1. HEART ATTACK PREDICTION
SYSTEM
BY
K.KANNAN
K.SASIDHARAN
B.V.SASIDHAR
S.DHIRAJ
1

2. ABSTRACT
• Cardiovascular disease is one of the most fatal
conditions in the present world.
• Statistical data display the lethalness of
Cardiovascular disease by revealing the
percentage of deaths worldwide caused due
to heart attacks.
• Thus, there is an implicit necessity to predict
the condition at the earliest.
2

3. ABSTRACT
• By utilizing the patients medical records ,a new
system is proposed to predict the chances of a
person contracting heart attack.
• Attributes such as age, blood pressure, thickness
of the artery etc. are fed into the fuzzy c means
algorithm which is used to predict risk of heart
attack in a person.
• FCM is a clustering algorithm which allows one
piece of data to belong to multiple clusters.
3

4. LITERATURE SURVEY
• [1]The healthcare industry collects huge amounts of
healthcare data which, unfortunately, are not ";mined"; to discover hidden
information for effective decision making. Discovery of hidden patterns
and relationships often goes unexploited
• [2]Association rules represent a promising technique to improve heart
disease prediction. Unfortunately, when association rules are applied on a
medical data set, they produce an extremely large number of rules. Most
of such rules are medically irrelevant and the time required to find them
can be impractical
• [3]The healthcare environment is still ‘information rich’ But ‘knowledge
poor’. There is a wealth of data available within the health care systems.
However, there is a lack of effective analysis tools to discover hidden
relationships in data.
• [4]Today medical services have come a long way to treat patients with
various diseases. Among the most lethal one is the heart disease problem
which cannot be seen with a naked eye and comes instantly when its
limitations are reached. Today diagnosing patients correctly and
administering effective treatments have become quite a challenge.
4

5. EXISTING SYSTEM
• Very few systems use the available clinical data for
prediction purposes and even if they do ,they are
restricted by the large number of association rules
that apply.
• Diagnosis of the condition solely depends upon the
Doctors’s intuition and patient’s records.
The disadvantages are
• Detection is not possible at an earlier stage.
• In the existing system, practical use of various
collected data is time consuming .
5

6. PROPOSED SYSTEM
• The proposed system acts as a decision support system and
will prove to be an aid for the physicians with the diagnosis.
• The algorithm ,Fuzzy c means uses clustering and makes use
of clusters and data points to predict the relativity of an
attribute.
• Each data point is associated with multiple clusters depending
upon the membership degrees.
Advantages:
• High performance and accuracy rate.
• FCM is very flexible and is widely in various domains with high
rates of success.
6

7. SYSTEM SPECIFICATION
Software Requirements:
• MS Windows XP and above
• MS Visual Studio.Net 2005
• MS SQL Server 2000
Hardware Requirements:
• Hard Disk: Greater than 15GB
• RAM: Greater than 1GB
• Processor: Core 2 Duo and Above
7

8. Architecture Of The System
SRM University-CSE Dept.SRM University-CSE Dept. 7/16 8

9. Activity Diagram
9

10. Sequence Diagram
10

11. List Of Modules
Modules for Heart Attack Prediction
Are
• User module
• Doctor module
• Clustering module
11

12. User Module
• With the datasets already acquired from the UCI
Machine learning repository, We can now proceed with
collecting the details of the patients.
• Data like the patients name, Blood group, Address,
Phone number, sex, weight, Height are collected from the
patients themselves to help with the creation of an
individual user account.
• Already registered user can directly start accessing the
system with the help of the user id and password
provided.
12

13. Doctor Module
• Doctor views all patient details and their Medical History.
• Doctor with the help of the medical records, punch in the
value of the attributes which is fed into FCM for
clustering purposes.
• The attributes used are given below
age, sex, chest pain, Rest BP, cholesterol, sugar, ECG, Max
heart range, Angina, Old peak, Sis lope, vessels,
Thalassemia.
• The result is a screen that displays the chance of a person
contracting heart attack
• The system then produces a list of suggestions for the
person with the given attributes
13

14. Use Case Diagrams
14

15. Clustering Module
• We employ Fuzzy C means Clustering which is apt
for clustering medical data. The data given by the
doctor and the patient has been Fed into then
algorithm. It is now the job of the clustering
algorithm.
• Data clustering is process of dividing data
elements into classes or clusters so that items in
the same class are as similar as possible, and
items in different classes are as dissimilar as
possible.
15

16. FUZZY C-MEANS CLUSTERING
16
• Fixed number of
clusters. One
per cluster.
• Each data point may
belong to one or
more clusters
depending on the
degree.
• The centroid may
change based on the
degree. Animation by Andrey A. Shabalin, Ph.D.Figure

17. Fuzzy C-Means Clustering
pick c centroids at
random
assign membership degrees
according to:
move each centroid to the
following position:
Note: formulas are result of the method of
Lagrange multipliers as applied to aforementioned
cost function. Proof left as exercise.
Animation by Andrey A. Shabalin, Ph.D.

18. Fuzzy C-Means Clustering (FCM)Fuzzy C-Means Clustering
Fixed number of clusters.
One .
Clusters are fuzzy sets.
Membership degree of a
point can be any number
between 0 and 1.
Sum of all degrees for a
point must add up to 1.
Animation by Matteo Matteucci, Ph.D.Figure

19. Fuzzy C-Mean Clustering
• Fuzzy C-Mean Algorithm
– Initiate k seeds of prototypes p1, p2, …, pk
– Grouping:
Assign samples to their nearest prototypes
Form non-overlapping clusters out of these samples
– Centering:
Centers of clusters become new prototypes
– Repeat the grouping and centering steps, until
convergence
ADVANTAGES
• Ensures a higher rate of accuracy and efficiency.
• Computation time is greatly reduced.
19

20. Screenshots
Login Page
20

21. Signup page
21

22. Patient’s details page
22

23. Patient’s Result
23

24. Patient Suggestions
24

25. Doctor’s view of the patient details
25

26. CONCLUSION
• Proposed, is a FCM clustering algorithm for predicting the risk
of heart attack in a patient using the attributes collected from
the doctor.
• Proper adaptation of FCM clusters the data into an optimum
number of clusters and aids with detecting the normal and
abnormal cases efficiently.
26

27. REFERENCES
1. Sellappan Palaniappan,Rafiah Awang, “Intelligent Heart Disease
Prediction System Using Data Mining Techniques” IEEE
Conference, 2008,pp 108-115.
2. Carolas Ordonez “Assosiation Rule Discovery With the Train and
Test Approach for Heart Disease Prediction” IEEE Transactions on
Information Technology in Biomedicine, Vol. 10, No. 2, April 2006.
3. Shanthakumar B.Patil,Y.S,Kumaraswamy”Intelligent and Effective
Heart Attack Prediction System Using Data Mining and Artificial
Neural Network”. European Journal of Scientific Research Vol. 31,
No. 04, 2009, 642-656 .
4. Palaniappan, S., Awang, R., 2008. Intelligent heart disease
prediction system using data mining techniques. International
Journal of Computer Science and Network Security 8, 108–115.
5. www.benjaminjamesbush.com/fuzzyclustering.pptx
27