Comparison of Distance Models on K-Nearest Neighbor Algorithm in Stroke Disease Detection

Stroke is a cardiovascular (CVD) disease caused by the failure of brain cells to get oxygen supply pose risk ischemic damage and result in death. This Disease can detect based on similarity symptoms experienced sufferer so that early steps be taking with appropriate counseling treatment. detecting requires machine learning method. In this research, author used one supervised classification methods, namely K-Nearest Neighbor (K-NN). K-NN method calculating distance training data. research compares Euclidean, Minkowski, Manhattan, Chebyshev models obtain optimal results. The have been tested using stroke dataset sourced from Kaggle repository. Based test results, model has highest levels accuracy compared other three an average value 95.49%, 96.03%, at K = 10. Euclidean Minkowski same level each 95.45%, 95.93% Meanwhile, Manhattan lowest models, which 95.42% but 96.03% 6