• Anil Kewat
• P N Srivastava
• Dharamdas Kumhar

Cancer, Diabetes, and Heart disease are the most common diseases which are the challenges and the major problems for the medical society of this real world and prediction of these diseases in the early stages are very important as it is one of the important causes of sudden death. Although specialists use some basic treatment methods and different types of pathology test for such type of disease prediction computer-aided diagnosis systems that use intelligent machine learning methods are used to help the health care professionals in the diagnosis of these diseases among the patients. For this research work, seven machine learning algorithms with the seven feature selection techniques were used and evaluated on the Heart disease, Breast Cancer and Diabetes datasets. The dataset used in this paper is collected from the UCI machine learning repository. We performed the simulation work on these datasets and analyze the results. After analyzing it is concluded that the support vector machine and J-48 machine learning algorithm gives the better results compare to the other machine learning algorithms for disease prediction.

Support vector machine, UCI, Feature Selection, Machine Learning, Dataset

"PERFORMANCE EVALUATION OF SOFT MACHINE LEARNING ALGORITHMS USING FEATURE SELECTION TECHNIQUES FOR DISEASE PREDICTION ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 1, page no.437-444, January-2019, Available :http://www.jetir.org/papers/JETIR1901451.pdf

"PERFORMANCE EVALUATION OF SOFT MACHINE LEARNING ALGORITHMS USING FEATURE SELECTION TECHNIQUES FOR DISEASE PREDICTION ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 1, page no. pp437-444, January-2019, Available at : http://www.jetir.org/papers/JETIR1901451.pdf