(Prediction of Heart Disease Using Machine
Learning)
(Zainab A. Alsyydi)
PG Student
Department of Computer science and information
technology
Thamar University, Yemen
Zaidalsyyadi666@gmail.com
Keywords- Indexed Terms-- Machine Learning, Decision Tree
Classifier, r
I Introduction
Data mining is extracting information and knowledge from
huge amount of data. Data mining is an essential step in
discovering knowledge from databases. There are numbers of
databases, data marts, data warehouses all over the world. Data
Mining is mainly used to extract the hidden information from a
large amount of database. Data mining is also called as
Knowledge Discovery Database (KDD).
The healthcare domain is one of the prominent
research fields in the current scenario with the rapid
improvement of technology and data. It is difficult
to handle the huge amount of data of the patients. It
is easier to handle this data through Big Data
Analytics. There are a lot of procedures for the
treatment of multiple diseases across the world.
Machine Learning is an emerging approach that
helps in prediction, diagnosis of a disease. This
paper depicts the prediction of disease based on
symptoms using machine learning.
Machine Learning algorithms such as Naive
Bayes, Decision Tree and Random Forest are
employed on the provided dataset and predict the
disease. Its implementation is done through the
python programming language. The research
demonstrates the best algorithm based on their
accuracy. The accuracy of an algorithm is
determined by the performance on the given dataset
Today, heart failure diseases affect more people worldwide
than other autoimmune conditions. Cardiovascular Diseases
(CVDs) affect the heart and obstruct blood flow through the
blood vessels. Chronic ailments in CVD include heart disease
(heart attack), cerebrovascular diseases (strokes), congestive
heart failure, and many more pathologies. Worldwide, CVDs
kill around 17 million a year, and death rates due to heart
(Dr. Basheer M. Almaqaleh)
Asst. Professor
Department of Computer science and information
technology
Thamar University, Yemen
e-mail address if desired
diseases have increased after the COVID-19 pandemicCVDs
commonly occur when the heart fails to supply blood under
normal conditions, leading to high blood pressure, diabetes,
chest pain, or other cardiac disorders. Initially, hospitals use
regular tools like ECGs to determine and evaluate the stage of
the disease. Better technologies like MCGs help in detecting
these diseases when they are in an early stage. However, such
devices and technologies are not just expensive and unfit for
smaller clinics for heart disease diagnosis but also time-
consuming and sensitive to tangential causes. Thus,
technicians and clinicians would greatly benefit if there was an
autonomous system in place that could perform a test for heart
disease detection and warn of CVD risk at an early stage. With
AI entering every other industry with the advance of computer
science, medical science perhaps has the vastest scope of need
and use for artificial intelligence solutions -- especially in
developing countries.
Several risk factors for manual heart disease prediction may
include inactivity in a physical form, unhealthy eating habits,
or even the consumption of alcohol. Preexisting conditions,
age, chest pain level, blood test results, and several such factors
can be ensembled together computationally for heart disease
prediction. With such well-defined parameters and the rise of
data science, a data-driven approach can surely help in heart
disease prediction using machine learning technologies. Early
identification of heart disease of improved diagnosis and high-
risk individuals using a prediction model can be recommended
for a fatality rate reduction, and decision-making is improved
for further treatment and prevention.
Be sure that the symbols in your equation have been defined
before or immediately following the equation. Use Machine
learning (ML) is a branch of artificial intelligence (AI) that is
increasingly utilized within the field of cardiovascular
medicine. It is essentially how computers make sense of data
and decide or classify a task with or without human
supervision. The conceptual framework of ML is based on
models that receive input data (e.g., images or text) and
through a combination of mathematical optimization and
statistical analysis predict outcomes (e.g., favorable,
unfavorable, or neutral). Several ML algorithms have been
applied to daily activities.
Heart disease describes a range of conditions that affect your
heart. Today, cardiovascular diseases are the leading cause of
death worldwide with 17.9 million deaths annually, as per the
World Health Organization reports [1]. Various unhealthy
activities are the reason for the increase in the risk of heart
disease like high cholesterol, obesity, increase in triglycerides
levels, hypertension, etc. [1]. There are certain signs which the
American Heart Association [2] lists like the persons having
sleep issues, a certain increase and decrease in heart rate
(irregular heartbeat), swollen legs, and in some cases weight
gain occurring quite fast; it can be 1-2 kg daily [3]. All these
symptoms resemble different diseases also like it occurs in the
aging persons, so it becomes a difficult task to get a correct
diagnosis, which results in fatality in near future.But as time is
passing, a lot of research data and patients records of hospitals
are available. There are many open sources for accessing the
patient’s records and researches can be conducted so that
various computer technologies could be used for doing the
correct diagnosis of the patients and detect this disease to stop
it from becoming fatal
Nowadays it is well known that machine learning and artificial
intelligence are playing a huge role in the medical industry. We
can use different machine learning and deep learning models to
diagnose the disease and classify or predict the results.
A complete genomic data analysis can easily be done using
machine learning models. Models can be trained for knowledge
pandemic predictions and also medical records can be
transformed and analyzed more deeply for better predictions ,
The main Methodology used for prediction is KNN
Algorithms, Decision Trees like CART, C4.5, CHAID, J48,
ID3 Algorithms, and Naive Bayes Techniques. This system
uses 13 medical attributes as input and with that input, Data
sets it to process the data mining techniques and shows the
most accurate one since all previous studies used three main
data mining techniques in their work: namely Decision Tree,
Neural Networks and Naïve Bayes Classifier are used. The
main task of data Prediction is done using these three
techniques however ,there are many disadvantages in this
studies represented in medical misdiagnoses are a serious risk
to our healthcare profession. If they continue, then people will
fear going to the hospital for treatment. We can put an end to
medical misdiagnosis by informing the public and filing claims
and suits against the medical practitioners at fault.
Most of these studies are theoretical analysis at the macro
level and there is a lack of quantitative investigations .
Data mining is a knowledge discovery technique to analyze
data and encapsulate it into useful information The current
research intends to predict the probability of getting heart
disease given patient data set Predictions and descriptions are
principal goals of data mining, in practice Prediction in data
mining involves attributes or variables in the data set to find an
unknown or future state
In this system, a heart disease data set is used. The main
aim of this system is to predict the possibilities of occurring
heart disease of the patients in terms of percentage. This is
performed through data mining classification techniques.The
classification technique is used for classifying the entire dataset
into two categories namely yes and No. Classification
technique is applied to the dataset through the machine learning
classification algorithm namely Decision tree classification and
Naïve Bayes Classification models
These models are used to enhance the accuracy level of the
classification technique. This model performs both the
classification and prediction methods. These models are
performed using python Programming Language where it will
benefit us in enhance visualization and ease of interpretation
Heart disease is very fatal and it should not be taken
lightly. heart disease happens more in males than females,
which can be read further from Harvard Health Publishing
[15] researchers found that, throughout life, men were about
twice as likely as women to have a heart attack that higher risk
persisted even after they accounted for traditional risk factors
of heart disease, including high cholesterol, high blood
pressure, diabetes, body mass index, and physical activity .The
researchers are working on this dataset as it contains certain
important parameters like dates from 1998, and it is
considered as one of the benchmark datasets when someone is
working on heart disease prediction.
II .LITERATURE SURVEY
A quiet significant amount of work related to the diagnosis of
Cardiovascular Heart disease using Machine Learning
techniques has motivated this study. An efficient
Cardiovascular heart disease prediction has been made by
using many techniques some of them include KNN,
Random Forest Classifier etc. It can be seen in Results that
each technique has its strength to register the defined
objectives
This Paper predicts heart disease for Male Patient using
Classification Techniques. The detailed information about
Coronary Heart diseases such as its Facts, Common Types,
and Risk Factors has been explained in this paper. The Data
Mining tool used is WEKA (Waikato Environment for
Knowledge Analysis), a good Data Mining Tool for
Bioinformatics Fields. The all three available Interface in
WEKA is used here. Naive Bayes, Artificial Neural Networks
and Decision Tree (J48) are Main Data Mining Techniques
and through this techniques heart disease is predicted in this
System [4].
Through this paper the information about Data Mining and
heart diseases has been gathered. The detailed information
about heart diseases, symptoms of heart attack and heart
disease types are presented in this paper, the three main data
mining techniques namely Decision Tree, Neural Networks
and Naive Bayes Classifier are used. The main task of data
Prediction is done using these three techniques. The
Advantages and Disadvantages of each technique can be
known using this paper [5].
This System predicts the arising possibilities of Heart
Disease. The outcomes of this system provide the chances of
occurring heart disease in terms of percentage. The datasets
used are classified in terms of medical parameters. This
system evaluates those parameters using data mining
classification technique. The datasets are processed in python
programming using two main Machine Learning Algorithm
namely Decision Tree Algorithm and Naive Bayes Algorithm
which shows the best algorithm among these two in terms of
accuracy level of heart disease. [6]
Through this paper: With the rampant increase in the heart
stroke rates at juvenile ages, we need to put a system in place
to be able to detect the symptoms of a heart stroke at an early
stage and thus prevent it. It is impractical for a common man
to frequently undergo costly tests like the ECG and thus there
needs to be a system in place which is handy and at the same
time reliable, in predicting the chances of a heart disease. Thus
we propose to develop an application which can predict the
vulnerability of a heart disease given basic symptoms like age,
sex, pulse rate etc. The machine learning algorithm neural
networks has proven to be the most accurate and reliable
algorithm and hence used in the proposed system[7]
Heart disease is the Leading cause of death worldwide. This
System predicts the arising possibilities of Heart Disease. The
outcomes of this system provide the chances of occurring
heart disease in terms of percentage. The datasets used are
classified in terms of medical parameters. This system
evaluates those parameters using data mining classification
technique. The datasets are processed in python programming
using two main Machine Learning Algorithm namely Decision
Tree Algorithm and Naive Bayes Algorithm which shows the
best algorithm among these two in terms of accuracy level of
heart disease [8]
This study proposes an efficient neural network with
convolutional layers to classify significantly class-imbalanced
clinical data. The data is curated from the National Health and
Nutritional Examination Survey (NHANES) with the goal of
predicting the occurrence of Coronary Heart Disease (CHD).
While the majority of the existing machine learning models
that have been used on this class of data are vulnerable to class
imbalance even after the adjustment of class-specific weights,
our simple two-layer CNN exhibits resilience to the imbalance
with fair harmony in class-specific performance. Given a
highly imbalanced dataset, it is often challenging to
simultaneously achieve a high class 1 (true CHD prediction
rate) accuracy along with a high class 0 accuracy, as the test
data size increases. We adopt a two-step approach: first, we
employ least absolute shrinkage and selection operator
(LASSO) based feature weight assessment followed by
majority-voting based identification of important features.
Next, the important features are homogenized by using a fully
connected layer, a crucial step before passing the output of the
layer to successive convolutional stages. We also propose a
training routine per epoch, akin to a simulated annealing
process, to boost the classification accuracy[9]
This paper presents a real-time system for predicting heart
disease from medical data streams that describe a patient’s
current health status. The main goal of the proposed system is
to find the optimal machine learning algorithm that achieves
high accuracy for heart disease prediction. Two types of
features selection algorithms, univariate feature selection and
Relief, are used to select important features from the dataset.
We compared four types of machine learning algorithms;
Decision Tree, Support Vector Machine, Random Forest
Classifier, and Logistic Regression Classifier with the selected
features as well as full features. We apply hyperparameter
tuning and cross-validation with machine learning to enhance
accuracy. One core merit of the proposed system is able to
handle Twitter data streams that contain patients’ data
efficiently. This is done by integrating Apache Kafka with
Apache Spark as the underlying infrastructure of the system.
The results show the random forest classifier outperforms the
other models by achieving the highest accuracy at 94.9%[10]
In order to tackle this issue and to accurately diagnosis the
patient of PD, we proposed a machine-learning-based
prediction system. In the development of the proposed system,
the support vector machine (SVM) was used as a predictive
model for the prediction of PD. The L1-norm SVM of features
selection was used for appropriate and highly related features
selection for accurate target classification of PD and healthy
people. The L1-norm SVM produced a new subset of features
from the PD dataset based on a feature weight value. For the
validation of the proposed system, the K-fold cross-validation
method was used. In addition, the metrics of performance
measures, such as accuracy, sensitivity, specificity, precision,
F1 score, and execution time, were computed for model
performance evaluation. The PD dataset was in this paper. The
optimal accuracy achieved the best subset of the selected
features that might be due to various contributions of the PD
features. The experimental findings of this paper suggest that
the proposed method can be used to accurately predict the PD
and can be easily incorporated in healthcare for diagnosis
purpose. Currently, the computer-based assisted predictive
system is playing an important role to assist in PD recognition.
In addition, the proposed approach fills in a gap on feature
selection and classification using voice recordings data by
properly matching the experimental design[11]
, the purpose of this study is to increase the accuracy of
coronary heart disease diagnosis through selecting significant
predictive features in order of their ranking. In this study, we
propose an integrated method using machine learning. The
machine learning methods of random trees (RTs), decision
tree of C5.0, support vector machine (SVM), and decision tree
of Chi-squared automatic interaction detection (CHAID) are
used in this study. The proposed method shows promising
results and the study confirms that the RTs model outperforms
other models[12].
Data mining is the useful tool to discovering the
knowledge from large data. Different methods & algorithms
are available in data mining. Classification is most common
method used for finding the mine rule from the large database.
Decision tree method generally used for the Classification,
because it is the simple hierarchical structure for the user
understanding & decision making. Various data mining
algorithms available for classification based on Artificial
Neural Network, Nearest Neighbour Rule & Baysen
classifiers but decision tree mining is simple one. ID3 and
C4.5 algorithms have been introduced by J.R Quinlan which
produce reasonable decision trees. The objective of this paper
is to present these algorithms. At first we present the classical
algorithm that is ID3, then highlights of this study we will • Coronary artery disease
discuss in more detail C4.5 this one is a natural extension of • Cardiac arrest
the ID3 algorithm. And we will make a comparison between • Congestive heart failure
these two algorithms and others algorithms such as C5.0 and • Stroke
CART[13] • Lift ,right heart failure
This study gathered data from a variety of sources and divided • Acute ,chronic heart failure
it into two parts: 80 percent for the training dataset and 20% • Systolic ,diastolic heart failure
for the test dataset. Different classifier methods were used to
IV Methodology
improve accuracy, which was then summarized. Random
Health care field has a vast amount of data, for processing
Forest Classifier, Decision Tree Classifier, Support Vector
those data certain techniques are used. Data mining is one of
Machine, k-nearest neighbor, Logistic Regression, and Naive
the techniques often used. Heart disease is the Leading cause
Bayes are the methods in question. SVM, Logistic Regression,
of death worldwide. This System predicts the arising
and KNN all performed as well as or better than other
possibilities of Heart Disease. The outcomes of this system
methods. This research offers a development in which
provide the chances of occurring heart disease in terms of
fundamental prefixes such as sex, glucose, blood pressure,
percentage. The datasets used are classified in terms of
heart rate, and others are used to determine which factors are
medical parameters. This system evaluates those parameters
prone to heart disease. The paper's next aim is to conduct real-
using data mining classification technique. The datasets are
life tests using various equipment and clinical trials. [14] processed in python programming using two main Machine
In this paper, we proposed three methods in which
Learning Algorithm namely Decision Tree Algorithm and
comparative analysis was done and promising results were
Naïve Bayes Algorithm which shows the best algorithm
achieved. The conclusion which we found is that machine
among these two in terms of accuracy level of heart disease
learning algorithms performed better in this analysis. Many
The proposed methodology includes the following steps: the
researchers have previously suggested that we should use ML.
first step is referred to as the collection of the data then in
[16] second step, it extracts significant values then the 3rd is the
preprocessing step where we explore the data. Data
III.HEART DISEASE
preprocessing deals with the missing values, cleaning of data
and normalization depending on algorithms used
A heart is a vital organ of the human body. If a heart does not
After pre-processing of data, each classifier is used to classify
perform its operation properly, it will influence the other organ
the pre-processed data. Finally, the proposed model is
of the human-like kidney, brain, etc. According to the undertaken, where we evaluated our model on the basis of
statistical data from WHO, one-third population worldwide
accuracy and performance using various performance metrics.
died from heart disease; heart disease is found to be the
Here in this model, an effective Heart Disease Prediction
leading cause of death in developing countries by 2017. The
System has been developed using different classifiers. This
heart pumps blood through the blood vessels of the circulatory
model uses 17 medical features such as an attributes below in
system. Blood provides the body with oxygen and nutrients, as
the table for prediction
well as assisting in the removal of metabolic wastes. In the
event, if blood in the body is insufficient then many organs Attribute Description Possible Values
like cerebrum suffer and if heart quits working by, death
Dummy Identification of
happens inside minutes. Patient Id
the patient
Heart disease risk factor include:
Gender Male, Female
• High Cholesterol
• High blood pressure Youth = 30-39, Young
Young
• Diabetics Adult =40-49 Adult
Age Young Adult
• Smoking =50-59 Old People =60-
Adult Old
• Consuming too much alcohol 69
• Being overweight or obese Stable Angina –
• Family history of coronary illness Predictable Chest Pain Stable angina
Symptoms of Heart attack: Unstable Angina –Chest Non-angina
• Shortness of breath Chest Pain pain that signal Unstable angina
• Pain and discomfort in chest Type impending heart attack Prinzmetal’s
• Pain may spread to left or right arm or to neck, jaw, back or Prinzmetal's Angina – angina
stomach have coronary Asymptomatic
• Fatigue artery disease
• Cold sweat and unsteadiness Low-density
• Rapid or irregular heart beat lipoproteins (LDL) (Bad
LDL
• Heart burn or abnormal pain Cholesterol Cholesterol), High-
HDL
Types of cardiovascular disease: density lipoproteins
(HDL) (Good
 Cholesterol on Innovations in Information and Communication Technology
(ICIICT), 2019.
Smoking Yes, No
[7] A. Gavhane, G. Kokkula, I. Pandya and K. Devadkar, "Prediction of
If Blood Sugar level is > Heart Disease Using Machine Learning," 2018 Second International
Blood Sugar 120 mg/dl -Increase the True, False Conference on Electronics, Communication and Aerospace Technology
risk (ICECA), 2018, pp. 1275-1278, doi: 10.1109/ICECA.2018.8474922
Normal(systolic<139mm [8] S. K. J. and G. S., "Prediction of Heart Disease Using Machine Learning
Algorithms," 2019 1st International Conference on Innovations in
Blood Hg), Prehypertension- Normal Information and Communication Technology (ICIICT), 2019, pp. 1-5,
Pressure (systolic >140 mmHg), Prehypertension doi: 10.1109/ICIICT1.2019.8741465
High – (systolic > 160 High [9] An efficient convolutional neural network for coronary heart disease
mmHg) prediction
Normal - ST_T wave Aniruddha Dutta, Tamal Batabyal, Meheli Basu, Scott T Acton
Abnormality, Left Expert Systems with Applications 159, 113408, 2020
Normal
(ECG) Ventricular Hypertrophy [10] Hager Ahmed, Eman MG Younis, Abdeltawab Hendawi, Abdelmgeid A
Abnormal Ali Future Generation Computer Systems 111, 714-722, 2020
(LVH) {Electro cardio
graphic results } Heart disease identification from patients’ social posts, machine learning
solution on Spark
Healthy,
Diet [11] Feature selection based on L1-norm support vector machine and
Unhealthy effective recognition system for Parkinson’s disease using voice
Alcohol True, False recordings
Amin Ul Haq, Jian Ping Li, Muhammad Hammad Memon, Asad Malik,
Tanvir Ahmad, Amjad Ali, Shah Nazir, Ijaz Ahad, Mohammad Shahid
V CONCLUSION IEEE access 7, 37718-37734, 2019
In this paper, two supervised data mining algorithm was [12] Javad Hassannataj Joloudari, Edris Hassannataj Joloudari, Hamid
applied on the dataset to predict the possibilities of having heart Saadatfar, Mohammad Ghasemigol, Seyyed Mohammad Razavi, Amir
Mosavi, Narjes Nabipour, Shahaboddin Shamshirband, Laszlo Nadai
disease of a patient, were analyzed with classification model
International journal of environmental research and public health 17 (3),
namely Naïve Bayes Classifier and Decision tree classification. 731, 2020
These two algorithms are applied to the same dataset in order [13] Badr HSSINA, Abdelkarim MERBOUHA,Hanane
to analyze the best algorithm in terms of accuracy.. EZZIKOURI,Mohammed ERRITALI TIAD laboratory, Computer
Sciences Department, Faculty of sciences and techniques Sultan
REFERENCES "A comparative study of decision tree ID3 and C4.5" Sultan Moulay
Slimane University Beni-Mellal, BP: 523, Morocco
[14] G.R. RAO1, SHOURYA KHUJNERI2, ATUL KUMAR
TOMAR3, RUDRAKSH SHARMA4 1 Associate Professor,
[1] World Health Organization, Cardiovascular Diseases, WHO, Geneva, Department of computer Engineering Bharati Vidyapeeth Deemed to be
Switzerland, 2020, https://www.who.int/health-topics/cardiovascular- University College of Engineering, Pune, India 2, 3, 4 Department of
diseases/#tab=tab_1. computer Engineering Bharati Vidyapeeth Deemed to be University
[2] American Heart Association, Classes of Heart Failure, American Heart College of Engineering, Pune, India" Heart Disease Prediction Using
Association, Chicago, IL, USA, 2020, https://www.heart.org/en/health- Machine Learning June 2022 | IJIRT | Volume 9 Issue 1 | ISSN: 2349-
topics/heart-failure/what-is-heart-failure/classes-of-heart-failure. 6002 "
[3] American Heart Association, Heart Failure, American Heart [15] An efficient convolutional neural network for coronary heart disease
Association, Chicago, IL, USA, 2020, https://www.heart.org/en/health- prediction
topics/heart-failure Aniruddha Dutta, Tamal Batabyal, Meheli Basu, Scott T Acton
Expert Systems with Applications 159, 113408, 2020
[4] Gandhi, Monika, and Shailendra Narayan Singh. "Predictions in heart [16] Rohit Bharti ,1 Aditya Khamparia ,2 Mohammad Shabaz ,3 Gaurav
disease using techniques of data mining." In 2015 International Dhiman ,4 Sagar Pande ,1 and Parneet Singh 5" Prediction of Heart
Conference on Futuristic Trends on Computational Analysis and Disease Using a Combination of Machine Learning and Deep Learning"
Knowledge Management (ABLAZE), pp. 520-525. IEEE, 2015. Computational Intelligence and Neuroscience Volume 2021, Article ID
[5] Rairikar, A., Kulkarni, V., Sabale, V., Kale, H., & Lamgunde, A. (2017, 8387680, 11 pages
June). Heart disease prediction using data mining techniques. In 2017
International Conference on Intelligent Computing and Control (I2C2)
(pp. 1-8). IEEE
[6] Santhana Krishnan.J, Geetha.S, “Prediction of Heart Disease Using
Machine Learning Algorithms”, IEEE 2019 1st International Conference