International Journal of Engineering and Advanced Technology (IJEAT)

ISSN: 2249 – 8958, Volume-8, Issue-3S, February 2019

Heart Disease Prediction using Logistic

Regression Algorithm using Machine
Learning
Reddy Prasad,Pidaparthi Anjali, S.Adil, N.Deepa

ABSTRACT---We are in a period of “Information Age” logistic regression algorithm is represented in the graphs
where the traditional industry can pressure the rapid shift to the showing the difference between the attributes.From the
industrial revolution for industrialization, based on economy of training data we haveto estimate the best and approximate
information technology Terabytes of data are produced and
coefficient and representit.
stored day-to day life because of fast growth in „Information
Technology‟. Terabytes of data are produced and stored day-to Naive bayes
day life because of fast growth in „Information Technology‟. The
data which is collected is converted into knowledge by data Naive bayesalgorithm[1] which is mainly used,also helps
analysis by using various combinations of algorithms. For for classification.The large datasets can be build by using
example: the huge amount of the data regarding the patients is the algorithm native bayes. It is a classification technique
generated by the hospitals such as x-ray results , lungs results and it assumes as independence among each attribute. It will
,heart paining results, chest pain results , personal health helps in the removing of correlated data.
records(PHRs) ., etc. There is no effective use of the data which
is generated from the hospitals. Some certain tools are used to Comparing and confusion matrices
extract the information from the database for the detection of
heart diseases and other functions is not accepted. The main
The comparison a confusing matrices, it is the summary
theme of the paper is the prediction of heart diseases using for the prediction of the result which we classified. Based on
machine learning techniques by summarizing the few current the classification of attributes the correct and incorrect
researches. In this paper the logistic regression algorithms is predictions are marked with count values.A confusion
used and the health care data which classifies the patients matrix,which is represented in table format will explains
whether they are having heart diseases or not according to the about the performance of characterization model on the
information in the record. Also I will try to use this data a model
which predicts the patient whether they are having heart disease
trained dataset.The most of the performance measures are
or not. calculated using this confusion matrix.
Keywords :-Heart Diseases; Machine Learning; Data The most important organ of the human body is heart.
Analysis; Logistic Regression Algorithms . The function of the heart is to pump the blood and circulates
entire body [2]. It is protected by rib cage and it is
I. INTRODUCTION: DOMAIN : surrounded by two layered tissue membrane called
To initiate with the work we can use different types of Pericardium. It is a four chambered organ which separates
techniques and algorithms. In this paper, machine oxygenated and deoxygenated blood. Heart is having the
learningtechniques are used toincreasetheaccuracy rate. In five types of blood vessels:arteries,veins,capillaries,
machine learning technique we can use the arterioles, venules and .The size of the human heart is about
followingalgorithm the size of the fist and weight approximately 300grams,the
1. Logistic regression weight in females being about 25% lesser than
males.Arteries and veins are present in heart which helps to
2. Naivebayes collect the blood from all the parts and purifies it and the
3. Comparing and confusionmatrix circulates to all the body parts. The nutrients and oxygen
Sklearn Logistic regression present in the body parts are provided by the blood and also
will helps in the removal of metabolic wastes. Now a days
The logistic regression is also known as sigmoid function
the life span of human being is reduced due to the heart
which helps in the easy representation in graphs. It also
diseases. The factors which may lead to heart disease are
provides high accuracy. In this algorithm first the data
obesity, high cholesterol,smoking, increase in blood
should be imported and then trained. By using equation the
pressure, diabetes and other factors.
As per the WHO(World Health Organization) records,
Revised Manuscript Received on February 14, 2019. each and every year millions of people died with different
Reddy prasad, ug scholar, department of computer science and
engineering, saveetha school of engineering, simats, chennai, tamil nadu, types of cardio attacks such as heart stroke, chest pain,etc.
india. (email id:[email protected]) We here proposed the collection of relevant data from the
Pidaparthi anjali, ug scholar, department of computer science and hospitals wherethe data is so enormous. Now we have to
engineering, saveetha school of engineering, simats, chennai, tamil nadu,
india
S.adil, ug scholar, department of computer science and engineering,
saveetha school of engineering, simats, chennai, tamil nadu, india
N.deepa, assistant professor, department of computer science and
engineering, saveetha school of engineering, simats, chennai,tamil nadu,
india (email id: [email protected])

Published By:
Blue Eyes Intelligence Engineering
Retrieval Number: C11410283S19/19©BEIESP 659 & Sciences Publication
 HEART DISEASE PREDICTION USING LOGISTIC REGRESSION ALGORITHM USING
MACHINE LEARNING
separate the data regarding the patients related to heart
diseases. We train the data as per proposed algorithm of
machine learning[3] by using logistic regression. For the
purpose of detecting the heart disease , we can enter patient
medical details into the trained data.

II. EXISTING SYSTEM :

The before all existing system[4] works on sets of both
Deep learning and data mining[5]. The existing system
modules generates comprehensive report by implementing
the strong prediction algorithm The main aims of the
existing system to compare and check the before patient
whose having disease outputs and new patient disease and
determine future possibilities of the heart disease to a
particular patient By Implementing the above mentioned
model we will get the goal of developing a system with
increased rate of accuracy of estimating the new patient
getting heart attack percentage. The model which is
proposed for Heart Attack Prediction System is invented for
using Deep learning[6] algorithms and approach. But by
using all the existing systems the accuracy is very less.

III. PROPOSED SYSTEM:

This proposed system have a data which classified if
patients have heart disease or not according to features in it.
This proposed system can try to use this data to create a
model which tries predict(reading data and data
Exploration)[7] if a patient has this disease or not. In this
proposed system, use logistic regression (classification)
algorithm. By using sklearn library to calculate score.
Implements Navie Bayes algorithm to getting accuracy
result.Finally analysing the results by the help of Comparing
Models and Confusion Matrix.
From the data we are having, it should be classified into
different structured data based on the features of the patient
heart. Fromtheavailabilityofthedata,wehaveto create a model
which predicts the patient disease using logistic regression
algorithm. First, we have to import the datasets. Read the
datasets, the data should contain different variables like
age,gender, sex, cp(chest pain),slope, target. The data should
be explored so that the information is verified.Create a
temporary variable and also build a model for logistic
regression. Here, we use sigmoid function which helps in the
graphical representation of the Implementation of Logistic Regression Algorithm :
classifieddata.Byusinglogisticregression, naïve bayes the
accuracy rateincreases.

Read the Data

Published By:
Blue Eyes Intelligence Engineering
Retrieval Number: C11410283S19/19©BEIESP 660 & Sciences Publication
 International Journal of Engineering and Advanced Technology (IJEAT)
ISSN: 2249 – 8958, Volume-8, Issue-3S, February 2019

Fixing Targets about the Disease

Accuracy% result in Knn Algorithm

Separate the data about sex, age

Accuracy% result in logistic regression algorithm

Heart disease Frequency for ages

Testing accuracy for logistic regression algorithm

Checking Disease

Result Accuracy% in algorithms:

Accuracy% result in Navie Bayes Accuracy% result in graph between

Algorithms

Acuuracy% result in Decision Tree

Published By:
Blue Eyes Intelligence Engineering
Retrieval Number: C11410283S19/19©BEIESP 661 & Sciences Publication
 HEART DISEASE PREDICTION USING LOGISTIC REGRESSION ALGORITHM USING
MACHINE LEARNING
IV. CONCLUSION
The amount of Heart diseases can exceed the control line
and reach to maximum point. Heart disease are complicated
andeachandeveryyearlotsof people are dying with this
disease By using this all systems one of the major
drawbacks of these works is mainly focus only to the
application of classify techniques and algorithms for heart
disease prediction, by all these studying various data
cleaning and mining techniques that prepare and build a
dataset appropriate for data mining. So that I can use this
Machine Learning in that logistic regression algorithms by
predicting if patient has heart disease or not. Any non-
medical employee can use this software and predict the heart
disease and reduce the time complexity of the doctors.

V. FUTURE WORK
Today’s, world most of the data is computerized, the data
is distributed and it is not utilizing properly. By Analyzing
the available data we can also use for unknown patterns. The
primary motive of this research is the prediction of heart
diseases with high rate of accuracy. For predicting the heart
disease we can use logistic regression algorithm,
naviebayes, sklearn in machine learning. The future scope of
the paper is the prediction of heart diseases by using
advanced techniques and algorithms in less time complexity.

REFERENCES
1. M.A. Jabbar ,2016;Heart disease prediction system based on
hidden naviebayes classifier;2018 International conference on
circuits , controls, communications and computing(14C)
2. Rifki Wijaya,2013.Preliminary design of estimation heart
disease by using machine learning ANN within on year;
communication technology andelectricvehicle technology ,
bandung-bali, Indonesia.
3. AditiGavhane , 2018 . Prediction of heart disease using
machine learning, ISBN:978-1-5386-0965-1.
4. Sana Bharti,2015 .Analytical study of heart disease prediction
comparing with different algorithms; International conference
on computing, communication andautomation(ICCA2015).
5. Monika Gandhi,2015. Prediction in heart disease using
techniques of data mining, International conference on
futuristic trend in computational analysis and knowledge
management(ABLAZE- 2015)
6. Sarath Babu,2017.Heart disease diagnosis using data mining
technique,international conference on
electronics,communication and aerospace technology
ICECA2017
7. A H Chen, 2011. HDPS: heart disease prediction system; 2011
computing in cardiology
8. Dinesh Kumar G, 2018 . Prediction of cardiovascular disease
using machine learning algorithms, procedingof 2018 IEEE
International Conference on Current Trends toward
Converging Technologies, Coimbatore, India.
9. Purushottam ,2015. Efficient heart disease prediction system
using decision tree;International conference on computing,
communication &automation
10. Nikhil Gawande ,2017. Heart diseases classification using
nd
convolutional neural network; 2012 2 International
conference on communication and electronics
systems(ICCES)
11. AnkitaDewan, 2015. Prediction of heart disease using a hybrid
technique in data mining classification 20152nd

Published By:
Blue Eyes Intelligence Engineering
Retrieval Number: C11410283S19/19©BEIESP 662 & Sciences Publication