<![CDATA[Diabetes is a disease that causes many deaths. According to data from WHO, in 2019 there were 2 million deaths due to diabetes. The recording of the patient's condition has been carried out for medical purposes. The large number of records that are only used as stored data will only later become digital waste. Data mining offers a classification process to process data into new knowledge. The recognition of new patterns from existing data results from algorithmic calculation processes as well as statistics. This study uses the type 2 diabetes dataset from the uci repository which was released in 2020. Previous research was conducted using the KNN algorithm with an accuracy rate of 92.5%. For numerical datasets, the decision tree algorithm is proven to be superior and can represent it in a language that is easy for humans to understand. One of the best and widely used classification algorithms for high-dimensional datasets is the decision tree. The results showed that the accuracy of the decision tree algorithm for type 2 diabetes data classification was 95.96%. Another output of this study is a decision tree from the early stage diabetes risk prediction dataset.]]>
Copyrights © 2023
