AI-Powered Heart Disease Prediction: Exploring Data Mining Algorithms

Desklib provides solved assignments and past papers to help students succeed.

RESEARCH PAPER TITLE
PREDICTIVE DATA MINING FOR MEDICAL
DIAGNOSIS: AN OVERVIEW OF HEART
DISEASE PREDICTION.
Student name
Student ID

OUT LINES
 Introduction
 Importance of data mining in Medical field
 Techniques for the analysis
 Tanagra
 Decision tree
 Naïve Bayes
 K-NN algorithm
 Intelligent heart disease prediction system
 Methodology
 Association rule discovery
 Conclusion

INTRODUCTION
• In this research paper, the data mining techniques
have explored. Survey of these techniques is
related to the medical field. Authors describe the
data mining tools which are used in Medical
research field particularly in the heart disease
section.
• The different numbers of data mining possible
solutions are applied to the same number of data
set. The outcomes revealed that the performance
of the decision tree is outclassed and the other
technique which performed well is Bayesian.

IMPORTANCE OF DATA MINING IN
MEDICAL FIELD
• In the medical field, data mining is used to the
diagnosis of the hidden disease by exploring the
unique pattern of the data set. According to
research, the available data is separated. This data
need to you integrates at one platform. Data can be
collected from the hospital information system.
According to the research report, annually, 12
million people died due to heart disease.

TECHNIQUES FOR THE
ANALYSIS
1. Tanagra
2. Decision tree
3. Naïve Bayes
4. K-NN algorithm

TANAGRA
• It is an algorithm of data mining and a platform for
researchers and students which provide accessibility
for data mining software.
• Tanagra is also helpful to analyze real or synthetic
data. Tanagra has the ability to group big data at a
point by using clustering algorithms, the other
machine learning algorithms like supervised and
meta supervised learning, the visualization of data is
included in it.

DECISION TREE
. It is a predictive data modeling technique
where a large number of data can discrete
set of values and classified in a tree form.
In this classification system, there are two
features one is called leaves and another
one is called branches.

NAÏVE BAYES
• This algorithm maximizes the posterior
probability in class. The benefit of
using this method is that we can use
the naïve Bayes model without using
any Bayesian methods. The working of
this classifier is very elegant in the
complex real-world situations.

K-NN ALGORITHM
• This classifier is depend upon the
nearest training data, in machine
learning algorithm it is the simplest
algorithm.

INTELLIGENT HEART DISEASE
PREDICTION SYSTEM
• The system came with the name "Intelligent heart
disease prediction system", in the system the
techniques which are working very efficiently, for
instance, decision trees, naive Bayes and neural
network algorithm is used. This data mining system
is web-based system and also can able to solve the
composite problem, for instance, it can find analyze
that how much old are you, also provide information
about gander, blood pressure sugar level.

METHODOLOGY
. In this methodology, the specific patterns are
extracted from the patient and then this pattern is
sent to get the prediction of a heart attack.
The data is processed though suitable mining
process. Once this data is processed, the k-means
algorithm is applied. Besides this the other small
number of algorithm is also applicable on this data.

CONCLUSION
• To conclude, this research paper illustrates an
algorithm of data mining which is specifically design
for the diagnosis of heart disease. The main target of
this research paper is to implement a different kind of
techniques and find the one which is more accurate
and the diagnosis of the heart disease precisely. This
target refers at one point get an efficient method to
predict the medical disease. The algorithms which are
described in this research paper have unique kind of
accuracy and specifications.