EUVIMEDEUVIMED entdecken
Crossref

Prediction Models for Major Adverse Cardiovascular Events Following ST-Segment Elevation Myocardial Infarction and Subgroup-Specific Performance

Ravi Prakshbhai Patel, Vaidya Honeyben Chandrakant, Kapil Khanna

International Journal of Current Pharmaceutical Review and Research · 30.06.2026 · 18 (06)

DOI: 10.25258/ijcpr.18.6.63 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Current Pharmaceutical Review and Research, online erschienen am 30.06.2026. Verfasst von Ravi Prakshbhai Patel und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Despite primary percutaneous coronary intervention (PCI) and guideline-directed therapy, patients who survive ST-segment elevation myocardial infarction (STEMI) continue to be at risk of major adverse cardiovascular events (MACE). Personalized follow-up may be aided by prediction models, but there is limited reporting on model performance across subgroups.

Methods

A retrospective cohort of 680 adults with STEMI who underwent primary or rescue PCI was analysed. The primary outcome was 12-month major adverse cardiovascular events, defined as all-cause death, recurrent myocardial infarction, stroke, target-vessel revascularization or heart failure hospitalization. A total of 42 baseline clinical, angiographic, laboratory and treatment parameters were used to develop logistic regression, random forest and gradient boosting models. Model discrimination and calibration and subgroup performance were assessed.

Results

118 patients (17.4%) had 12-month MACE. MACE patients were older than non-MACE patients, had more diabetes, chronic kidney disease, anterior wall infarction, multivessel disease, higher Killip class and lower left ventricular ejection fraction. Gradient boosting had the highest discrimination (AUC 0.84; 95% CI 0.79-0.89), followed by random forest (AUC 0.82) and logistic regression (AUC 0.78). Gradient boosting had a sensitivity of 78.0%, and a specificity of 77.4%. The best performance was observed in non-diabetic patients (AUC 0.86) and the worst in chronic kidney disease (AUC 0.77). Killip class, LVEF, creatinine, diabetes, symptom-to-balloon time, multivessel disease, final TIMI flow and discharge statin/non-adherence risk were important predictors.

Conclusion

Gradient boosting model outperformed MACE prediction following STEMI and demonstrated clinically significant differences between subgroups. Prediction tools should be reported to be calibrated and perform well in subgroups before clinical use.

Zitieren

APA

Patel, R. P., Chandrakant, V. H., & Khanna, K. (2026). Prediction Models for Major Adverse Cardiovascular Events Following ST-Segment Elevation Myocardial Infarction and Subgroup-Specific Performance. International Journal of Current Pharmaceutical Review and Research, 18(06). https://doi.org/10.25258/ijcpr.18.6.63

Vancouver

Patel RP, Chandrakant VH, Khanna K. Prediction Models for Major Adverse Cardiovascular Events Following ST-Segment Elevation Myocardial Infarction and Subgroup-Specific Performance. International Journal of Current Pharmaceutical Review and Research. 2026;18(06). doi:10.25258/ijcpr.18.6.63

BibTeX
@article{Patel2026,
  author = {Patel, Ravi Prakshbhai and Chandrakant, Vaidya Honeyben and Khanna, Kapil},
  title = {Prediction Models for Major Adverse Cardiovascular Events Following ST-Segment Elevation Myocardial Infarction and Subgroup-Specific Performance},
  journal = {International Journal of Current Pharmaceutical Review and Research},
  year = {2026},
  volume = {18},
  number = {06},
  doi = {10.25258/ijcpr.18.6.63}
}
Kostenlos starten →