlighted the clinical benefit of incorporating 3D features. SHAP analysis identified corridor mass and burden as key predictors. CONCLUSIONS: ML models using 3D CMR substrate features significantly improve post-MI MACE prediction compared with traditional methods, offering interpretable and personalized risk stratification tools.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Myocardial InfarctionMachine LearningMagnetic Resonance Imaging, CineImaging, Three-DimensionalHumansRetrospective StudiesRisk AssessmentFemaleMaleMiddle AgedPredictive Learning ModelsAged

Stichwörter der Autor:innen

3D substrate featurescardiac magnetic resonancemachine learningmyocardial infarctionrisk stratification

Autor:innen und Institutionen

  • Department of Radiology, The Second Affiliated Hospital of Kunming Medical University, Kunming, China.
  • Department of Ultrasound Diagnosis, Daping Hospital, Army Medical University, Chongqing, China.
  • Department of Statistics and Actuarial Science, School of Computing and Data Science, University of Hong Kong, Hong Kong.
  • Department of Radiology, The Sixth Affiliated Hospital of Kunming Medical University, Yuxi, China.
  • Department of Radiology, Yan'an Hospital of Kunming City, Kunming, China.
  • Department of Radiology, Hospital of Honghe State Affiliated with Kunming Medical University, Kunming, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, L., Zhao, X., Fan, Y., Peng, L., Cui, Y., Peng, J., Li, G., Li, X., Chen, Y., Wang, L., Gong, X., Li, Y., Wu, J., Wang, J., Yu, L., Ma, J., & Zhao, X. (2026). 3D Cardiac Magnetic Resonance Substrate Features-Based Machine Learning Model for Post-myocardial Infarction Risk Stratification: a Multicenter Study. Canadian Journal of Cardiology. https://doi.org/10.1016/j.cjca.2026.01.064

Vancouver

Wang L, Zhao X, Fan Y, Peng L, Cui Y, Peng J, et al. 3D Cardiac Magnetic Resonance Substrate Features-Based Machine Learning Model for Post-myocardial Infarction Risk Stratification: a Multicenter Study. Canadian Journal of Cardiology. 2026. doi:10.1016/j.cjca.2026.01.064

BibTeX
@article{Wang2026,
  author = {Wang, Lujing and Zhao, Xiaoying and Fan, Yuhong and Peng, Liang and Cui, Yu and Peng, Jiayan and Li, Guihua and Li, Xingyu and Chen, Yixin and Wang, Li and Gong, Xiuxian and Li, Yanli and Wu, Jingjing and Wang, Jin and Yu, Lequan and Ma, Jian and Zhao, Xinxiang},
  title = {3D Cardiac Magnetic Resonance Substrate Features-Based Machine Learning Model for Post-myocardial Infarction Risk Stratification: a Multicenter Study},
  journal = {Canadian Journal of Cardiology},
  year = {2026},
  doi = {10.1016/j.cjca.2026.01.064}
}
Kostenlos starten →