January 5, 2022The American Journal of Emergency Medicine44 citationsOpen Access

Machine learning-based in-hospital mortality prediction models for patients with acute coronary syndrome

JKJun Ke YCYiwei Chen XWXiaoping Wang

Structured PICO

Can machine learning-based models predict the risk of in-hospital death in patients with acute coronary syndrome?

Population

Patients with acute coronary syndrome (ACS)

Intervention

Machine learning-based predictive models (logistic regression, GBDT, random forest, and SVM algorithms)

Outcome

In-hospital deathhard clinical

Machine learning algorithms can predict in-hospital mortality in ACS patients, highlighting the clinical importance of monitoring biomarkers like NT-proBNP, D-dimer, cTnI, and LDH alongside Killip class.

Abstract

The predictive model developed using logistic regression, GBDT, random forest, and SVM algorithms can be used to predict the risk of in-hospital death of ACS patients. Based on our findings, we recommend that clinicians focus on monitoring the changes of NT-proBNP, D-dimer, Killip, cTnI, and LDH as this may improve the clinical outcomes of ACS patients.

Ask AI

Helpful

Bookmark

View Full Paper