Skip to content
DraconiticResearch
Search Sources API
197,693 studies31 sourcesUpdated 38 min ago
Peer-reviewedCC BY-NC-ND 4.0JACC Asia

XGBoost Model With CMR Features for Prognostic Assessment in Patients With ST-Segment Elevation Myocardial Infarction

  • Yizhi Zhang1
  • Jiyuan Chen1
  • Zhiguo Zou1
  • Bihe Xu1
  • Chongwen Wu2
  • Lai Wei1
  • Jianxun Dong1
  • Xincheng Zhang1
  • Heng Ge1
  • Song Ding1,3
  • Jun Pu1
  1. 1Department of Cardiology, Shanghai Renji Hospital, School of Medicine, Shanghai Jiaotong University School of Medicine, Shanghai, China
  2. 2Department of Radiology, Shanghai Renji Hospital, School of Medicine, Shanghai Jiaotong University School of Medicine, Shanghai, China
  3. 3Department of Cardiology, Punan Branch of Renji Hospital, School of Medicine, Shanghai Jiaotong University School of Medicine, Shanghai, China
Read full textDOICite

Abstract

Background: Accurate prognostic models for ST-segment elevation myocardial infarction (STEMI) are essential to guide clinical practice.

Objectives: This study sought to construct predictive models integrating demographic, clinical, and cardiac magnetic resonance (CMR) imaging variables to forecast long-term major adverse cardiac and cerebrovascular events (MACCEs).

Methods: Patients with STEMI underwent CMR imaging within 1 week and 1 month after primary percutaneous coronary intervention. Twenty-four demographic, clinical, and CMR variables were used to construct 4 predictive models (naive Bayes, logistic regression, k-nearest neighbors, and XGBoost) for forecasting MACCEs during long-term follow-up. Model interpretability was assessed using Shapley values.

Results: A total of 483 patients were included (median age: 59.6 years, IQR: 54.0-65.0 years; median follow-up: 89.3 months; IQR: 60.3-115.4 months). During follow-up, 98 of 483 patients (20.3%) experienced MACCEs. The XGBoost model demonstrated superior predictive performance compared with the other approaches. Key CMR predictors included microvascular obstruction, left ventricular ejection fraction recovery, infarct size, intramyocardial hemorrhage, infarct core T1, and remote myocardium T1. Among clinical features, Killip class, body mass index, and age were most influential. Remote myocardium T1 was inversely correlated with left ventricular ejection fraction recovery at 1 month after percutaneous coronary intervention (R = −0.34; 95% CI: –0.43 to −0.27; P < 0.01).

Conclusions: An XGBoost model integrating clinical and CMR features effectively predicted long-term MACCEs in patients with STEMI. Microvascular obstruction emerged as the most important CMR-based prognostic factor.

Related

  1. Outcome Stratification in Non-ST-Segment Elevation Myocardial Infarction: Standardized Assessment of Left Ventricular Global Longitudinal Strain
    Yaoyuan Xiao, Xi Li, Qinghua Fu +2
    Reviews in cardiovascular medicinePeer-reviewedCC BYFull textCardiovascular medicineEurope PMC
  2. Prognostic Value of Serum Lipoprotein(a) Levels in Japanese Patients With ST-Segment Elevation Myocardial Infarction
    Keiko Nishiyama, Kensaku Nishihira, Michikazu Nakai +11
    Circulation JournalPeer-reviewedCC BY-NC-NDFull text2 citedSurgery & anaesthesiaJ-STAGE
  3. ST-Segment Elevation Myocardial Infarction Secondary to Aortic Root Thrombosis in a Patient With a Left Ventricular Assist Device
    Umama Gorsi, Julia Kumar, Nathan Kim +2
    CureusPeer-reviewedCC BYFull textGeneral medicineEurope PMC
  4. Anomalous left coronary artery origin unmasked by non-ST-elevation myocardial infarction
    Miłosz Dziarmaga, Krzysztof Sobczyk, Mateusz Dziarmaga +2
    Postepy w kardiologii interwencyjnej = Advances in interventional cardiologyPeer-reviewedCC BY-NC-SAFull textGeneral medicineEurope PMCPMC
  5. Simultaneous two-vessel occlusion causing ST-segment elevation myocardial infarction associated with elevated lipoprotein (a): A case report
    Shingo Watanabe, Junichi Onuma, Ryota Ishida +2
    Journal of Cardiology CasesPeer-reviewedLicence not statedFull textCardiovascular medicinePMC

Cite

BibTeXRIS
BibTeX
@article{zhang2026xgboost,
  title = {{XGBoost Model With CMR Features for Prognostic Assessment in Patients With ST-Segment Elevation Myocardial Infarction}},
  author = {Yizhi Zhang and Jiyuan Chen and Zhiguo Zou and Bihe Xu and Chongwen Wu and Lai Wei and Jianxun Dong and Xincheng Zhang and Heng Ge and Song Ding and Jun Pu},
  journal = {JACC Asia},
  year = {2026},
  month = jul,
  doi = {10.1016/j.jacasi.2026.05.019},
  url = {https://doi.org/10.1016/j.jacasi.2026.05.019},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - JOUR
TI  - XGBoost Model With CMR Features for Prognostic Assessment in Patients With ST-Segment Elevation Myocardial Infarction
AU  - Yizhi Zhang
AU  - Jiyuan Chen
AU  - Zhiguo Zou
AU  - Bihe Xu
AU  - Chongwen Wu
AU  - Lai Wei
AU  - Jianxun Dong
AU  - Xincheng Zhang
AU  - Heng Ge
AU  - Song Ding
AU  - Jun Pu
PY  - 2026
DA  - 2026/07/02
JO  - JACC Asia
DO  - 10.1016/j.jacasi.2026.05.019
UR  - https://doi.org/10.1016/j.jacasi.2026.05.019
AB  - Background: Accurate prognostic models for ST-segment elevation myocardial infarction (STEMI) are essential to guide clinical practice.  Objectives: This study sought to construct predictive models integrating demographic, clinical, and cardiac magnetic resonance (CMR) imaging variables to forecast long-term major adverse cardiac and cerebrovascular events (MACCEs).  Methods: Patients with STEMI underwent CMR imaging within 1 week and 1 month after primary percutaneous coronary intervention. Twenty-four demographic, clinical, and CMR variables were used to construct 4 predictive models (naive Bayes, logistic regression, k-nearest neighbors, and XGBoost) for forecasting MACCEs during long-term follow-up. Model interpretability was assessed using Shapley values.  Results: A total of 483 patients were included (median age: 59.6 years, IQR: 54.0-65.0 years; median follow-up: 89.3 months; IQR: 60.3-115.4 months). During follow-up, 98 of 483 patients (20.3%) experienced MACCEs. The XGBoost model demonstrated superior predictive performance compared with the other approaches. Key CMR predictors included microvascular obstruction, left ventricular ejection fraction recovery, infarct size, intramyocardial hemorrhage, infarct core T1, and remote myocardium T1. Among clinical features, Killip class, body mass index, and age were most influential. Remote myocardium T1 was inversely correlated with left ventricular ejection fraction recovery at 1 month after percutaneous coronary intervention (R = −0.34; 95% CI: –0.43 to −0.27; P < 0.01).  Conclusions: An XGBoost model integrating clinical and CMR features effectively predicted long-term MACCEs in patients with STEMI. Microvascular obstruction emerged as the most important CMR-based prognostic factor.
SN  - 2772-3747
ER  -