DIAGNOSIS PENYAKIT DIABETES DALAM DATA MEDIS MENGGUNAKAN METODE NAÏVE BAYES

Abstract

Abstract
Diabetes is a chronic disease with a globally increasing prevalence. Early detection risk prediction of diabetes are
crucial for better prevention and management. This study aims to develop a diabetes prediction model using the
Naïve Bayes method based on patient medical data. The data used includes risk factors such as age, body mass
index, family history, blood pressure, and laboratory test results. The Naïve Bayes method was chosen for its ability
to handle categorical and numerical data, as well as its efficiency on large datasets. In this study, there are 9
attributes used to classify diabetes datasets. Using this measurement technique, the accuracy of the model and the
Area Under Curve (AUC) as an indicator of the prediction quality of the algorithm used can be calculated. Unlike
previous studies, this study considered risk factors such as age, body mass index, glucose levels, family history,
and laboratory test results. The focus of this research is on diabetes. such as glucose, laboratory results, and genetic
risk factors. Using this measurement technique, the accuracy of the model and the Area Under Curve (AUC) as an
indicator of the prediction quality of the algorithm used can be calculated. Unlike previous studies, this study
considered risk factors such as age, body mass index, glucose levels, family history, and laboratory test results.
The focus of this research is on diabetes. such as glucose, laboratory results, and genetic risk factors.