Vol-2 Issue-2 2016 IJARIIE-ISSN (O)-2395-4396

SURVEY OF HEART DISEASE

PREDICTION BASED ON DATA MINING
ALGORITHMS

S.B.BHALERAO 1 , DR. B.L.GUNJAL2

1
ME Student, Department of Computer Engineering, Amrutvahini COE, Sangamner, Maharashtra, India
2
Associate Professor, Department of Computer Engineering, Amrutvahini COE, Sangamner,
Maharashtra, India

ABSTRACT
The medical field is dealing with huge amount of data regularly. Handling that large data by traditional way may
affect the results. Advanced data mining techniques are used to find out facts in database and for medical research,
particularly in Heart disease prediction. Heart disease is the leading cause of death all over the world. The massive
amounts of data generated for prediction of heart disease which is too difficult and baggy to be processed and
analyzed by conventional methods. Data mining provides the methodology and technology to transform these
mounds of data into useful information for decision making. Use of data mining algorithms will result in quick
prediction of disease with high accuracy. In this paper we survey different papers in which single or hybrid
combination of data mining algorithms are used for the prediction of heart disease, so that we can identify the
algorithms with high accuracy for further research.

Keyword: - Data mining; Heart disease prediction; Data mining techniques

1. Introduction

1.1 Data mining and medical industry

Data mining is technique of exacting implicit, previously unknown and future useful information from available
data. In short it is process of analyzing data from different viewpoint and assembling the knowledge from it. To
extract unknown patterns and relationships from huge databases, data mining mixes the statistical analysis, machine
learning and database technology. The acquire knowled ge can be useful for different application namely health care
industry. Health Informatics is a rapidly growing field that is concerned with evolving Computer Science and
Information Technology to medical and health data. Medical Data Mining is a domain of challenge which involves
lot of misdiagnosis and uncertainty. A general framework proposed for medical data mining is shown in Fig.1 [2].

1844 www.ijariie.com 856

Vol-2 Issue-2 2016 IJARIIE-ISSN (O)-2395-4396

Clustering
Outlier
detection

Medical
Data Medical Data Knowledge
Data Preprocessing Mining
Evolution
Selection

Association Classification
Rule

1.2 Heart disease

Heart is an important organ of all living individual, which plays an essential role of blood pumping to the rest of the
organs through the blood vessels of the circulatory system. If circulation of blood in body is improper the organs
like brain suffer and if heart stops working altogether and death occurs. Life is completely dependent on proper
working of the heart. The term Heart disease refers to disease of heart & blood vessel system within it.
Factors that increases the risk of Heart disease:
 Family history
 Age
 Smoking
 Poor diet
 High blood pressure
 High blood cholesterol
 Obesity
 Physical inactivity
 Hyper tension
In many cases, diagnosis is generally based on patient’s current test report & doctor’s experience. Thus the diagnosis
is a complex task that requires high skill & much experience.

2. Literature Survey

Carlos Ordonez [3] did study on prediction of heart disease with the help of Association rules. They used a simple
mapping algorithm. This algorithm constantly treats attributes as numerical or categorical. This is used to convert
medical records to a transaction format. An improved algorithm is used to mine the constrained association rules. A
mapping table is prepared and attribute values are mapped to items. The decision tree is used for mining data
because they automatically Split numerical values [3]. The split point chosen by the Decision tree are of little use
only. Clustering is used to get a global understanding of data.

1844 www.ijariie.com 857

Vol-2 Issue-2 2016 IJARIIE-ISSN (O)-2395-4396

Deepika [4] have worked on Pruning-Classification Association Rule (PCAR), for mining A ssociation Rule. PCAR
based on analysis of Apriori algorithm. PCAR deals with minimum frequency item sets. It deletes irregular item
from item sets. Then it classifies item sets based on frequency of item sets and find out the frequent item sets.

C. Ordonez [12] uses association rules a technique in data mining to get better heart disease prediction result .The
author have worked on the limitation of association rule which is nothing but mining the entire data set without
validation on an independent sample. The modified algorithm with search constraints was introduced to trim down
the number of association rules and validated using train and test approach. They have studied two complementary
tasks: predicting the absence and predicting the existence of heart disease.

P. Chandra, M.Jabbar [13] produced class association rules using feature subset selection to detect a heart disease.
Association rule determines relations between attributes values and classification to predict the class in the patient
dataset [13]. Feature selection measures like genetic search determines attributes which helps in predicting heart
diseases.

Usha Rani [5] have proposed a system for predicting heart disease with the help of artificial neural network which is
a combination of feed forward and back propagation algorithm. The experiment is carried out by considering single
and multilayered neural network models. Parallelism is implemented to speed up the learning process at each neuron
in all hidden and output layer.

In [6] R. Setthukkarasi, have developed a novel neuro fuzzy technique to diagnose the fact of the disease from the
set of the patient report. A generalized database is constructed for decision making from the reduced attributes set
which is output of genetic algorithm. A four layered fuzzy neural network fo r efficient modeling and reasoning with
temporal dependencies under uncertainty is used.

In [8] Chaitrali Dangare has implemented system to predict heart disease three data mining classification techniques
were applied that is Decision trees, Naive Bayes & Neural Networks. From results it has been seen that Neural
Networks better than Decision trees & Naive Bayes.

M.Akhil jabbar, B.LDeekshatulu, Priti Chandra [7] propose a new algorithm which combines KNN with Genetic
Algorithm for effective classification. To provide optimal solution genetic algorithms perform global search on
complex large and multimodal dataset. From the results it is also observed that hybridizing GA with KNN performs
well and give great accuracy.

Ankita Dewan [1], proposed efficient genetic algorithm mix with the back propagation technique approach for heart
disease prediction. They have made conclusion that neural network is best among all the classification techniques
for a non-linear data. BP algorithm is the best classifier of Artificial Neural Network which is a common method of
training. In this the primary system output is compared to the desired output, and the system is adjusted until the
difference between the two is minimized. But it has drawback of being stuck in a local minima.

Shadab Adam Pattekari and Asma Parveen [9] developed a Decision Support in Heart Disease Prediction System
using Naive Bayesian Classification technique. The system discovers the hidden knowledge from a past heart
disease database. This is the most effective model to predict patients with heart disease. This model could respond to
complex queries, each with its own strength with respect to ease of model interpretation, access to detailed
information and accuracy.

R. Bhuvaneswari et al., [10], use Naive Bayes classifier in medical applications. The author have used two well-
known algorithms of data mining classification that is Back propagation Neural Network(BNN) and Nave Bayesian
(NB) which calculate the probability of the object among all objects by studying the previous experience. Bayesian
technique is developed on the probability concept. The posterior from the prior is calculated by bayes rules based on
the precise nature of the probability model, Naive Bayes classifiers is used to trained very efficiently in a supervised
learning setting.

Nilakshi P. Waghulde, Nilima P. Patil [11] did an experiment with Heart Disease dataset by taking into
consideration of Multi-Layer Neural Network along with Back propagation Learning Algorithm for training the
network. To optimize the initialization of neural network weights genetic algorithm is used. This work shows the

1844 www.ijariie.com 858

Vol-2 Issue-2 2016 IJARIIE-ISSN (O)-2395-4396

result of Genetic Neural Network for prediction of heart disease by improving the accuracy as 98% using optimize
neural network architecture it predicts whether the patient is suffering from heart disease or not.

K. Srinivas [14] proposed Application of Data Mining Technique in the prediction of Heart Attacks. The author
have studied classification based data mining techniques such as Rule based, Decision tree, Naive Bayes and
Artificial Neural Network to the massive Volume of healthcare data. Tanagra data mining tool was used for
examining data analysis, machine learning and statistical learning algorithms. They have used the training data set
of 3000 instances with fourteen different attributes. The instances in the dataset are representing the outcome of
different types of testing to predict the accuracy of heart disease.

Sudha et al. [15] studied the classification algorithm like Naive Bayes, Decision tree and Neural Network for
detecting the stroke diseases. The classification technique like decision trees, Bayesian classifier and back
propagation neural network were used in this study. The records with unrelated data were deleted from data
warehouse before mining process occurs.

Dr. D. P. Shukla et. al. [16] performed a work of, designing a system which could recognize the probability of a
coronary heart disease. He has separated all parameters into two levels based on the criticality of the parameter and
assigned each level a separate weight age. Finally both the levels are ta ken into consideration to take a final
decision. The author has proposed neuro-fuzzy integrated approach at two levels. In this the error rate is very low
and work efficiency is high. The author have made conclusion that this same method could be used to perform the
analysis on some other diseases also.

3. CONCLUSIONS
In this survey paper we have studied the various exiting technique for predicting heart disease with the
support of data mining. From this survey we got the knowledge about how to apply data mining technique to predict
the heart disease. Previously exiting system was design mostly with single algorithm which is not providing good
accuracy, from some researchers work we have observed that by hybridization of two or more algorithm we can
acquire more accuracy.

4. ACKNOWLEDGEMENT
It gives me an immense pleasure to express my sincere and heartiest gratitude towards my guide
Dr.B.L.Gunjal for her guidance, encouragement, moral support and affection during the course of my work. I am
also thankful to all who have contributed indirectly and materially in words and deeds for completion of this work.

5. REFERENCES

[1]. Ankita Dewan, Meghna Sharma,” Prediction of Heart Disease Using a Hybrid Technique in Data Mining
Classification”, 2nd International Conference on Computing for Sustainable Global Development IEEE 2015 pp
704-706.
[2]. R. Alizadehsani, J. Habibi, B. Bahadorian, H. Mashayekhi, A. Ghandeharioun, R. Boghrati, et al., "Diagnosis
of coronary arteries stenosis using data mining," J Med Signals Sens, vol. 2, pp. 153-9, Jul 2012.
[3]. Carlos Ordonez, Edward Omincenski and Levien de Braal ,“Mining Constraint Association Rules to Predict
Heart Disease”, Proceeding of 2001, IEEE International Conference of Data Mining, IEEE Computer Society,
ISBN-0-7695-1119-8, 2001, pp: 433-440.
[4]. Deepika. N, “Association Rule for Classification of Heart Attack patients ”, IJAEST, Vol 11(2), pp 253-257,
2011.
[5]. Usha. K Dr, “Analysis of Heart Disease Dataset using neural network approach”, IJDKP, Vol 1(5), Sep 2011.
[6]. R. Setthukkarase, Kannan, “An Intelligent System for mining Temporal rules in Clinical database using Fuzzy
neural network”,European Journal of Scientific Research, ISSN 1450-216, Vol 70(3), pp 386-395, 2012.
[7]. M Akhil Jabbar, BL Deekshatulu, Priti Chandra,” Heart disease classification using nearest neighbor classifier
with feature subset selection”, Anale. Seria Informatica, 11, 2013.
[8]. Chaitrali S Dangare, Sulabha S Apte.” Improved study of heart disease prediction system using data mining
classification techniques ”, International Journal of Computer Applications, 47(10):44–48, 2012.
[9]. Shadab Adam Pattekari and Asma Parveen,” PREDICTION SYSTEM FOR HEART DISEASE USING
NAIVE BAYES”, International Journal of Advanced Computer and Mathematical Sciences ISSN 2230-9624,
Vol 3, Issue 3, 2012, pp 290-294.

1844 www.ijariie.com 859

Vol-2 Issue-2 2016 IJARIIE-ISSN (O)-2395-4396

[10]. R. Bhuvaneswari and K. Kalaiselvi, “Naïve Bayesian Classification Approach in Healthcare Applications”,
International Journal of computer Science and Telecommunication”, vol. 3, no. 1, pp. 106-112, Jan
2012.
[11]. Nilakshi P. Waghulde, Nilima P. Patil,”Genetic Neural Approach for Heart Disease Prediction”,
International Journal of Advanced Computer Research (ISSN (print): 2249-7277 ,Vol 4 Number-3 Issue-
Sept 2014.
[12]. C. Ordonez, “Association rule discovery with the train and test approach for heart disease
prediction.,” IEEE transactions on information technology in biomedicine : a publication of the IEEE
Engineering in Medicine and Biology Society, vol. 10, no. 2, pp. 334–43, Apr. 2006.
[13]. P. Chandra, M. Jabbar, and B. Deekshatulu, “Prediction of Risk Score for Heart Disease using
Associative Classification and Hybrid Feature Subset Selection,” in 12th International Conference on
Intelligent Systems Design and Applications (ISDA), 2012, pp. 628–634.
[14]. Srinivas K, Rani KB, Govrdhan A.,” Application of data mining techniques in healthcare and
prediction of heart attacks”, International Journal on Computer Science and Engineering. 2011,2(2):2505.
[15]. Sudha A, Gayathiri P, Jaisankar N,” Effective analysis and predictive model of stroke disease using
classification methods”, International Journal of Computer Applications. 2012; 43(14):26–31.
[16]. Ashish Kumar Sen, Shamsher Bahadur Patel, Dr. D. P. Shukla, “A Data Mining Technique for
Prediction of Coronary Heart Disease Using Neuro-Fuzzy Integrated Approach Two Level”,
International Journal Of Engineering And Computer Science ISSN:2319 -7242 Volume 2 Issue 9 Sept.,
2013 Page No. 2663-2671.

Miss Shubhada B. Bhalerao Perusing masters in Computer

Engineering at AVCOE, Sangamner. She has received his
Bachelors in Computer Engineering from Cummins college of
Engineering, Pune. She is a member of Association of
Computer Machinery (ACM).

Dr. B. L. Gunjal is Associate Professor

in Amrutvahini College of Engineering,
Sangamner. Received PhD degree from
University of Pune. Her Research interests
Includes Image Processing, Data Mining.
She is having 18 Years teaching experience
In Computer Engineering. She is
Having 25 international and national journals.
And conferences publications. She is
Awarded as”BEST TEACHER” by SPPU.

1844 www.ijariie.com 860