scispace - formally typeset
Search or ask a question
Author

P. Gayathri

Bio: P. Gayathri is an academic researcher. The author has contributed to research in topics: Association rule learning & Multivariate adaptive regression splines. The author has an hindex of 2, co-authored 2 publications receiving 58 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: In this work, principle component analysis algorithm is used for reducing the dimensions and it determines the attributes involving more towards the prediction of stroke disease and predicts whether the patient is suffering from stroke disease or not.
Abstract: In today‟s world data mining plays a vital role for prediction of diseases in medical industry. Stroke is a lifethreatning disease that has been ranked third leading cause of death in states and in developing countries. The stroke is a leading cause of serious, long term disability in US. The time taken to recover from stroke disease depends on patients‟ severity. Number of work has been carried out for predicting various diseases by comparing the performance of predictive data mining. Here the classification algorithms like Decision Tree, Naive Bayes and Neural Network is used for predicting the presence of stroke disease with related number of attributes. In our work, principle component analysis algorithm is used for reducing the dimensions and it determines the attributes involving more towards the prediction of stroke disease and predicts whether the patient is suffering from stroke disease or not. General Terms Data mining, Classification algorithm, Stroke disease.

59 citations

Journal ArticleDOI
TL;DR: In this article, the classification algorithms adopts and makes use of decision trees, Bayesian classifier, back propagation neural network, multivariate adaptive regression splines, adaptive-network-based fuzzy inference system,genetic algorithm, Fuzzy rulebase,Association rule and k means clustering for prediction of the diseases mentioned above.
Abstract: techniques. The Classification algorithms adopts and makes use of decision trees, Bayesian classifier, back propagation neural network, multivariate adaptive regression splines,Adaptive-network-based fuzzy inference system ,genetic algorithm, Fuzzy rulebase,Association rule and k means clustering for prediction of the diseases mentioned above. It consists of attributes containing patient‘s medical history and symptoms. The records used for this study of prediction of diseases are cleaned and filtered with the data‘s which are irrelevant and aims to analyze the predictive/descriptive data mining techniques developed for the diagnosis of life threatening diseases.

19 citations


Cited by
More filters
01 Jan 2002

9,314 citations

Journal Article
TL;DR: The observations reveal that Neural networks with 15 attributes has outperformed over all other data mining techniques for heart disease prediction and decision tree has also shown good accuracy with the help of genetic algorithm and feature subset selection.
Abstract: Heart disease is a term that assigns to a large number of medical conditions related to heart. These medical conditions describe the abnormal health conditions that directly influence the heart and all its parts. Heart disease is a major health problem in today’s time. This paper aims at analyzing the various data mining techniques introduced in recent years for heart disease prediction. The observations reveal that Neural networks with 15 attributes has outperformed over all other data mining techniques. Another conclusion from the analysis is that decision tree has also shown good accuracy with the help of genetic algorithm and feature subset selection.

141 citations

Journal ArticleDOI
01 Jul 2013
TL;DR: In this article, the authors summarized the commonly used techniques for heart disease prediction and their complexities are summarized in this paper and observed that Hybrid Intelligent Algorithm improves the accuracy of the prediction system.
Abstract: The Healthcare industry generally clinical diagnosis is done mostly by doctor's expertise and experience. Computer Aided Decision Support System plays a major role in medical field. With the growing research on heart disease predicting system, it has become important to categories the research outcomes and provides readers with an overview of the existing heart disease prediction techniques in each category. Neural Networks are one of many data mining analytical tools that can be utilized to make predictions for medical data. From the study it is observed that Hybrid Intelligent Algorithm improves the accuracy of the heart disease prediction system. The commonly used techniques for Heart Disease Prediction and their complexities are summarized in this paper.

71 citations

Journal ArticleDOI
TL;DR: Survey of relevant data mining techniques which are involved in risk prediction of heart disease provides best prediction model as hybrid approach comparing with single model approach.
Abstract: Comparison of classification techniques in Data mining to find the best technique for creating risk prediction model of heart disease at minimum effort. In Data mining, different methods used to find risk prediction of heart disease. There are two types of model used in analysis of data. First one is applying single model to various heart data and another one is applying combined model to the data. The combined model also known as hybrid model. This paper provides a quick and easy understanding of various prediction models in data mining and helps to find best model for further work. This is unique approach because various techniques listed and expressed in bar chart to understand accuracy level of each. These techniques are chosen based on their efficiency in the literature. In previous studies of different researcher expressed their effort on finding best approach for risk prediction model and here we found best model by comparing those researcher’s findings as survey. This survey helps to understand the recent techniques involved in risk prediction of heart disease at classification in data mining. Survey of relevant data mining techniques which are involved in risk prediction of heart disease provides best prediction model as hybrid approach comparing with single model approach.

68 citations

Journal ArticleDOI
TL;DR: According to the experimental results, the best machine learning algorithm is the support vector machine algorithm with the linear kernel, while the best feature selection algorithms is the reliefF method.
Abstract: Prediction of a heart attack is very important since it is one of the leading causes of sudden death, especially in low-income countries Although cardiologists use traditional clinical methods such as electrocardiography and blood tests for heart attack prediction, computer aided diagnosis systems that use machine learning methods are also in use for this task In this study, we used machine learning and feature selection algorithms together Our aim is to determine the best machine learning method and the best feature selection algorithm to predict heart attacks For this purpose, many machine learning methods with optimum parameters and several feature selection methods were used and evaluated on the Statlog (Heart) dataset According to the experimental results, the best machine learning algorithm is the support vector machine algorithm with the linear kernel, while the best feature selection algorithm is the reliefF method This pair gave the highest accuracy value of 8481%

63 citations