<?xml version="1.0" encoding="utf-8"?>
<Articles JournalTitle="International Cardiovascular Research Journal">
    <Article>
        <Journal>
            <PublisherName>Shiraz University of Medical Sciences</PublisherName>
            <JournalTitle>Int Cardio Res J</JournalTitle>
            <Issn>2251-9149</Issn>
            <Volume>16</Volume>
            <Issue>2</Issue>
            <PubDate PubStatus="epublish">
                <Year>2022</Year>
                <Month>Jun</Month>
                <Day>15</Day>
            </PubDate>
            <journal_id_doi/>
        </Journal>
        <title locale="en_US">Comparison of Random Forest and Artificial Neural Network Models to Evaluate Diagnostic Factors in the Necessity to Perform Angiography</title>
        <AuthorList>
            <Author>
                <FirstName>Parastoo</FirstName>
                <LastName>Golpour</LastName>
            </Author>
            <Author>
                <FirstName>Mohammad</FirstName>
                <LastName>Tajfard</LastName>
            </Author>
            <Author>
                <FirstName>Majid</FirstName>
                <LastName>Ghayour-Mobarhan</LastName>
            </Author>
            <Author>
                <FirstName>Mohsen</FirstName>
                <LastName>Moohebati</LastName>
            </Author>
            <Author>
                <FirstName>Ali</FirstName>
                <LastName>Taghipour</LastName>
            </Author>
            <Author>
                <FirstName>habibollah</FirstName>
                <LastName>Esmaily</LastName>
            </Author>
            <Author>
                <FirstName>Sara</FirstName>
                <LastName>Sabbaghian Tousi</LastName>
            </Author>
        </AuthorList>
        <ArticleType>Research Article</ArticleType>
        <History>
            <PubDate PubStatus="accepted">
                <Year>2022</Year>
                <Month>May</Month>
                <Day>29</Day>
            </PubDate>
            <PubDate PubStatus="received">
                <Year>2022</Year>
                <Month>Jan</Month>
                <Day>05</Day>
            </PubDate>
            <PubDate PubStatus="epublish">
                <Year>2022</Year>
                <Month>Jun</Month>
                <Day>15</Day>
            </PubDate>
            <PubDate PubStatus="ppublish">
                <Year>2022</Year>
                <Month>06</Month>
                <Day>30</Day>
            </PubDate>
        </History>
        <abstract locale="en_US">: Background: Coronary Artery Disease (CAD) is the most common type of
        <br/>
 cardiovascular disorders. Despite being costly and invasive, coronary angiography is a
        <br/>
 reliable method for diagnosing CAD. Therefore, it is crucial to use non-invasive methods
        <br/>
 to screen candidates for angiography to accelerate the process of decision-making. Two
        <br/>
 powerful Machine Learning (ML) methods are Random Forest (RF) and Artificial
        <br/>
 Neural Network (ANN).
        <br/>
 Objectives: The present study aimed to compare RF and ANN to define the most
        <br/>
 important features for positive CAD results and predict the need for angiography as a
        <br/>
 screening method.
        <br/>
 Methods: This cross-sectional study was performed on 1128 patients referred for
        <br/>
 angiography. The data were divided into test and train sets. The models (RF and
        <br/>
 ANN) were fitted with the angiographic outcome variable (positive or negative) as the
        <br/>
 dependent variable and five features as predictors. Then, the performances of the models
        <br/>
 were compared by considering the Area Under the Rock Curve (AUC). All statistical
        <br/>
 analyses were done using the R software, version 4.1.2.
        <br/>
 Results: Out of the 1128 patients, 752 (66.7%) had positive angiography results. The AUC
        <br/>
 values were 0.75 and 0.52 for the test data set in ANN and RF models, respectively.
        <br/>
 Conclusion: Fasting Blood Sugar (FBS), gender, age, Body Mass Index (BMI), and
        <br/>
 smoking habit were important in predicting the results of an angiography for CAD.
        <br/>
 Applying these factors in ML approaches can be considered a screen for angiography to
        <br/>
 accelerate the process of diagnosis.</abstract>
        <web_url>https://brieflands.com/articles/ircrj-122437.html</web_url>
        <pdf_url>No Link</pdf_url>
        <kwd-group>
            <kwd>Artificial Neural Network</kwd>
            <kwd>Random Forest</kwd>
            <kwd>Angiography</kwd>
            <kwd>Machine Learning</kwd>
            <kwd>Coronary Artery Disease</kwd>
            <kwd>Risk factor</kwd>
        </kwd-group>
    </Article>
</Articles>
