International Journal of Computer Trends and Technology (IJCTT) volume 4 Issue 6June 2013

ISSN: 2231-2803 http://www.ijcttjournal.org Page 1609

A Soft Computing Approach for Heart
Disease Analysis

Nitika Dahiya
#1
, Madan Lal Yadav
#2


*
Department of CSE, ASET, Amity University, Uttar Pradesh, Noida,India



Abstract :The aim of this study is to define a fuzzy based
prediction system, that will accept the patient basic
information as well as the symptoms as input and
identify the chances of heart disease. The fuzzy based
system is defined on multiple parameters based on which
the patient disease analysis can be performed. The
parameters taken in this work are Patient Age, Blood
Pressure, Cholesterol Level and the Heart Beat. At the
initial stage, as user input these parameters, the fuzzy
interference engine process on it and identify the fuzzy
values from the system. These fuzzified parametric
information is maintained in the database. The
fuzzification process is here presented in the form of
fuzzy diagrams also. Once the patient fuzzified
information is maintained in the database, patient or the
Doctor can perform a query to identify the patients at
different criticality level. For this, we have designed a
user friendly input environment where a fuzzy query can
be performed by specifying the parameter and the
criticality level of the parameter. We have also defined
the fuzzy engine by performing the different fuzzy
operators while working with these all parameters.

Keywords Fuzzy System, Heart Disease, Operator, Dataset,
Data Mining, Prediction based.

I INTRODUCTION

The prediction based systems are always the
major challenge for the data mining approaches, where the
current data analysis is been used to identify the future
aspects. This challenge becomes more critical when we
talk about the medical disease prediction and the analysis.
The medical field is one of the major research area for the
data mining but itself it is critical because it required some
expert concern[1].
The involvement of the data mining approaches in the
health care industry cannot be imagine. There are number
of health care organization, medical industries that uses
these mining approaches and the analysis to derive the
effective results. There are number of trends and the
patterns to work on medical data to analyze the patient

situation as well as the disease and the diagnose
prediction[4,6].
The influence of data mining on the quality of Health Care
cannot be understated. All Health Care organizations
retain detailed and comprehensive records of patient data.
Trends and patterns identified in these records can
positively impact the quality of Health Care. The huge
amounts of patient data makes identification of these
trends a difficult task. The data mining applications built
for this purpose can make this very simple and produce
efficient results.
There have been several cases, where application
of data mining techniques have helped in resolving a
problem in the health industry. For instance, data mining
on pneumonia patient records in a hospital, showed that
patients who were administered medication immediately
on arrival responded better than patients who were not
administered medication on arrival. In order to arrive at
this conclusion the data mining application, used several
inputs, such as the tests and other information of the
patients who showed better medication results. Various
relations were drawn between the inputs. One of these was
the relation between the results and the time taken to
administer medication after arrival. It was found that,
shorter the time taken, better the result will be[10,11].
There were several other key issues that were
addressed at this time. The data mining tests proved that
several tests, which were largely extraneous, were
conducted on the patients. These led to a delay in the
administration of medication and thereby affected the
recovery of the patient. To overcome this, a standardized
plan was created to treat pneumonia patients. The
identification of these associations between inputs and
finding the resultant best outcome was possible only
because of data mining techniques.

II. LITERATURE SURVEY

N. Aditya Sundar accomplished a work, Performance
analysis of classification data mining techniques over heart
disease database . This paper describes about a prototype
using data mining techniques, namely Nave Bayes and
WAC (weighted associative classifier).This system can
answer complex what if queries which traditional
International Journal of Computer Trends and Technology (IJCTT) volume 4 Issue 6June 2013

ISSN: 2231-2803 http://www.ijcttjournal.org Page 1610

decision support systems cannot.. Presently authors are
analyzing the performances of the two classification data
mining techniques by using various performance
measures. Chen performed a work, HDPS: Heart Disease
Prediction System. Author develop a heart disease predict
system that can assist medical professionals in predicting
heart disease status based on the clinical data of patients.
Presented approaches include three steps. Firstly, Author
select 13 important clinical features, i.e., age, sex, chest
pain type, trestbps, cholesterol, fasting blood sugar, resting
ecg, max heart rate, exercise induced angina, old peak,
slope, number of vessels colored, and thal. Secondly,
author develops an artificial neural network algorithm for
classifying heart disease based on these clinical features.
Mrs.G.Subbalakshmi performed a work, Decision
Support in Heart Disease Prediction System using Naive
Bayes. This research has developed a Decision Support in
Heart Disease Prediction System (DSHDPS) using data
mining modeling technique, namely, Nave Bayes. Using
medical profiles such as age, sex, blood pressure and
blood sugar it can predict the likelihood of patients getting
a heart disease. It is implemented as web based
questionnaire application. It can serve a training tool to
train nurses and medical students to diagnose patients with
heart disease. E. Barati performed a work, A Survey on
Utilization of Data Mining Approaches for Dermatological
(Skin) Diseases Prediction. This paper is intended to
introduce data mining and its various techniques and a
survey of the available literature on medical data mining.
Author emphasize mainly on the application of data
mining on skin diseases. In this paper, Author have
summarized the different uses of classification in
dermatology. It is one of the most important methods for
diagnosis of erythemato-squamous diseases.Milan Kumari
performed a work, Comparative Study of Data Mining
Classification Methods in Cardiovascular Disease
Prediction. In this research paper data mining
classification techniques RIPPER classifier, Decision
Tree, Artificial neural networks (ANNs), and Support
Vector Machine (SVM) are analyzed on cardiovascular
disease dataset. Performance of these techniques is
compared through sensitivity, specificity, accuracy, error
rate, True Positive Rate and False Positive Rate. J yoti Soni
performed a work, Predictive Data Mining for Medical
Diagnosis: An Overview of Heart Disease Prediction.
This research paper intends to provide a survey of current
techniques of knowledge discovery in databases using data
mining techniques that are in use in todays medical
research particularly in Heart Disease Prediction. Number
of experiment has been conducted to compare the
performance of predictive data mining technique on the
same dataset and the outcome reveals that Decision Tree
outperforms. Mr. Dhiraj Pandey performed a work,
Prediction system to support medical information system
using data mining approach. In the proposed approach an
extendable and improved item set generation has been
constructed, and developed, for mining the relationships of
the symptoms and disorder in the medical databases. It
will produce hybrid dimension association rules and the
rules have been displayed in form of tables and graphs.

III. METHOD


Medical diagnostic related expert system is always one of
the favorite research area for many researcher. Lot of work
has already been done in this field. Each work has its
significance in itself. But still No work is perfect in such
expert system. There are no. of disease with lot of
symptoms and the diagnosis of these problems. Each
disease, symptom , diagnosis is itself a research area.
Many researchers have already done lot of work with
diseases that can be identified by the human normal
behavior or the daily habits. Some such disease include
lung problems, cancer etc. There are no. of approaches
being used with such problems like neural network fuzzy
approach etc. We are presenting our work for the heart
disease and we are providing the risk estimation using
Fuzzy algorithm,
Health care organizations store huge amounts of
data in the form of patient databases. Trends in these
databases can be identified using data mining practices,
which sort and model the data in order to arrive at a
conclusion. The data mining applications present the data
in the form of data marts. This allows end users to choose
the specific sets of data, which they want to be analyzed.
The data in these data marts can then be presented using a
graphical user interface, arranging the data into columns
and rows. In the Health care industry, however, the lack
of standard clinical vocabulary has hindered the process of
data mining to a certain extent. For example a simple term
such as hypertension can be expressed in various ways in
health care. This could lead to unnecessary problems,
during the process of data mining. The increase in the use
of standardized terms will reduce the percentage of errors
in the data mining process.
Cleaning the data before it can be mined is also an
important step in the data mining process. In many Health
care organizations, the mode of preparing patient reports
can lead to a good deal of confusion. For instance, in a
certain hospital, a report was prepared, before and after a
patient went in for an X-ray check. This could be
construed as two different reports, when analyzing the data
and produce erroneous results. Further in certain
organizations, in order to reduce the number of reports, a
patients record contains only the name of the attending
physician and not the names of other physicians consulted
or tests performed at a later stage, leading to erroneous
predictions.
International Journal of Computer Trends and Technology (IJCTT) volume 4 Issue 6June 2013

ISSN: 2231-2803 http://www.ijcttjournal.org Page 1611

The data mining effort thus requires the
wholehearted participation of all health care personal to
produce comprehensive and correct reports, which can be
mined. Further, the number of input variables for the data
mining application has to be determined correctly. The
number of inputs should not be so large, that it produces
not be limited to such an extent, that they produce biased
results. Co-operation between the physicians and analysts
is also recommended, since some of the results might be
more easily understood by the health care personal.
A medical diagnostic system cannot be implemented
without an expert personal. In this present we have defined
a medical application to identify the person heart disease
or the chances of heart disease. For this heart disease
analysis we have used one of the major soft computing
technique called fuzzy logic. The fuzzy logic is one of the
intelligent scheme to deal with uncertainty. The fuzzy
logic takes the intelligent decision based on the
characteristics of current population set. The fuzzy rule is
implemented on the physical characteristics of a person.

A. Dataset

The dataset of the patients are collected from a Heart
Hospital. The dataset is maintained in paper files which is
then converted into MS Access database .The four
parameters of the patients are considered for the research
and analysis-Age, Cholesterol Level , Blood Pressure and
Heart Beat.
In this study, we use low density lipoprotein cholesterol
and systolic blood pressure.
We consider a set of m diseases D, and define a collective
set of n features F relevant to these diseases. Usually we
have n>>m. Let:
D ={d
1
, d
2
, d
3
, , d
m
}
F ={f
1
, f
2
, f
3
, , f
n
}
To specify the symptoms of a patient, he would be
checked against all features in the set F and a value would
be assigned to each feature. The values are selected from
the set:
{ Very Low, Low, Moderate, High, Very High }
For example, a single symptom can be specified as <
runny nose, Moderate >. By checking the patient for all n
features of the set F and assigning a proper value for each
feature, the set of patients symptoms S will be obtained as
follows:
S ={ <f
1
, v
1
>, <f
2
, v
2
>, <f
3
, v
3
>, , <f
n
, v
n
> }
where: v
i
is the value assigned to the feature f
i
when
checking the patient, i=1, ,n.
B. Parameters

1) Blood Pressure: It is the major factor that can predict
the chances of heart disease. Generally a heart patient have
the higher blood pressure. According to the fuzzy rule set
we have divided the patient blood pressure in four major
categories called Very High, High, Normal and
Low. If the blood pressure is greater than 172, it is
considered very high. If the blood pressure is between 154
and 172 it is considered high blood pressure. If it is
between 127 and 154 then it is considered medium
otherwise it is considered Low.



Fig1.Blood Pressure Fuzzy Analysis


2) Cholesterol: Cholesterol is another major factor that can
increase the chances of heart disease in a patient. Higher
the Cholesterol value more chances of heart disease.
According to the study we have divided the cholesterol
level in a patient in four major categories called Very
High, High, Normal and Low. If the cholesterol
level is greater than 307, it is considered very high. If
cholesterol level is between 217 and 307 it is considered
high blood pressure. If it is between 188 and 250 then it is
considered medium otherwise it is considered Low.



International Journal of Computer Trends and Technology (IJCTT) volume 4 Issue 6June 2013

ISSN: 2231-2803 http://www.ijcttjournal.org Page 1612

Fig 2.Cholesterol Level Fuzzy Analysis

3) Heart Beat: Heart beat is another major factor that can
increase the chances of heart disease in a patient. Higher
the Heart Beat value more chances of heart disease.
According to the study we have divided the Heart Beat
level in a patient in three major categories called High,
Normal and Low. If the Heart Beat Level is greater
than 194, it is considered high. If Heart Beat level is
between 141 and 194 it is considered Average Heart Beat
otherwise it is considered Low.




Fig 3.Heart Beat Fuzzy Analysis


4) Age: Age is another major factor that predict the
chances of heart disease in a patient.. According to the
study we have divided the Age of a patient in four major
categories called Young, Middle, Old and Very
Old. If the Age is greater than 52, it is considered Very
Old. If the age is between 40 and 52, it is considered Old,
between 33 and 45 is middle otherwise it is considered
Young.



Fig 4.Age Fuzzy Analysis

C. Fuzzy Without Operators

Fuzzy logic is an approach to computing based on
"degrees of truth" rather than the usual "true or false" (1 or
0) Boolean logic on which the modern computer is based.
Fuzzy logic includes 0 and 1 as extreme cases of truth but
also includes the various states of truth in between,
example, A cup of coffee is not exact Hot or Cold but
.48 of coldness.
In Fuzzy Without Operators two queries are considered
a)Fuzzy Query
Select * from patientinfo where Age is Nominal
Young,BloodPressure is Nominal Low, Cholesterol is
Nominal Low, Heartbeat is Nominal Low

b)SQL Query
Select * from patientinfo where agey>=0 and agey<=.3
and blow>=0 and blow<=.3 and clow>=0 and clow<=.3
and hlow>=0 and hlow<=.3

The fuzzy query is here performed on different attributes
including age, blood pressure, cholesterol level and heart
beat. The input is also taken in the form of accepted fuzzy
values and the criticality level of these values. Based on
this fuzzy query, the defuzzification is here performed and
relatively records are accessed from the database and
presented in the form of table.


Fig 5.Fuzzy Without Operators

International Journal of Computer Trends and Technology (IJCTT) volume 4 Issue 6June 2013

ISSN: 2231-2803 http://www.ijcttjournal.org Page 1613


Fig 6.Age Membership Function

Here figure 5 is showing two queries and figure 6 is
showing the age data retrieved on the basis of query.

D. Fuzzy With Operators

a)Union (logical OR)-The membership of an element in
the union of two fuzzy sets is the larger of the
memberships in these sets.
(A OR B)=max ((A), (B))
e.g., (tall OR small) =max ((tall), (small))

b)Intersection (logical AND)-The membership of an element
in the intersection of two fuzzy sets is the small of the
memberships in these sets.
(A AND B) =min ((A), (B))
e.g., (tall AND small) =min ((tall), (small))



User can select the input values for different attributes as
well as the criticality of these values is defined. Along
with these, all attributes are combined in query by using
set of fuzzy operators. As the user input is submitted, a
respective fuzzy query and based on which a defuzzified
SQL query is generated and shown in the text box.


Fig 7.Fuzzy with operators

E. Prediction Value

In the end Prediction Value is found which gives the
criticality of disease in patient. A final decision is also
taken for each patient. The decision can be Very Low,
Low, Medium, High, Very High.
To find the prediction value mean-maxima technique has
been used. The numerical value is the mean of the
numerical values corresponding to the degree of
membership at which the membership function is scaled.







International Journal of Computer Trends and Technology (IJCTT) volume 4 Issue 6June 2013

ISSN: 2231-2803 http://www.ijcttjournal.org Page 1614


Fig 8. Decision And Prediction Value


IV. CONCLUSION
Clinical medicine is one of the most interesting areas in
which data mining may have an important practical
impact. The widespread availability of large clinical data
collections enables thorough retrospective analysis, which
may give healthcare institutions an unprecedented
opportunity to better understand the nature and peculiarity
of the undergoing clinical processes. The present work is
the analysis on the patient symptom information based on
which a pre-level decision is taken to identify the chances
of a heart disease. The work is under the intelligent system
that can be adapted by a doctor. In this work we have
taken a parameter based fuzzification that will perform the
analysis based on some parameters.

REFERENCES
[1] N. Aditya Sundar, Performance analysis of classification data
mining techniques over heart disease database, [IJESAT]
International J ournal of engineering science & advanced
technology ISSN: 22503676
[2] AH Chen, HDPS: Heart Disease Prediction System,
Computing in Cardiology 2011;38:557-560, ISSN 0276-6574
[3] Mrs.G.Subbalakshmi, Decision Support in Heart Disease
Prediction System using Naive Bayes, Indian J ournal of
Computer Science and Engineering (IJ CSE), ISSN 0976-5166
Vol. 2 No. 2 Apr-May 2011 170-174
[4] E. Barati,A Survey on Utilization of Data Mining Approaches
for Dermatological (Skin) Diseases Prediction, J ournals in
Science and Technology, J ournal of Selected Areas in Health
Informatics (J SHI) March Edition, 2011
[5] Milan Kumari, Comparative Study of Data Mining
Classification Methods in Cardiovascular Disease Prediction,
IJ CST ISSN : 2229-4333 (Print)|ISSN:0976-8 491
[6] J yoti Soni, Predictive Data Mining for Medical Diagnosis: An
Overview of Heart Disease Prediction, International J ournal of
Computer Applications (0975 8887)
[7] Mr. Dhiraj Pandey, Prediction system to support medical
information systemusing data mining approach, International
J ournal of Engineering Research and Applications (IJ ERA)
ISSN: 2248-9622
[8] J yoti Soni, Intelligent and Effective Heart Disease Prediction
System using Weighted Associative Classifiers, International
J ournal of Computer Applications (0975 8887) Volume 17
No.8, March 2011
[9] Dr. D. Raghu, Probability based Heart Disease Prediction using
Data Mining Techniques, IJCST ISSN : 0976-8491 (Online) |
ISSN : 2229-4333(Print)
[10] Shantakumar B.Patil, Intelligent and Effective Heart Attack
Prediction SystemUsing Data Mining and Artificial Neural
Network, European J ournal of Scientific Research ISSN :
0975-3397 Vol. 3 No. 6 J une 2011 2385
[11] M.A.J abbar, Knowledge discovery frommining association
rules for heart disease prediction, J ournal of Theoretical and
Applied Technology ISSN: 1992-8645 E-ISSN: 1817- 3195,
2005
[12] T Srinivasan, Knowledge Discovery in Clinical Databases with
Neural Network for Evidence.

[13] Sellappan Palaniappan, Intelligent Heart Disease Prediction
SystemUsing Data Mining Techniques, IJ CSNS International
J ournal of Computer Science and Network Security, VOL.8
No.8, August 2008
[14] K. Rajeswari, Prediction of Risk Score for Heart Disease in
India Using Machine Intelligence, 2011 International
Conference on Information and Network Technology IACSIT
Press, Singapore IPCSIT vol.4 (2011) (2011)
[15] K.Srinivas, Mining Association Rules from Large Datasets
Towards Disease Prediction, 2012 International Conference on
Information and Computer Networks (ICICN 2012) IPCSIT
[16] V.V.J aya Rama krishniah, Predicting the Heart Attack
Symptoms using Biomedical Data Mining Techniques, The
International J ournal of Computer Science & Applications
(TIJ CSA) Volume 1, No. 3, May 2012 ISSN 2278-1080