Rough Set Classifications and Performance Analysis in Medical Health Care

Medical health care (MHC) system is found to be most approachable and believable system, where utmost care has been taken by human intelligence with criteria like cure, prevent, and side effects. MHC is a new paradigm and in transition in integrating with smart clinical IoT devices powered with automated capabilities of data mining, artificial intelligence, and machine learning. Thus accurate prediction and classification from clinical datsets is the need of hour. Rough set theory (RST) plays a vital role in machine learning, inductive reasoning, and decision support expert systems. In this paper, we use RST-based feature selection method with a neural network to improve the classification accuracy in using different medical datasets. It is observed that a lot of objects or data is generally discarded (to make the dataset normal) during data preprocessing which would adversely affect the performance of classification. Our RST-based proposed method outperforms and opens a new dimension of applications in machine learning in the wide MHC domains including radiology, pathology, oncology, cardiology, neurology.