E. P. Ephzibah

Bio: E. P. Ephzibah is an academic researcher from VIT University. The author has contributed to research in topics: Feature selection & Fuzzy logic. The author has an hindex of 8, co-authored 17 publications receiving 308 citations.

A neuro fuzzy expert system for heart disease diagnosis

Abstract: Heart disease in India is one of the major causes of death. This disease is common not only in old and middle aged people but also in young people. It is caused due to improper diet habits. The proposed system finds a solution to diagnose the disease using some of the evolutionary computing techniques like genetic algorithm, fuzzy rule based learning and neural networks. The neuro fuzzy classification of the disease with the help of genetic algorithms for feature selection is the frame work of the proposed system.

Heart Disease Prediction Using Hybrid Genetic Fuzzy Model

Abstract: The objective of the work is to diagnose heart disease using computing techniques like genetic algorithm and fuzzy logic. The system would help the doctors to automate heart disease diagnosis and to enhance the medical care. In this paper a hybrid genetic-fuzzy heart disease diagnosis system is designed. The genetic algorithm is used for a stochastic search that provides the optimal solution to the feature selection problem. The relevant features selected from the dataset help the diagnosing system to develop a classification model using fuzzy inference system. The rules for the fuzzy system are generated from the sample data. Among the entire rule set the important and relevant subset of rules are selected using genetic algorithm. The proposed work uses the benefits of genetic algorithms and fuzzy inference system for effective prediction of heart disease in patients. The selected features are sex, serum cholesterol (chol), maximum heart rate achieved (thalach), Exercise induced angina (exang), ST depression induced by exercise relative to rest (oldpeak), number of major vessels coloured (ca) and thal value. Fuzzification using Fuzzy Gaussian membership function and defuzzification using centroid method improves the performance of the system. The work has been evaluated using the performance metrics like accuracy, specificity, sensitivity, confusion matrix that help in proving the efficiency of the work. The obtained classification accuracy is 86% using the stratified k fold technique with the values for specificity and sensitivity as .90 and .80 respectively. The number of attributes has been reduced from 13 to 7 from heart disease dataset available in the UCI Machine learning repository. When compared with the existing system the accuracy of the proposed work has been increased by 1.54%. The proposed model is named as GAFL model called Genetic Algorithm Fuzzy Logic model for effective heart disease prediction. It is easy to build the model thereby providing an easy option to be used in hospitals and medical centers for the aid of the physicians.

Cost effective approach on feature selection using genetic algorithms and fuzzy logic for diabetes diagnosis .

Abstract: A way to enhance the performance of a model that combines genetic algorithms and fuzzy logic for feature selection and classification is proposed. Early diagnosis of any disease with less cost is preferable. Diabetes is one such disease. Diabetes has become the fourth leading cause of death in developed countries and there is substantial evidence that it is reaching epidemic proportions in many developing and newly industrialized nations. In medical diagnosis, patterns consist of observable symptoms along with the results of diagnostic tests. These tests have various associated costs and risks. In the automated design of pattern classification, the proposed system solves the feature subset selection problem. It is a task of identifying and selecting a useful subset of pattern-representing features from a larger set of features. Using fuzzy rule-based classification system, the proposed system proves to improve the classification accuracy.

Framing Fuzzy Rules using Support Sets for Effective Heart Disease Diagnosis

Abstract: Significance and relevance of certain features are obtained by various techniques. Feature subset selection involves summarizing mutual associations between class decisions and attribute values in a pre-classified database. In this paper genetic algorithm is used to find the relevant set of features by optimizing the fitness function and using the operators like crossover and mutation. Fuzzy logic is a form of knowledge representation suitable for notions that cannot be defined precisely, but which depend upon their contexts. In this work the fuzzy rules are framed with the help of support sets. The classification done using fuzzy inference system provides results that are better than other techniques.

Heart Disease Classification Using PCA and Feed Forward Neural Networks

Abstract: The primary objective of this work is to discover a meaningful information in heart disease dataset for better diagnosis. This work is done using the data set available in UCI Machine learning repository. The work focuses on selecting the important features in the dataset using Principal Component Analysis and regression techniques. Using regression, the exponentiated estimate of the coefficient exp(B) of the feature is considered for feature selection. The exp(B) is the odds ratio of the independent variables. The work is done taking into consideration the components extracted using Principal Components Analysis technique and applying various operations on these components to produce methods like PCA1, PCA2, PCA3 and PCA4. It is observed that for one of the proposed methods PCA1, the prediction accuracy is 92.0% using regression and 95.2% using feed forward neural network classifier which is better than other methods. It is also observed that the accuracy of exp(B) is closer to PCA1 method, hence concluding that the exp(B) can also be considered for feature selection.

Survey of Machine Learning Algorithms for Disease Diagnostic

Abstract: In medical imaging, Computer Aided Diagnosis (CAD) is a rapidly growing dynamic area of research. In recent years, significant attempts are made for the enhancement of computer aided diagnosis applications because errors in medical diagnostic systems can result in seriously misleading medical treatments. Machine learning is important in Computer Aided Diagnosis. After using an easy equation, objects such as organs may not be indicated accurately. So, pattern recognition fundamentally involves learning from examples. In the field of bio-medical, pattern recognition and machine learning promise the improved accuracy of perception and diagnosis of disease. They also promote the objectivity of decision-making process. For the analysis of high-dimensional and multimodal bio-medical data, machine learning offers a worthy approach for making classy and automatic algorithms. This survey paper provides the comparative analysis of different machine learning algorithms for diagnosis of different diseases such as heart disease, diabetes disease, liver disease, dengue disease and hepatitis disease. It brings attention towards the suite of machine learning algorithms and tools that are used for the analysis of diseases and decision-making process accordingly.

Hybrid genetic algorithm and a fuzzy logic classifier for heart disease diagnosis

Abstract: For the past two decades, most of the people from developing countries are suffering from heart disease. Diagnosing these diseases at earlier stages helps patients reduce the risk of death and also in reducing the cost of treatment. The objective of adaptive genetic algorithm with fuzzy logic (AGAFL) model is to predict heart disease which will help medical practitioners in diagnosing heart disease at early stages. The model consists of the rough sets based heart disease feature selection module and the fuzzy rule based classification module. The generated rules from fuzzy classifiers are optimized by applying the adaptive genetic algorithm. First, important features which effect heart disease are selected by rough set theory. The second step predicts the heart disease using the hybrid AGAFL classifier. The experimentation is performed on the publicly available UCI heart disease datasets. Thorough experimental analysis shows that our approach has outperformed current existing methods.

Original Article: Clinical decision support system: Risk level prediction of heart disease using weighted fuzzy rules

Abstract: As people have interests in their health recently, development of medical domain application has been one of the most active research areas. One example of the medical domain application is the detection system for heart disease based on computer-aided diagnosis methods, where the data are obtained from some other sources and are evaluated based on computer-based applications. Earlier, the use of computer was to build a knowledge based clinical decision support system which uses knowledge from medical experts and transfers this knowledge into computer algorithms manually. This process is time consuming and really depends on medical experts' opinions which may be subjective. To handle this problem, machine learning techniques have been developed to gain knowledge automatically from examples or raw data. Here, a weighted fuzzy rule-based clinical decision support system (CDSS) is presented for the diagnosis of heart disease, automatically obtaining knowledge from the patient's clinical data. The proposed clinical decision support system for the risk prediction of heart patients consists of two phases: (1) automated approach for the generation of weighted fuzzy rules and (2) developing a fuzzy rule-based decision support system. In the first phase, we have used the mining technique, attribute selection and attribute weightage method to obtain the weighted fuzzy rules. Then, the fuzzy system is constructed in accordance with the weighted fuzzy rules and chosen attributes. Finally, the experimentation is carried out on the proposed system using the datasets obtained from the UCI repository and the performance of the system is compared with the neural network-based system utilizing accuracy, sensitivity and specificity.