Comparison of Random Forest and Artificial Neural Network Models to Evaluate Diagnostic Factors in the Necessity to Perform Angiography

authors:

avatar Parastoo Golpour ORCID 1 , avatar Mohammad Tajfard ORCID 2 , 3 , avatar Majid Ghayour-Mobarhan ORCID 4 , 5 , avatar Mohsen Moohebati 6 , avatar Ali Taghipour ORCID 1 , avatar habibollah Esmaily ORCID 2 , avatar Sara Sabbaghian Tousi ORCID 1 , *

Department of Epidemiology and Biostatistics, School of Health, Mashhad University of Medical Sciences, Mashhad, IR Iran
Social Determinants of Health Research Center, Mashhad University of Medical Sciences, Mashhad, IR Iran
Department of Health Education and Health Promotion, Faculty of Health, Mashhad University of Medical Sciences, Mashhad, IR Iran
International UNESCO Center for Health-Related Basic Sciences and Human Nutrition, Mashhad University of Medical Sciences, Mashhad, IR Iran
Metabolic Syndrome Research Center, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, IR Iran
Cardiovascular Research Center, School of Medicine, Mashhad University of Medical Sciences, Mashhad, IR Iran
International Cardiovascular Research Journal: Vol.16, issue 2; e122437
published online: June 15, 2022
article type: Research Article
received: January 05, 2022
revised: May 02, 2022
accepted: May 29, 2022

how to cite: Golpour P, Tajfard M , Ghayour-Mobarhan M , Moohebati M , Taghipour A , et al. Comparison of Random Forest and Artificial Neural Network Models to Evaluate Diagnostic Factors in the Necessity to Perform Angiography. Int Cardiovasc Res J. 2022;16(2):e122437. 

Abstract

Background: Coronary Artery Disease (CAD) is the most common type of cardiovascular disorders. Despite being costly and invasive, coronary angiography is a reliable method for diagnosing CAD. Therefore, it is crucial to use non-invasive methods to screen candidates for angiography to accelerate the process of decision-making. Two powerful Machine Learning (ML) methods are Random Forest (RF) and Artificial Neural Network (ANN).  
Objectives: The present study aimed to compare RF and ANN to define the most important features for positive CAD results and predict the need for angiography as a screening method.
Methods: This cross-sectional study was performed on 1128 patients referred for angiography. The data were divided into test and train sets. The models (RF and ANN) were fitted with the angiographic outcome variable (positive or negative) as the dependent variable and five features as predictors. Then, the performances of the models were compared by considering the Area Under the Rock Curve (AUC). All statistical analyses were done using the R software, version 4.1.2.
Results: Out of the 1128 patients, 752 (66.7%) had positive angiography results. The AUC values were 0.75 and 0.52 for the test data set in ANN and RF models, respectively.
Conclusion: Fasting Blood Sugar (FBS), gender, age, Body Mass Index (BMI), and smoking habit were important in predicting the results of an angiography for CAD. Applying these factors in ML approaches can be considered a screen for angiography to accelerate the process of diagnosis. 
 

Fulltext

The full-text is available in pdf.

References

  • 1.

    The references are available in pdf.