Related Experiment Video
Updated: Sep 26, 2025
Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
Machine learning to predict no reflow and in-hospital mortality in patients with ST-segment elevation myocardial
Lianxiang Deng1,2, Xianming Zhao3, Xiaolin Su4
1Department of Cardiology, The First Affiliated Hospital of Guangxi Medical University, 6 Shuangyong Road, Nanning, 530021, Guangxi, China.
Insights
Machine learning algorithms effectively predict no reflow and in-hospital death in ST-elevation myocardial infarction patients undergoing primary percutaneous coronary intervention. The random forest algorithm demonstrated optimal performance for both outcomes.
Area of Science:
- Cardiology
- Machine Learning
- Medical Informatics
Background:
- ST-elevation myocardial infarction (STEMI) patients undergoing primary percutaneous coronary intervention (pPCI) face risks of no reflow (NR) and in-hospital death.
- Predictive models are crucial for managing these high-risk patients.
- Machine learning algorithms (MLA) offer potential for accurate risk prediction.
Purpose of the Study:
- To implement machine learning algorithms (MLA) to develop an optimal model for predicting the no reflow (NR) phenomenon.
- To predict in-hospital death in ST-elevation myocardial infarction (STEMI) patients undergoing primary percutaneous coronary intervention (pPCI).
- To evaluate the performance of different MLA models in clinical decision-making.
Main Methods:
- Retrospective analysis of 854 STEMI patients who underwent pPCI.
- Data split into training (66.7%) and testing (33.3%) sets using random sampling.
- Multiple MLA models, including random forest (RAN), decision tree (CTREE), support vector machine (SVM), and neural network (NNET), were trained and evaluated over 10 repetitions.
- Receiver operator characteristic (ROC) curves and area under the curve (AUC) with 95% confidence intervals (CIs) were used for performance measurement.
Main Results:
- The random forest algorithm (RAN) showed optimal discrimination for NR, achieving an AUC of 0.7891 (95% CI: 0.7093-0.8688).
- For in-hospital mortality, RAN achieved the highest AUC of 0.9273 (95% CI: 0.8819-0.9728), outperforming SVM, NNET, and CTREE.
- Other models like SVM also showed strong performance, with AUCs of 0.7488 for NR and 0.8935 for mortality.
Conclusions:
- Machine learning algorithms, particularly the random forest model, demonstrate high performance in predicting no reflow and in-hospital mortality in STEMI patients post-pPCI.
- These MLA models can be valuable tools for clinical decision-making and risk stratification.
- Further implementation of MLA in clinical practice can improve patient outcomes.
Background:
The machine learning algorithm (MLA) was implemented to establish an optimal model to predict the no reflow (NR) process and in-hospital death that occurred in ST-elevation myocardial infarction (STEMI) patients who underwent primary percutaneous coronary intervention (pPCI).
Methods:
The data were obtained retrospectively from 854 STEMI patients who underwent pPCI. MLA was applied to predict the potential NR phenomenon and confirm the in-hospital mortality. A random sampling method was used to split the data into the training (66.7%) and testing (33.3%) sets. The final results were an average of 10 repeated procedures. The area under the curve (AUC) and the associated 95% confidence intervals (CIs) of the receiver operator characteristic were measured.
Results:
A random forest algorithm (RAN) had optimal discrimination for the NR phenomenon with an AUC of 0.7891 (95% CI: 0.7093-0.8688) compared with 0.6437 (95% CI: 0.5506-0.7368) for the decision tree (CTREE), 0.7488 (95% CI: 0.6613-0.8363) for the support vector machine (SVM), and 0.681 (95% CI: 0.5767-0.7854) for the neural network algorithm (NNET). The optimal RAN AUC for in-hospital mortality was 0.9273 (95% CI: 0.8819-0.9728), for SVM, 0.8935 (95% CI: 0.826-0.9611); NNET, 0.7756 (95% CI: 0.6559-0.8952); and CTREE, 0.7885 (95% CI: 0.6738-0.9033).
Conclusions:
The MLA had a relatively higher performance when evaluating the NR risk and in-hospital mortality in patients with STEMI who underwent pPCI and could be utilized in clinical decision making.
More Related Videos
18:11A Research Method For Detecting Transient Myocardial Ischemia In Patients With Suspected Acute Coronary Syndrome Using Continuous ST-segment Analysis
Published on: December 28, 2012
05:41Left Anterior Descending Coronary Artery Ligation for Ischemia-Reperfusion Research: Model Improvement via Technical Modifications and Quality Control
Published on: December 16, 2022
Related Concept Videos
01:30Acute Coronary Syndrome I: Introduction
01:28Acute Coronary Syndrome IV: Interprofessional Care