Soft Computing based Approaches for Classifying Diseases using Medical Diagnosis Dataset

Huge amounts of data are handled regularly by the medical field. The findings can be influenced by managing enormous information using conventional methods. The levels in expression of thousands of genes that can be calculated concurrently in today's biology research in a single experiment scientist. Machine learning algorithms can be used in medical research to find out information, particularly for prediction of disease with the help of cell's molecular level is reflected in the profile of gene expression. For order assessing patient medications and physicians, early identification of illness is key. Machine learning algorithms like Decision trees, Support vector machine, Artificial Neural Networks, Bayes classification techniques, k-Nearest Neighbors classification techniques, etc. are used to determine different diseases. With high accuracy, the use of machine learning algorithms can lead to rapid prediction of disease. Because of this DNA micro-array method, it is possible to track large numbers of gene expressions. Using this large amount of gene data, researchers try to find the probability of diagnosis of disease with data-set gene expression. A number of techniques with comfortable results are developed.