Implementasi Data Mining Untuk Klasifikasi Penyakit Liver Dengan C4.5 Adaboost

Abstract

With the development of the times, it is undeniable that science and technology as well as the ease of development of the internet make it easier for people to identify liver disease, and become strong supporters of diseases with special needs. The initiative of computer experts with artificial intelligence or artificial intelligence, bioinformatics is defined as the application of computational and analytical tools to capture and view biological data. The amount of data on liver disease that continues to increase requires several methods to process and draw conclusions and information from the data, which is expected to be able to improve the quality of data or information as well as the efficiency and effectiveness of data

processing. ultimately facilitate or assist in policy making, especially in tackling the problem of liver disease. To support this, data mining techniques can be used to find valuable information from a collection of information or historical data of the liver. Research on liver using data mining classifications has been done, both comparisons of several classifications of data mining models or improvements to data mining classifications. Research on liver has been carried out and research has been carried out. To conduct this research, it is necessary to have a study of previous related research. In order to know what methods were used, what kind of data was studied, and what kind of model was produced. The dataset used does not contain missing values, so there is no need to preprocess the data. In this study, the C4.5, Support Vector Machine (SVM) and C4.5 Adaboost classification methods were used. The results of this study indicate that the C4.5 Adaboost method is 77.12% and the sensitivity value is 76.40%, where the value is greater than the two other methods of analysis used