Related Experiment Video
Updated: Jul 26, 2026
Establishment of an In vitro System to Study Intracellular Behavior of Candida glabrata in Human THP-1 Macrophages
Published on: December 10, 2013
Development and validation of a predictive models for predicting the cardiac events within one year for patients
Kok Yew Ngew1, Hao Zhe Tay1, Ahmad K M Yusof2,3
1Novartis Corporation (Malaysia) Sdn Bhd, Petaling Jaya, Malaysia.
Insights
Predicting cardiac events after percutaneous coronary intervention (PCI) is crucial. This study developed machine learning models, with logistic regression best for mortality and support vector machines for revascularization, aiding clinical management.
Area of Science:
- Cardiovascular Medicine
- Medical Informatics
- Machine Learning
Background:
- Percutaneous coronary intervention (PCI) is a standard treatment for coronary artery disease.
- Predicting post-PCI complications and readmissions can enhance patient management.
- Developing accurate risk prediction models is essential for improving clinical outcomes.
Purpose of the Study:
- To develop and validate predictive models for cardiac events within one year after PCI.
- To compare the performance of different machine learning models for risk prediction.
Main Methods:
- Retrospective cohort study using the National Cardiovascular Disease (NCVD)-PCI registry (N=28,007).
- Data split into training (n=24,409) and testing (n=3,598) sets.
- Developed and validated four models: logistic regression (LR), random forest, support vector machine (SVM), and artificial neural network.
Main Results:
- Logistic regression (LR) showed the best performance in predicting 1-year mortality post-PCI (AUC: 0.820).
- Support vector machine (SVM) demonstrated the highest discrimination for target vessel revascularization (TVR) and composite mortality/TVR events (AUC: 0.720).
- Patient demographics and clinical features were consistent between training and testing cohorts.
Conclusions:
- Optimal prediction models with good discriminatory ability were identified for mortality and TVR outcomes.
- A simple machine learning framework proved effective for risk prediction post-PCI.
Purpose:
Percutaneous coronary intervention (PCI) is a common treatment modality for coronary artery disease. Accurate prediction of patients at risk for complications and hospital readmission after PCI could improve the overall clinical management. We aimed to develop and validate predictive models to predict any cardiac event within a year post PCI procedure.
Methods:
This is a retrospective cohort study utilizing data from the National Cardiovascular Disease (NCVD)-PCI registry. The data collected (N = 28,007) were split into training set (n = 24,409) and testing set (n = 3598). Four predictive models (logistic regression [LR], random forest method, support vector machine [SVM], and artificial neural network) were developed and validated. The outcome on risk prediction were compared.
Results:
The demographic and clinical features of patients in the training and testing cohorts were similar. Patients had mean age ± standard deviation of 58.15 ± 10.13 years at admission with a male majority (82.66%). In over half of the procedures (50.61%), patients had chronic stable angina. Within 1 year of follow up mortality, target vessel revascularization (TVR), and composite event of mortality and TVR were 3.92%, 9.48%, and 12.98% respectively. LR was the best model in predicting mortality event within 1-year post-PCI (AUC: 0.820). SVM had the highest discrimination power for both TVR event (AUC: 0.720) and composite event of mortality and TVR (AUC: 0.720).
Conclusions:
This study successfully identified optimal prediction models with the good discriminatory ability for mortality outcome and good discrimination ability for TVR and composite event of mortality and TVR with a simple machine learning framework.
