|
KMID : 1100520230290020120
|
|
Healthcare Informatics Research
2023 Volume.29 No. 2 p.120 ~ p.131
|
|
|
Data Modeling Using Vital Sign Dynamics for In-hospital Mortality Classification in Patients with Acute Coronary Syndrome
|
|
Sarawuth Limprasert
Ajchara Phu-ang
|
|
|
Abstract
|
|
|
Objectives: This study compared feature selection by machine learning or expert recommendation in the performance ofclassification models for in-hospital mortality among patients with acute coronary syndrome (ACS) who underwent percutaneouscoronary intervention (PCI).
Methods: A dataset of 1,123 patients with ACS who underwent PCI was analyzed. Afterassigning 80% of instances to the training set through random splitting, we performed feature scaling and resampling withthe synthetic minority over-sampling technique and Tomek link method. We compared two feature selection methods: recursivefeature elimination with cross-validation (RFECV) and selection by interventional cardiologists. We used five simplemodels: support vector machine (SVM), random forest, decision tree, logistic regression, and artificial neural network. Theperformance metrics were accuracy, recall, and the false-negative rate, measured with 10-fold cross-validation in the trainingset and validated in the test set.
Results: Patients’ mean age was 66.22 ± 12.88 years, and 33.63% had ST-elevation ACS. Fifteenof 34 features were selected as important with the RFECV method, while the experts chose 11 features. All models withfeature selection by RFECV had higher accuracy than the models with expert-chosen features. In the training set, the randomforest model had the highest accuracy (0.96 ± 0.01) and recall (0.97 ± 0.02). After validation in the test set, the SVM modeldisplayed the highest accuracy (0.81) and a recall of 0.61.
Conclusions: Models with feature selection by RFECV had higheraccuracy than those with feature selection by experts in identifying patients with ACS at high risk for in-hospital mortality.
|
|
|
KEYWORD
|
|
|
Acute Coronary Syndrome, Machine Learning, Mortality, Vital Sign, Data Mining
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|