A Comparative Study Between Artificial Neural Network and Support Vector Machine for Acute Coronary Syndrome Prognosis

Abstract

ABSTRACT. Despite medical advances, mortality due to acute coronary syndrome remains high. For this reason, it is important to identify the most critical factors for predicting the risk of death in patients hospitalized with this disease. To improve medical decisions, it is also helpful to construct models that enable us to represent how the main driving factors relate to patient outcomes. In this study, we compare the capability of Artificial Neural Network (ANN) and Support Vector Machine (SVM) models to distinguish between patients hospitalized with acute coronary syndrome who have low or high risk of death. Input variables are selected using the wrapper approach associated with a mutual information filter and two new proposed filters based on Euclidean distance. Because of missing data, the use of a filter is an important step in increasing the size of the usable data set and maximizing the performance of the classification models. The computational results indicate that the SVM model performs better. The most relevant input variables are age, any previous revascularization, and creatinine, regardless of the classification algorithms and filters used. However, the Euclidean filters also identify a second important group of input variables: age, creatinine and systemic arterial hypertension.

Diagnosis of coronary artery disease based on machine learning algorithms support vector machine, artificial neural network, and random forest

“…Findings in this study showed that the SVM algorithm performed better than other algorithms. [ 39 ] In a study, Akella examined six different data mining algorithms, including ANN and SVM algorithms for predicting CAD. The results showed that the ANN algorithm was better than other algorithms in all performance parameters, including accuracy, AUC, sensitivity, and F1-Score.…”

Input Variable Selection for Oil Palm Plantation Productivity Prediction Model

“…Hasil yang diperoleh adalah terpilihnya 6 dari 9 variabel dengan tingkat akurasi model prediksi menyamai model prediksi dengan 9 variabel input. Sementara pada [12] dilakukan modifikasi kriteria sensitivitas data berbasis jarak dengan menambahkan kriteria disagreement dimana perhitungan sensitivitas data hanya dilakukan pada data input yang memiliki output berbeda sehingga mengurangi kompleksitas komputasi. Metode seleksi variabel input yang digunakan mampu memilih 4 variabel signifikan dari kandidat 28 variabel input.…”