Cerebral infarction is one of the causes of stroke in the brain and is included in ischemic stroke. To detect infarction in the brain, classification in machine learning can be used. They are k-Nearest Neighbor (kNN) and Naive Bayes (NB). kNN is a simple and well-known machine learning method with high accuracy values. however, kNN can produce sub-optimal results if very little training data is used. Because it will produce accuracy from a biased model and has less than optimal performance. Meanwhile, Naive Bayes Classifier has a better level of accuracy compared to other classifier models. And only requires a small training test to get high accuracy. Therefore, this study will compare 2 different classifications to get the highest accuracy in the brain infarction dataset obtained from the Department of Radiology, dr. Cipto Mangunkusumo Hospital (RSCM). The accuracy of this method reaches 91% for kNN and 97% for Naive Bayes.
Thalassemia is a blood disorder that occurred in Southeast Asia. Thalassemia cannot be cured, but early detected thalassemia with screening process is the best way to prevent thalassemia disease. If early detection is done, patients can get the right treatment. It helps them increase their life expectancy and reduce the risk of thalassemia to the next generation. In this paper, we use thalassemia data and propose a random forest method to classify thalassemia disease well and accurately. The result concludes that the random forest algorithm can give the best accuracy, precision and recall which is 100 percent by using multiple five in range of 70 to 85 percent as the training data.
Stroke is a condition caused by disruption in the blood supply to the brain. When the flow of blood is decreasing and resulting dead brain tissue that is called an infarction. If this condition not treated immediately and don’t get the right treatment will cause the death of the brain. Therefore, the classification of infarction is important to help increase the life expectancy of the patients. In this study, we are using infarction data from the Department of Radiology at Dr. Cipto Mangunkusumo Hospital and propose a random forest method to help the health sector for detecting infarction quickly and accurately. The best result by using the random forest method is 94.44 percent with 65 percent as training data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.