Scribd Logo
Upload

Welcome to Scribd!

  • 35 views

    Using Artificial Intelligence To Detect Heart Disease Analysis of Grid Search To Increase Accuracy and Deploying Custom Models Online

    Uploaded by

    International Journal of Innovative Science and Research Technology
    In this paper, I discuss a method for detecting cardiac illness utilising artificial intelligence and machine learning algorithms, and making these systems publicly available

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Using Artificial Intelligence To Detect Heart Disease Analysis of Grid Search To Increase Accuracy and Deploying Custom Models Online

    Uploaded by

    International Journal of Innovative Science and Research Technology
    35 views4 pages
    In this paper, I discuss a method for detecting cardiac illness utilising artificial intelligence and machine learning algorithms, and making these systems publicly available

    Original Title

    Using Artificial Intelligence to Detect Heart Disease Analysis of Grid Search to Increase Accuracy and Deploying Custom Models Online

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    In this paper, I discuss a method for detecting cardiac illness utilising artificial intelligence and machine learning algorithms, and making these systems publicly available

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    35 views4 pages

    Using Artificial Intelligence To Detect Heart Disease Analysis of Grid Search To Increase Accuracy and Deploying Custom Models Online

    Uploaded by

    International Journal of Innovative Science and Research Technology
    In this paper, I discuss a method for detecting cardiac illness utilising artificial intelligence and machine learning algorithms, and making these systems publicly available

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 4

    Volume 8, Issue 2, February – 2023 International Journal of Innovative Science and Research Technology

    ISSN No:-2456-2165

    Using Artificial Intelligence to Detect Heart Disease:


    Analysis of Grid Search to Increase Accuracy and
    Deploying Custom Models Online
    Akshat Kishore
    Student
    The Shri Ram School Aravali
    Gurgaon, India

    Abstract:- In this paper, I discuss a method for detecting These illnesses are generally associated with blood
    cardiac illness utilising artificial intelligence and machine vessel blockages or narrowing, which can lead to heart attacks,
    learning algorithms, and making these systems publicly strokes, and angina. Heart disorders come in a variety of
    available. We demonstrate how artificial intelligence may forms, including those that damage the heart's rhythm, valve,
    be used to forecast if someone would get cardiac disease. A or muscle. Machine learning is greatly useful for evaluating
    python-based application is created for healthcare whether anybody has had cardiac disease. In either event, if
    research in this study since it is more dependable and aids they are anticipated in advance, physicians would find it much
    in tracking and establishing various kinds of health simpler to gather vital information for diagnosing and treating
    monitoring apps. We demonstrate categorical variable patients.
    manipulation and the conversion of categorical columns in
    data processing. We tested a range of machine learning II. THE PROBLEM
    models to achieve the goal of the research and compared
    the accuracy of each of these models to find the most Numerous studies and investigations have been
    accurate. We outline the key stages of application conducted on reducing the risk of heart disease. Based on
    development, including the gathering of databases, blood pressure, smoking habits, cholesterol and blood pressure
    applying logistic regression, parameter tuning, assessing levels, diabetes, and data from population studies, it is now
    the features of the dataset, deploying the model and possible to forecast the development of heart disease [4].
    connecting it to the front-end using APIs. These prediction algorithms have been modified by
    researchers into simpler score sheets that patients may use to
    Keywords:- Artificial Intelligence, Machine Learning, determine their risk of developing heart disease. A common
    Healthcare, AI in Healthcare. risk prediction criterion used in algorithms for heart disease
    prediction is the Framingham Risk Score (FRS). The goal of
    I. INTRODUCTION this work was to create a classification algorithm-based
    intelligent system for heart disease prediction based on risk
    In England, CVD (Cardio Vascular Disease) causes close factor categories.
    to 34% of all fatalities, compared to 40% in the European
    Union. As risk factors for CVD become more common in
    formerly low-risk nations, the rate of CVD is expected to
    climb globally. At the current rate of 80%, cardiovascular
    disease (CVD) will surpass infectious illness as the leading
    cause of death in the majority of developing countries by 2020
    [1]. Not only is CVD a major cause of death, but it also ranks
    first in the world for years of life lost due to impairment. The
    graph below analyses leading death causes globally. [2]

    Over 75% of premature CVD, according to the World


    Health Organization (WHO), is avoidable, and lowering risk
    factors can help lessen the rising burden of CVD on patients
    and healthcare providers [3]. Although age is an established
    risk factor for the development of CVD, postmortem data
    shows that the process of acquiring CVD in later years is not
    unavoidable. As a result, risk mitigation is essential.

    Fig 1: Graph showing global death causes

    IJISRT23FEB247 www.ijisrt.com 489


    Volume 8, Issue 2, February – 2023 International Journal of Innovative Science and Research Technology
    ISSN No:-2456-2165
    III. ETHICS AND FEATURES  V.A. Medical Center, Long Beach and Cleveland Clinic
    Foundation Robert Detrano, M.D., Ph.D. [6]
    We have aimed to incorporate Microsoft’s Responsible
    AI and Ethics Code in our models as described below: [5] This data contains 13 parameters which are frequently
     Inclusivity- We have made sure that our web app is used to determine the presence of heart disease.
    available on freely on the internet, available to be used by
    almost any user across the globe.
     Fairness- Our product aims to provide an easy-to-use
    platform for classification of heart disease based on real
    life parameters such as blood pressure and cholesterol.
     Privacy- both versions of the app ensure full privacy of the
    user by using the basic information gathering, that is, the
    data the user enters exist in our database only while
    running the model: they cease to exist once the result is
    obtained.
     Reliability and Safety- our machine learning models have
    been trained on a big dataset and thus has a high accuracy.
    Thus, the model predicts correct output almost all the time
    it runs.

    IV. RESEARCH AIMS

    The aims of the research are as follows:


     To evaluate the methods for detecting heart disease using
    Artificial intelligence in Python.
     To critically analyse the earlier actions and use a proper
    methodological strategy for superscribing the found issue
     To critically utilise Python language data interpretation
    techniques for identifying health issues.
     To evaluate the artefact or product critically utilising
    cybersecurity strategies, employing the right techniques,
    and determining the work's weaknesses and strengths.

    V. THE PYTHON MODEL

    A. Data
    We used publicly available heart disease data ay UCI,
    obtained through the following creators: Fig 1: Correlation plot
     Hungarian Institute of Cardiology. Budapest: Andras
    Janosi, M.D. We performed data exploration to analyse the
     University Hospital, Zurich, Switzerland: William dependence of variables with high correspondence to the
    Steinbrunn, M.D. presence of the disease condition. This was done using
     University Hospital, Basel, Switzerland: Matthias Matplotlib in Python to visualise the obtained data and its
    Pfisterer, M.D. correlation with the presence of a heart disease.

    Fig 3: Analysis of heart disease presence based on age

    IJISRT23FEB247 www.ijisrt.com 490


    Volume 8, Issue 2, February – 2023 International Journal of Innovative Science and Research Technology
    ISSN No:-2456-2165
    B. The models The Grid Search Model gives the maximum accuracy of
    As a part of model creation, we tested 7 of the most all models due to its hyperparameter tuning algorithm
    common models used for use in such classification problems, described in the next section.
    as summarised in table 1. A summary of the models tested and
    their basic metrics can be seen in the table below.

    Table 1: Summary of all tested models

    Model type Precision Recall F1-Score

    KNN 0.635 0.595 0.595


    SVC 0.745 0.725 0.735
    GridSearch on SVC 0.85 0.85 0.85
    RandomForest 0.82 0.835 0.825
    DecisionTree 0.745 0.755 0.74
    GaussianNB 0.82 0.835 0.825

    Logistic Regression 0.835 0.85 0.84

    C. Grid Search: How it Works


    Grid Search is a method through which Hyperparameters
    can be chosen for any particular model. We chose the SVM
    model considering that it was found to give maximum
    accuracy to hyper parameter tuning.

    Hyperparameters are simply variables that the


    programmer specifies while building a Machine Learning
    Model. Thus, tuning these parameters can improve the
    accuracy of the model.

    The combination with the best performance, and takes


    that combination as its starting point.

    Grid Search assesses the performance for each possible


    combination of the hyperparameters and their values, chooses
    the combination with the best performance, and takes that
    combination as its starting point.

    Grid Search Algorithm will iterate through each of the Fig 2: Working of Grid Search
    points in the graph below and compare the accuracy each
    hyperparameter. Therefore, the grid search algorithm iterates through the
    following number of cases:
    For example, say there is a model which has 2
    hyperparameters, each having exactly 3 possible values. The 𝑁 = 𝑛1 . 𝑛2 . 𝑛3 . . . 𝑛𝑛
    Grid Search Algorithm will iterate through each of the points
    in the graph below and compare the accuracy each Where 𝑛1 is the number of possibilities in the first
    hyperparameter. hyperparameter, 𝑛2 is the number of possibilities in the
    second hyperparameter and so on till n hyperparameters.

    Grid search can also be represented mathematically as a


    cartesian product of the sets of hyperparameters. For example,
    consider two hyperparameters as below:

    𝐻𝑃1 = [𝑎, 𝑏, 𝑐]
    𝐻𝑃2 = [𝑥, 𝑦, 𝑧]

    IJISRT23FEB247 www.ijisrt.com 491


    Volume 8, Issue 2, February – 2023 International Journal of Innovative Science and Research Technology
    ISSN No:-2456-2165
    𝑁
    = [(𝑎, 𝑥), (𝑎, 𝑦), (𝑎, 𝑧), (𝑏, 𝑥), (𝑏, 𝑦), (𝑏, 𝑧), (𝑐, 𝑥), (𝑐, 𝑦), (𝑐, 𝑧)] REFERENCES

    Where N is the set of all iterations that the grid search [1]. Jack Stewart, Gavin Manmathan and Peter Wilkinson
    will perform. Such as set is called a Cartesian product of 𝐻𝑃1 “Primary prevention of cardiovascular disease: A review
    of contemporary guidance and literature,” National
    and 𝐻𝑃2 . Library of Medicine
    [2]. Lauren F Friedman “Just 2 things cause a quarter of all
    Now, as we can see above, grid search checks for each of deaths in the world,” Business Insider
    the parameter’s combinations possible. On the other hand, an [3]. “Cardiovascular diseases (CVDs),” WHO
    algorithm like random search would look through a random set [4]. Zaibunnisa L. H. Malik, Momin Fatema, Nikam Pooja
    of these parameter combinations for better computation times. and Gawandar Ankita “Heart disease prediction using
    artificial intelligence,” IJERT
    Therefore, GridSearch results in maximum accuracy but [5]. “Heart disease dataset,” UCI Machine Learning
    can be slightly slow to compute. However, for out of 7000 Repository
    patients, the GridSearch code ran in less than second. [8] [6]. Petro Liashchynskyi and Pavlo Liashchynskyi “Grid
    search, random search, genetic algorithm: a big
    VI. DEPLOYMENT comparison for NAS,” ArXiv.org
    [7]. Tong Yu and Hong Zhu “Hyper-Parameter optimization:
    A review of algorithms and applications,” ArXiv.org

    Fig 3: Complete analysis of the workflow of creating and


    deploying the model

    VII. RESULTS

    The website has been published on the internet. It has a


    list of parameters which the user must enter and click on the
    “Calculate Possibilities” button.

    Following this, the server code is called and the entered


    parameter are indirectly passed to the model.predict() function
    which gives the result as 0 or 1.

    These results are then simply converted to String outputs


    and displayed to the user on the website in less than 3 seconds.

    VIII. CONCLUSION

    The usage of artificial intelligence can be used to predict


    heart diseases and can have the following advantages:
     Prevention of early risks such as embolic strokes.
     Patients can immediately contact doctors to confirm any
    diagnoses.
     General purpose doctors who are not specialised in
    cardiovascular disease can use this tool to help in
    diagnosis.
     Doctors in rural areas with minimal medical study can use
    the tool as an aid.

    IJISRT23FEB247 www.ijisrt.com 492

    You might also like