2021 5th International Conference on Information Systems and Computer Networks (ISCON)

GLA University, Mathura, India. Oct 22-23, 2021

Heart Disease Prediction Using Supervised Machine

Learning Algorithms
Narendra Mohan Vinod Jain Gauranshi Agrawal
Assistant Professor, Assistant Professor, Department of Computer Engineering
Department of Computer Engineering and Department of Computer Engineering and and Applications
Applications Applications GLA University, Mathura, India
GLA University, Mathura GLA University, Mathura, India [email protected]
[email protected] [email protected]
(ORCHID-0000-0003-0260-7319) (ORCHID- 0000-0002-7037-3318)
2021 5th International Conference on Information Systems and Computer Networks (ISCON) | 978-1-6654-0341-2/21/$31.00 ©2021 IEEE | DOI: 10.1109/ISCON52037.2021.9702314

Abstract—Predicting and detecting cardiac disease has must consider many factors when diagnosing patients, which
always been a difficult and time-consuming undertaking for makes the doctor's job extremely difficult. These
doctors. To treat cardiac disorders, hospitals and other clinics shortcomings encourage researchers to develop a non-
are giving costly therapies and operations. As a result, invasive method for predicting heart disease. So, there is a
anticipating cardiac disease in its early stages will be beneficial need to develop an automated system that can detect heart
to people all around the world, allowing them to take required diseases on the basis of various human medical factors. In this
treatment before it becomes serious. Heart disease has been a work the power we predict heart diseases on the basis of
major issue in recent years, with the primary causes being various factors. The following section describes a review of
excessive alcohol use, tobacco use, and a lack of physical activity.
the literature on predicting heart disease.
Machine learning methods are utilized to forecast cardiac
illnesses in this article. For training and testing, a data II. LITERATURE SURVEY
collection containing diverse human health parameters is used.
Many AI&ML algorithms are used to predict cardiac disorders. Fahd Saleh Alotaibi [1] work on heart diseases and made a
The performance of the machine learning algorithm is model for prediction of heart diseases. S.Nandhini et al. [2]
compared after it has been implemented. apply machine learning algorithms for prediction of heart
diseases. Sanjay Kumar Sen [3] uses popular classifiers to
Keywords—Artificial Intelligence, Machine learning, health predict and diagnose heart disease, including Nave Bayes,
care services, heart disease prediction. SVM, Decision Tree, and K-Nearest Neighbour. A review on
machine learning models for early diagnosis of heart disorders
I. INTRODUCTION was proposed by R. Katarya and P. Srinivas [4]. The study
Heart is the most important organ of the human body. concludes that machine learning can be used to detect cardiac
Heart diseases are the main cause of so many deaths in the problems. A model for predicting cardiac disease was
world now a days. Heart is responsible for pumping of blood proposed by A. Gavhane et al. [5]. M. Kavitha et al. [6]
in human cells. Without the functioning of the heart no one proposed a new model for predicting cardiac disease. P.
can live. Heart diseases refer to all kind of diseases that affect Sujatha and K. Mahalakshmi [7] evaluate the power of
the working of the heart. There are a lot of types of heart machine learning algorithm for prediction of heart diseases.
diseases in the world. Coronary artery diseases CAD is a type
P. S. Kohli and S. Arora [8] also apply ML algorithms in
of most common disease in human hearts. Heart failure HF is
heart diseases prediction. Ed-Daoudy and K. Maalmi apply
also most common type of heart disease. HF is main cause of
big data approach for early detection of heart diseases.
so many deaths now a days.
Erdoğan and S. Güney works on heart diseases prediction
The blocking in coronary arteries is the main cause of using AI and machine learning techniques. Lakshmanarao et
CAD diseases. The blood moves through coronary arteries al. also worked on heart failures and their reasons. S. Farzana
and circulates through all human body. According to a survey, and D. Veeraiah make a dynamic model for prediction of
more than 26 million [3] people are suffering from CAD heart diseases using multi machine learning techniques. S. K.
diseases in the world. In 2005, more than 17.5 million people J. and G. S. and R. Atallah and A. Al-Mousa also develop a
died in the world because of CAD diseases. There is an model for detection and prediction of heart diseases. R.
increase of about 2% in CAD diseases throughout [4] the Wijaya et al. applied machine learning and neural networks to
world. develop a system for prediction and detection of heart
diseases. Author conclude that Neural Networks improves the
There are many reasons of heart diseases in human body. performance of ML algorithms in prediction of heart diseases.
There are mainly two types of risk factors which are Following a review of the literature, it is clear that more
responsible for heart diseases. One category of factors is research is needed in this area. The intended work in this
including those factors which cannot be controlled such as approach is discussed in the next section.
family history, human age and gender. Another category
includes those factors which are responsible for heart diseases III. PROPOSED WORK
and can be controlled. Risk factors such as smoking habits can
be controlled. The heart diseases can be detected by many Recognizing the preparation of raw health-care diseases
ways and angiography is the most common way to detect must be early detected. ML systems are used to analyze raw
heart diseases. However, the angiography method has several data and provide a different and fresh perspective on cardiac
disadvantages. This is an expensive operation, and doctors disease. In the restorative profession, the heart disease outlook
is both challenging and significant. To do heart disease

978-1-6654-0341-2/21/$31.00 ©2021 IEEE 1

Authorized licensed use limited to: M/s Shanti Education Society. Downloaded on September 04,2024 at 06:16:55 UTC from IEEE Xplore. Restrictions apply.
prediction, we used python and pandas activities. The dataset
for forecasting heart illness that we used comes from Kaggle.
In the restorative profession, the heart disease outlook is both
challenging and significant. To do heart disease prediction,
we used python and pandas activities. The dataset for
forecasting heart illness that we used comes from Kaggle.
The suggested system is depicted in the diagram below.
Figure 1 depicts the suggested approach for predicting cardiac
disease using machine learning techniques.

Fig. 3. Confusion matrix of K-NN

Fig. 4. Confusion matrix of Logistic Regression

Fig. 1. Proposed model for heart disease prediction

In this proposed work, the information set is to begin with

partitioned into preparing and testing information sets. At that
point the ML models are prepared on the preparing
information set. At that point the execution of the ML models
is tried on the testing information set. At last, the execution of
ML models is calculated on the premise of the rate of testing
information it approves correctly. This proposed work is
actualized in python programming dialect and the another
area talk about the comes about and examination of this work.

Fig. 5. Confusion matrix of Naïve Bayes

Table 1 is showing the performance of machine learning

models.
The next section discusses the conclusion and future scope
of this paper.
IV. RESULT AND ANALYSIS
Fig. 2. Confusion matrix of Random Forest
This section shows how four machine learning algorithms
were applied to a data set to predict heart disease.
Figure 3, figure 4 and figure 5 are showing the confusion
matrix of RF, KNN, LR and NB machine learningmodels.

2
Authorized licensed use limited to: M/s Shanti Education Society. Downloaded on September 04,2024 at 06:16:55 UTC from IEEE Xplore. Restrictions apply.
 V. CONCLUSION AND FUTURE SCOPE of Recent Engineering Research and Development (IJRERD), ISSN:
2455-8761, vol.3, pp.39-46, 2018.
Four machine learning models KNN, NB, LR and RF are [3] Sanjay Kumar Sen, “Predicting and Diagnosing of Heart Disease
used to predict the heart diseases in human body on the basis using Machine Learning Algorithms,” International Journal of
of some medical parameters. LR algorithms is best among Engineering and Computer Science (IJECS), vol.6, pp.21623-21631,
four which is 90.2%. In future other ML models can be used 2017.
to predict heart diseases. [4] R. Katarya and P. Srinivas, "Predicting Heart Disease at Early
Stages using Machine Learning: A Survey," 2020 International
Conference on Electronics and Sustainable Communication Systems
TABLE I. PREDICTION ACCURACY
(ICESC), Coimbatore, India, 2020, pp.
Sr. Prediction 302-305.doi:10.1109/ICESC48915.2020.9155586
Type of model Accuracy [5] Gavhane, G. Kokkula, I. Pandya and K. Devadkar, "Prediction of
No.
Heart Disease Using Machine Learning," 2018 Second International
1 K NearestNeighbour 82.0% Conference on Electronics, Communication and Aerospace
Technology (ICECA), Coimbatore, India, 2018, pp. 1275-1278. doi:
10.1109/ICECA.2018.8474922
2 Naïve Bayes 86.9% [6] M. Kavitha, G. Gnaneswar, R. Dinesh, Y. R. Sai and R. S. Suraj,
"Heart Disease Prediction using Hybrid machine Learning Model,"
3 Random Forest 86.9% 2021 6th International Conference on Inventive Computation
Technologies (ICICT), Coimbatore, India, 2021, pp. 1329-1333.
4 LogisticRegression 90.2% doi: 10.1109/ICICT50816.2021.9358597
[7] P. Sujatha and K. Mahalakshmi, "Performance Evaluation of
Supervised Machine Learning Algorithms in Prediction of Heart
Disease," 2020 IEEE International Conference for Innovation in
REFERENCES Technology (INOCON), Bangluru, India, 2020, pp. 1-7. doi:
[1] Fahd Saleh Alotaibi, “Implementation of Machine Learning Model 10.1109/INOCON50539.2020.9298354
to predict Heart Failure Disease,” International Journal of Advanced [8] P. S. Kohli and S. Arora, "Application of Machine Learning in
Computer Science and Applications (IJACSA), vol.10, no.6, pp.261- Disease Prediction," 2018 4th International Conference on
268, 2019. Computing Communication and Automation (ICCCA), Greater
[2] S.Nandhini, Monojit Debnath, Anurag Sharma and Pushkar, “Heart Noida, India, 2018, pp. 1-4. doi: 10.1109/CCAA.2018.8777449
Disease Prediction using Machine Learning,” International Journal

3
Authorized licensed use limited to: M/s Shanti Education Society. Downloaded on September 04,2024 at 06:16:55 UTC from IEEE Xplore. Restrictions apply.