UTILIZING K – NEIGHBORS ALGORITHM TO CLASSIFY THE STROKE DISEASE

Abstract

Stroke is the most common cause of disability in adults and one of ten leading causes of death in the world. It is estimated that in year 2030, stroke will be one of the four leading causes of death. However, the chances to avoid permanent disability greatly increases when treatment is given quickly after stroke onset. Machine learning can be portrayed as a significant tracker in areas like surveillance, medicine, data management with the aid of suitably trained machine learning algorithms. Data mining techniques applied in this work give an overall review about the tracking of information. The proposed idea is to find that which algorithm is suitable to classify stroke disease. With the help of Kaggle we have collected the data set. Next, the case sheets were mined using tagging and maximum entropy methodologies, and the proposed stemmer extracts the common and unique set of attributes to classify the strokes. This paper presents a prototype to classify stroke that combines text mining tools and machine learning algorithms. Data mining techniques applied in this work give an overall review about the tracking of information with respect to semantic as well as syntactic perspectives. the case sheets of 507 patients were collected from a Multispecialty Hospital. Next, the case sheets were mined using tagging and maximum entropy methodologies, and the proposed stemmer extracts the common and unique set of attributes to classify the strokes. The study brings out the effectiveness of the classification method for structured entities like patient case sheets. This study predicts the type of stroke for a patient based on classification methodologies with the accuracy of 91%. In this work, classification of both the types of strokes, with various classifiers with its kernel is illustrated which also adds to the novelty of the study. In short, most of the classification aids the medical specialist to classify the type of stroke