Survey on data mining techniques in heart disease prediction

INTERNATIONAL CONFERENCE ON INFORMATION COMMUNICATION AND EMBEDDED SYSTEMS ICICES 2013
978-1-4673-5788-3/13/$31.00©2013IEEE
7
An Empirical Study on applying Data Mining
Techniques for the Analysis and Prediction
of Heart Disease
Sivagowry .S#1, Dr. Durairaj. M*2 and Persia.A#3
#Research Scholar, School of Computer Science and Engg.
Bharathidasan University, Trichy, Tamilnadu, India.
*Assistant Professor, School of Computer Science and Engg.
Bharathidasan University, Trichy, Tamilnadu, India
Abstract— The health care environment is found to be rich in
information, but poor in extracting knowledge from the
information. This is because of the lack of effective analysis tool
to discover hidden relationships and trends in them. By applying
the data mining techniques, valuable knowledge can be extracted
from the health care system. Heart disease is a group of condition
affecting the structure and functions of heart and has many root
causes. Heart disease is the leading cause of death in the world
over past ten years. Researches have been made with many
hybrid techniques for diagnosing heart disease. This paper deals
with an overall review of application of data mining in heart
disease prediction.
Index Terms— Data Mining, Decision Tree, Naïve Bayes,
Classification, Clustering.
I. INTRODUCTION
Data Mining is the exploration of large datasets to extract
hidden and previously unknown patterns, relationships and
knowledge that are difficult to detect with traditional statistics
[17]. Data mining techniques are the result of a long process
of research and product development. Data Mining is divided
into two tasks such as Predictive Tasks and Descriptive Tasks.
Predictive Tasks predict the value of a specific attribute based
on other attribute. Classification, Regression and Deviation
Deduction come under Predictive Tasks. Descriptive Tasks
derive pattern that summarize the relationship between data.
Clustering, Association Rule Mining and Sequential Pattern
Discovery are coming under Descriptive Tasks.Data Mining
involves few steps from raw data collection to some form of
new knowledge. The iterative process consists of following
steps like Data cleaning, Data Integration, Data Selection,
Data transformation, Data Mining, Pattern Evaluation, and
Knowledge the core for Knowledge Discovery Process
Figure 1: Data Mining is the core of Knowledge Discovery Process
Medical Data Mining is a domain of challenge which involves
lot of imprecision and uncertainty. Provision of quality
services at affordable cost is the major challenge faced in the
health care organization. Poor clinical decision may lead to
disastrous consequences. Health care data is massive. Clinical
decisions are often made based on doctor’s experience rather
than on the knowledge rich data hidden in the data base. This
in some cases will result in errors, excessive medical cost
which affects the quality of service to the patients [33].
Medical history data comprises of a number of tests essentials
to diagnose a particular disease. It is possible to gain the
advantage of Data mining in health care by employing it as an
intelligent diagnostic tool. The researchers in the medical field
identify and predict the disease with the aid of Data mining
techniques [29].
II. HEART DISEASE
The initial diagnosis of a heart attack is made by a
combination of clinical symptoms and characteristic
electrocardiogram (ECG) changes. An ECG is a recording of
the electrical activity of the heart. Confirmation of a heart
attack can only be made hours later through detection of
elevated creatinine phosphokinase (CPK) in the blood. CPK is
a muscle protein enzyme which is released into the blood
circulation by dying heart muscles when their surrounding
dissolves [3].
World Health Organization in the year 2003 reported that
29.2% of total global deaths are due to Cardio Vascular
Disease (CVD). By the end of this year, CVD is expected to
be the leading cause for deaths in developing countries due to
change in life style, work culture and food habits. Hence,
more careful and efficient methods of cardiac diseases and
periodic examination are of high importance [1].
III. DATA SETS
The Data set is taken from Data mining repository of
University of California, Irvine (UCI). Data set from
Cleveland data set, Hungary Data set, Switzerland Data set,
long beach and Statlog data set are collected. Cleveland,
Hungary, Switzerland and va long beach data set contains 76
attributes in all. But only 14 attributes are used. Among all
those Cleveland data set and Statlog data set are the most

978-1-4673-5788-3/13/$31.00©2013IEEE
2
commonly used data set. Because all the other has missing
values. The Figure 2 shows some sample of data set collected
from the UCI repository.
Figure 2: Sample Data Set
Attributes Used
No Name Description
1 Age Age in Years
2 Sex 1=male, 0=female
3 cp Chest pain type(1 =
typical angina, 2
=atypical angina, 3 =
non-anginal pain, 4 =
asymptomatic)
4 trestbps Resting blood sugar(in
mm Hg on admission
to hospital)
5 chol Serum cholesterol in
mg/dl
6 fbs Fasting blood
sugar>120 mg/dl(1=
true, 0=false)
7 restecg Resting
electrocardiographic
results(0 = normal, 1 =
having ST-T wave
abnormality, 2 = left
ventricular
hypertrophy)
8 thalach Maximum heart rate
9 exang Exercise induced
angina
10 oldpeak ST depression induced
by exercise relative to
rest
11 slope Slope of the peak
exercise ST segment
(1=upsloping, 2=flat,
3= downsloping)
12 Ca Number of major
vessels colored by
fluoroscopy
13 thal 3= normal, 6=fixed
defect, 7= reversible
defect
14 num Class(0=healthy,
1=have heart disease)
IV. DATA MINING TECHNIQUES USED IN HEART
DISEASE PREDICTION
Data mining techniques such as clustering, Classification,
Regression and Association Rule mining are used in
extracting knowledge from database. Medical data are mined
by using the techniques above and the diagnosis of disease is
carried out. Application of Data mining technique in medical
data is as explained below:
Data Mining and Association Rules
An Association Rule is an implication expression of the form
;ҏҏY, where X and Y are disjoint sets (i.e) XŀY = Ø. The
strength of Association Rule can be measured in terms of
support and confidence. Support determines how often a rule
is applicable to a given data set. Confidence determines how
frequently the item set is used.
Support (XҏҏY) = P (XŀY)
Confidence (XҏҏY) = P (XŀY)/P(X).
Minimum support and minimum confidence are the two
thresh hold in Association Rule mining. Association Rule
Mining is divided into two tasks like frequent item set
generation and Rule generation.
Carlos Ordonez and et al.,[7] used Association rules to
predict the heart disease. They used a simple mapping
algorithm. This algorithm uniformly treats attributes as
numerical or categorical. This is used to transform medical
records to a transaction format. An improved algorithm is
used to mine the constrained association rules. A mapping
table is constructed and attribute values are mapped to items.
The Decision tree is found incapable in mining data because
they automatically split numerical values [7]. But in medical
fields the standard cutoffs are in the numerical format only.
The split point chosen by the Decision tree are of little use
only. And interpreting the experimental results using Decision
tree is very difficult. Clustering was useful to have a global
understanding of data. A constrained version of clustering
focusing on projection of data could be useful, but it deserves
further research. So all these factors justify the use of
Association Rule in mining medical data.
Deepika [11] have used Pruning-Classification Association
Rule (PCAR), for mining Association Rule.
PCAR comes from analyzing and considering of Apriori
algorithm. PCAR deletes minimum frequency item with
minimum frequency item sets. It deletes infrequent item from
item sets. Then classifies item sets based on frequency of item
sets and discovers frequent item sets. The below Figure 3
shows how the PCAR algorithm works [11].

978-1-4673-5788-3/13/$31.00©2013IEEE
3
Figure 3: Procedure of PCAR Algorithm
B. Data Mining and Classification
Usha Rani [38] has implemented artificial neural network in
heart disease database using feed forward and back
propagation algorithm. The experiment is conducted by
considering single and multilayered neural network models.
Parallelism is implemented at each neuron in all hidden and
output layer to speed up the learning process. 13 neurons are
set for input, each neuron corresponds to each attributes.
Neural network provides satisfactory results for classification
task.
Training
Samples
Test
Samples
Classification
Efficiency
Single
Layer
Multi
Layer
100 300 76% 82%
150 200 79.4% 83%
250 150 86.2% 89.3%
350 100 90.6% 94%
Table 1: Experimental Results of Heart Disease Data set [37]
In Asha Rajkumar [3] , the data mining Classification is
based on supervised machine learning Algorithm. Tangara
tool is used to classify the data and evaluated using 10 fold
cross validation. The performance analysis of Naïve Bayes, K-nn,
Decision List Algorithm is based on accuracy and time
taken to build the model. Naïve bayes algorithm is considered
to be better since it takes only some to calculate the accuracy
than other algorithm. And also it resulted in lower error rates.
Naïve Bayes algorithm gives 52.23% of accurate result. The
below Table 2 shows the performance study of the algorithm.
Table 2: Performance study of the Algorithm [3]
In [24] R. Setthukkarasi,, proposed a novel neuro fuzzy
technique to diagnose the severity of the disease from the set
of the patient records. A generalized database is constructed
for decision making from the reduced attributes set obtained
through genetic algorithm. A four layered fuzzy neural
network for efficient modeling and reasoning with temporal
dependencies under uncertainity is used. A Decision Support
Subsystem is constructed by extracting rules from the
temporal patterns retrieved from the relationship between
trained data set. Radial Basic Function (RBF) neural network
is constructed with five input nodes, training and
normalization in hidden layer and output layer with one output
node. RBF is used to train large amount of data with very few
inputs. Data preprocessing by genetic algorithm, generalized
database generation, Dataset training by RBF fuzzy neural
network, Rule generation, Query processing and Severity
based diagnosis are the steps followed for predicting the heart
disease. The Figure 4 shows the logical view of Rule
generation Process [24].
Figure 4: Logical view of Rule Generation Process
Rafiah Awang and Sellapan Palaniappan [25, 26] developed a
prototype called Intelligent Heart Disease Prediction System
(IHDPS) using data mining technique namely Decision Trees,
Naïve Bayes and Neural Network. Each technique has its own
strength in realizing the objective of data mining. Data Mining
Extension (DMX), a SQL based query language is for
building and accessing the models’ contents. IHDPS answers
complex “what if” queries where decision support system
cannot. The most common modeling objective used in Data
mining is Classification and Prediction. Decision Tree and
Neural network come under Classification and Regression,
Association Rules and Clustering [26] comes under
prediction. Naïve bayes is the most effective in heart disease
prediction as it has the highest percentage of correct
predictions (86.53%). Five Data mining rules are defined and
evaluated using the three techniques namely Decision Trees,
Naïve Bayes and Neural Network.
Anbarasi.M and et Al., [1] has used Genetic Algorithm (GA)
to determine the attributes for the diagnosis of heart disease.
Future extraction is done using GA. Attributes number is
reduced as 6. The Table 3 shows the reduced number of
attributes using GA [1].
Algorithm
used
Accuracy Time
taken
Naïve
Bayes
52.33% 609ms
Decision
List
52% 719ms
KNN 45.67% 1000ms

978-1-4673-5788-3/13/$31.00©2013IEEE
4
Predictable attribute:
Diagnosis
Value Healthy: No heart disease
Value Sick: Has Heart disease
Reduced Input attributes:
1.Type - Chest Pain Type
2.Rbp - Resting blood pressure
3.Eia - Exercise induced angina
4.Oldpk - Old peak
5.Vsl - No. of vessels colored
6.Thal -Maximum heart rate
achieved
Table 3: Reduced Attributes list using GA [1]
Three Classifiers are used for comparing the performance in
predicting the heart disease. The classifiers taken for study are
Naïve Bayes, Classification by Clustering and Decision Tree.
Decision tree outperforms but it takes more time to build the
model. Naïve bayes perform consistently before and after
reduction of attributes. Classification via Clustering is very
poor in its performance. Weka tool is used in evaluation the
performance.
Shantakumar B. Patil and et al.,[30, 31 ] clustered the data
warehouse using K-means clustering algorithm after pre
processing the data. Maximal Frequent Item Set Algorithm
(MAFIA) is employed for the extraction of association rules
from the clustered dataset besides performing efficiently when
the database consists of very long item sets specifically.
Multilayer perception Network (MLPNN) and Back
propagation is used as training algorithm.
Pseudo code for MAFIA [29]:
MAFIA(C, MFI, Boolean IsHUT) {
name HUT = C.head C.tail;
if HUT is in MFI
stop generation of children and return
Count all children, use PEP to trim the tail, and
recorder by increasing support,
For each item i in C, trimmed_tail {
IsHUT = whether i is the first item in the tail
newNode = C I
MAFIA (newNode, MFI, IsHUT)}
if (IsHUT and all extensions are frequent)
Stop search and go back up subtree
If (C is a leaf and C.head is not in MFI)
Add C.head toMFI
}
In Application of Data Mining Techniques in Health Care and
Prediction of Heart Attack [34] One Dependency Augmented
Naïve Bayes Classifier [17] (ODANB) and Naïve Credal
Classifier 2 (NCC2) is used. The objective of this work is to
examine the potential use of Classification based Data Mining
techniques like Naïve Bayes, Rule based, Decision Tree and
Artificial Neural Network. For the prediction of heart disease
Naïve Bayes found to be the best when compared with
ODANB. Text Mining can also be used in future to mine the
vast amount of unstructured data available in health care
databases.
In [35], Subbulakshmi and et al., used Naïve Bayes for
predicting Decision Support in heart disease prediction
System (DSHDPS). It can serve as a training tool for nurses
and medical students in diagnosing the heart disease. Naïve
Bayes is found to be the best in heart disease prediction. It is
used to create models with predictive capability. It provides
new ways of exploring and understanding the data. Naïve
Bayes is used to get efficient output.
Enter
Patient
Record
Naïve
Bayes
Data set
Calculates
probability of each
Calculates yes or no
probability
Tells about
risk
Fig 5: Implementation of Naïve Bayes Algorithm on the patient data [35]
In Naïve Bayesian Classification Approach in Health Care
application, Bhuvaneshwari. R [6] proposed that Naïve Bayes
Classification can be used as a best decision support system.
In [15], Kavitha K.S used hybridization to train neural
network using Genetic Algorithm. In this Feed- forward
neural network and Back propagation is used as a learning
algorithm. Chen A.H [10] used Artificial Neural Network
(ANN) algorithm for classifying the heart disease based on
input. Learning Vector Quantization (LVQ) is a prototype
based supervised Classification Algorithm. Accuracy is 80%,
Sensitivity is 85% and Specificity is 70%. To prove
goodness, ROC Curve is also displayed. The below Figure 6
shows the computational steps of LAV model.
Figure 6: The Computational Steps of LAV Model
In [9] Chaitrali S. Dangare and Sulabha have added 2 more
attributes such as obesity and smoking to the existing 13

978-1-4673-5788-3/13/$31.00©2013IEEE
5
attributes. Decision tree, Naïve Bayes and Artificial Neural
Network has been tested with both 13 and 15 attributes. In
both the case, the neural network showed better performance.
The Figure 7 shows the Graphical Representation of Accuracy
for each method.
Figure 7: Graphical Representation of Accuracy for each method [9]
Clustering, Time Series and Association Rule can also be
used for Data Mining Classification. Text mining can be used
to mine huge amount of unstructured data in future.
In [20], Milan Kumari compares RIPPER, SVM, Decision
Tree and Artificial Neural Network based on Sensitivity,
Specificity, Accuracy, Error Rate, True Positive Rate and
False Positive Rate. SVM predicts with least error rate and
highest accuracy when compared with other techniques [19].
Future work is predicted to done using Meta models. In [23],
Feed forward back propagation neural network is used as a
classifier to distinguish between infected or non-infected
person in both the cases. Neural network tool box from
Matlab 7.9 is used to evaluate the performance of the
proposed network.
Levenburg-Marquardt back propagation algorithm is used to
train the network. Neural network can be used for identifying
the patients suffering Heart disease.
A Novel Approach for Heart Disease diagnosis using Data
Mining and Fuzzy Logic [21] reduces the number of attributes
to reduce the number of tests for the patients. Decision Tree
and Naïve Bayes combined with Fuzzy logic outplayed other
Data Mining techniques in predicting Heart disease. In [32],
Shouman and et. Al., used K-Nearest Neighbor (K-NN) in
classification problem. Integrating voting with K-NN cannot
enhance its accuracy in diagnosing the heart disease. When
voting is applied to Decision Tree, different decision rules are
extracted from each subset, which extract new knowledge
leads to increasing accuracy in Decision Tree. But in K-NN
no new knowledge is extracted, just distance between clusters
in measured. Applying K-NN achieved an accuracy of 97.4%
without voting. But voting in K-NN results in decrease in
accuracy.
C.Data Mining and Clustering
In [4], Bala Sundar and et. al., used K-means Clustering
Algorithm for the prediction of the heart disease. It is a
method of cluster analysis which aims to partition ‘n’
observations to ‘k’ clusters. Euclidaen distance formula is
used to minimize the sum of square of distance between data.
Naïve Bayes is found to slow and Neural Network takes
number of iterations in predicting the disease when compared
using time and accuracy.
Figure 8: Exponential accuracy of k-means with existing techniques
The Figure 8 explains the exponential accuracy of k-means
with existing techniques [4]. Santhi and et. Al., [28] proposes
the performance of clustering and classification algorithm
using heart disease data. Performance of classifiers of Bayes,
functions, Lazy, Metammulti Boost AB, Rules, Trees, etc., are
calculated. The performance of classification is calculated
using cross validation test mode and clusers by mode of
classes to evaluate clusters. Data preprocessing is done by
attribute subset selection algorithm. Final result showed that
Naïve Bayes tress has highest prediction accuracy than
clustering Algorithm.
V. CONCLUSION
Heart disease prediction is a major challenge in the health
care industry. Instead of going for a number of tests,
predicting heart disease with less number of attributes is a
challenging task in Data Mining. Existing literature shows that
Classification task in Data Mining plays a vital role in heart
disease prediction when compared with Clustering,
Association Rule and Regression. In Classification Decision
Tree outperforms in some cases, where Neural Network and
Naïve Bayes outperforms in some other cases. Each technique
has its own merits and demerits. When combined with each
other or with Fuzzy logic, Heart disease prediction with Data
Mining techniques will become most successful with less
number of attributes. Text mining the medical data is another
extension found in predicting the health care data.
REFERENCES
[1] Anbarasi.M, Anupriya and Iyengar “Enhanced Prediction of Heart
Disease with Feature Subset Selection using Genetic Algorithm”,

978-1-4673-5788-3/13/$31.00©2013IEEE
6
International Journal of Engineering and Technology, Vol 2(10), 2010,
pp 5370-5376.
[2] Annoj P.K.,” Clinical decision support system: Risk level prediction of
heart disease using Data Mining Algorithms”, Journal of King Saud
University- Computer and Information Sciences, 2012,pp 27-40.
[3] Asha Rajkumar and Mrs. Sophia Reena, “ Diagnosis of Heart Disease
using Data Mining Algorithms, Global Journal of Computer Science and
Technology, vol. 10(10), 2010, pp 38-43.
[4] Bala Sundar V, “Development of Data Clustering Algorithm for
predicting Heart”, IJCA, Vol 48(7), June 2012, pp 8-13.
[5] Bhagyashree Ambulkar and Vaishali Borkar “Data Mining in Cloud
Computing”, MPGINMC, Recent Trends in Computing, ISSN 0975-
8887,2012, pp 23-26.
[6] Bhuvaneswari. R, “Naïve Bayesian Classification Approach in Health
Care Application”, International Journal of Computer Science and
Telecommunication, vol 3(1), Jan 2012, pp 106-112.
[7] 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.
[8] Cengiz colak.M , Cemiz colak and Hasan Kocatruk “Predicting
coronary artery disease using different artificial neural network
models”, CAD and Artificial neural network, pp 249-254, 2008.
[9] Chaltrali S. Dangare and Sulabha, “Improved Study of Heart Disease
Prediction System using Data Mining Classification Techniques”,
IJCA, Vol 47(10), pp 44-48, June 2012.
[10] Chen A.H., “HDPS: Heart Disease Prediction System”, Computing in
Cardiology, ISSN 0276-6574, pp 557-560, 2011.
[11] Deepika. N, “Association Rule for Classification of Heart Attack
patients”, IJAEST, Vol 11(2), pp 253-257, 2011.
[12] Jabbar M.A., “Knowledge discovery from mining association rules for
Heart disease Prediction”, JATIT, Vol 41(2), pp 166-174, 2012.
[13] Jyothi Soni, Uzma ansari and Dipesh Ansari “Intelligent and Effective
Heart Disease Prediction System using Weighted Associate Classifer”,
IJCSE, Vol 3(6), pp 2385-2392, June 2011.
[14] K.Rajeswari, “Prediction of Risk Score for Heart Disease in India using
Machine Intelligence”,IPCSIT, Vol 4, 2011.
[15] Kavitha K.S, “Modeling and designing of evolutionary neural network
for heart disease prediction”, IJCSI, Vol 7(5), pp 272-283, September
2010.
[16] Latha Parthiban and R.Subramanian, “Intelligent Heart Disease
Prediction System using CANFIS and Genetic Algorithm”,
International Journal of Biological and Life Sciences, Vol 3(3), pp157-
160,2007.
[17] Liangxiao. J, Harry.Z, Zhihua.C and Jiang.S “One Dependency
Augmented Naïve Bayes”, ADMA, pp 186-194, 2005.
[18] Mia Shouman, “Using data mining techniques in heart disease diagnosis
and treatment”, 978-1-4673-0483-2, Japan-Egypt Conference on
Electronics, Communications and Computers, pp 189-193, 2012.
[19] Milan Kumari and Sunila Godara, “Review of Data Mining
Classification Model in Cardio Vascular Disease diagnosis”, IJCA,
2011.
[20] Milan Kumari and Sunila Godara, “Comparative Study of Data Mining
Classification Methods in Cardio-Vascular Disease Prediction”, IJCST,
Vol 2(2), June 2011.
[21] Nidhi Bhatia and Kiran Jyothi, “A Novel Approach for heart disease
diagnosis using Data Mining and Fuzzy logic”, IJCA, Vol 54(17), pp
16-21, September 2012.
[22] Nithya N.S, Sarumathi. S and Dr. Duraisamy. K “ Assessment of the
risk factors of Heart Attack using frequent feature Selection Method”,
International Journal of Communications and Enggineering, Vol 1(1),
ISSN 0988-0382, pp 127-133, March 2012.
[23] Qeethara Kadhim Al. Shayea, “Artificial neural network in Medical
Diagnosis”, IJCSI, Vol 3(2), March 2011.
[24] R. Setthukkarase and 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.
[25] Rafiah Awang and Palaniappan. S “Intelligent Heart Disease Prediction
System Using Data Mining techniques”, IJCSNS, Vol 8(8), pp 343-350,
Aug 2008.
[26] Rafiah Awang and Palaniappan. S “Web based Heart Disease Decision
Support System using Data Mining Classification Modeling techniques”
, Proceedings of iiWAS, pp 177-187, 2007.
[27] Raghu. D.Dr, “Probability Based Heart Disease Prediction using Data
Mining Techniques”, IJCST, Vol 2(4), pp 66-68, Dec 2011.
[28] Santhi. P, “Improving the performance of Data Mining Algorithm in
Health Care data”, IJCST, Vol 2(3), 2011.
[29] Setiawan N.A, “ Rule Selection for Coronary Artery Disease Diagnosis
Based on Rough Set” ,International Journal of Recent Trends in
Engineering, Vol 2(5), pp 198-202, Dec 2009.
[30] Shantakumar B.Patil, “Intelligent and Effective Heart Attack Prediction
System using Data Mining and Artifical Neural Network”, European
Journal of Scientific Research, Vol 31(4), pp 642-656, 2009.
[31] Shanthakumar B. Patil, “Extraction of Significant patterns from Heart
Disease Ware Houses for Heart Attack Prediction”, IJCSNS, Vol 9(2),
pp 228-235, Feb 2009.
[32] Shouman.M, Turner.T and Stocker.R, “Applying K-Nearest Neighbour
in diagnosing Heart Disease Patients”, International Journal of
Information and Education Technology, Vol 2(3), June 2012.
[33] Siri Krishnan Wasan, Vasutha Bhatnagar and Harleen Kaur “The Impact
of Data Mining techniques on medical diagnostics”, Data Science
Journal, Vol 5(19), pp 119-126, October 2006.
[34] Srinivas, Kavitha Rani and Dr. Govarthan, “Application of Data Mining
Techniques in Health Care and Prediction of Heart Attack”, IJCSE, Vol
2(2), pp 250-255, 2010.
[35] Subbulakshmi, Ramesh and Chinna Rao “Decision Support in Heart
Disease Prediction System using Naïve Bayes”, IJCSE, ISSN 0976-
5166, Vol 2(2), May 2011.
[36] Sudha.A, Gayathri.p and Jaishankar. N “Utilization of Data Mining
Approaches for prediction of life Threatening Disease Survivability”,
IJAC (0975-8887), Vol 14(17), March 2012.
[37] Jyothi. S, Ujma.A, Dipesh. S and Sunita. S “Predictive Data Mining for
Medical Diagnosis : An Overview of Heart Disease Prediction”, IJCA,
Vol 17(8), pp 43-48, March 2011.
[38] Usha. K Dr, “Analysis of Heart Disease Dataset using Neural network
approach”, IJDKP, Vol 1(5), Sep 2011.

Survey on data mining techniques in heart disease prediction

More Related Content

What's hot (20)

Viewers also liked (15)

Similar to Survey on data mining techniques in heart disease prediction (20)

Recently uploaded (20)

Survey on data mining techniques in heart disease prediction