III. LITERATURE SURVEY
Numerous studies have been done that have focus on diagnosis of heart disease. They have applied different
data mining techniques for diagnosis & achieved different probabilities for different methods.
An Intelligent Heart Disease Prediction System (IHDPS) is developed by using data mining techniques
Naive Bayes, Neural Network, and Decision Trees was proposed by SellappanPalaniappan et al .[3].
Each method has its own strength to get appropriate results. To build this system hidden patterns and
relationship between them is used. It is web-based, user friendly & expandable.
To develop the multi-parametric feature with linear and nonlinear characteristics of HRV (Heart Rate
Variability) a novel technique was proposed by HeonGyu Lee et al. [5]. To achieve this, they have used
several classifiers e.g. Bayesian Classifiers, CMAR (Classification based on Multiple Association
Rules), C4.5 (Decision Tree) and SVM (Support Vector Machine).
The prediction of Heart disease, Blood Pressure and Sugar with the aid of neural networks was
proposed by Niti Guru et al. [4]. The dataset contains records with 13 attributes in each record. The
supervised networks i.e. Neural Network with back propagation algorithm is used for training and
testing of data.
The problem of identifying constrained association rules for heart disease prediction was studied by
Carlos Ordonez [7]. The resultant dataset contains records of patients having heart disease. Three
constraints were introduced to decrease the number of patterns [6]. They are as follows:
1. The attributes have to appear on only one side of the rule.
2. Separate the attributes into groups. i.e. uninteresting groups.
3. In a rule, there should be limited number of attributes.
The result of this is two groups of rules, the presence or absence of heart disease.
Franck Le Duff et al. [9] builds a decision tree with database of patient for a medical problem.