<![CDATA[Diabetes Mellitus (DM) is a chronic disease with a high prevalence that can cause serious complications if not diagnosed early. The initial diagnostic process, which relies on manual interpretation by medical personnel, is often time-consuming and prone to causing treatment delays. Therefore, this study aims to implement the Random Forest algorithm in a machine learning system to classify Diabetes Mellitus quickly and accurately. The system development method used is the Agile model with a Scrum approach to ensure an iterative and adaptive development cycle. This system was built using the Python programming language and a MySQL database, utilizing a patient dataset that includes variables such as the number of pregnancies, glucose levels, blood pressure, body mass index (BMI), age, and other health parameters. The results showed that the Random Forest algorithm successfully performed the classification with an accuracy rate of 90.8%, demonstrating excellent performance in predicting diabetes risk. The implication of this research is the development of an objective and efficient intelligent system to assist healthcare workers in conducting initial screening, thereby enabling more effective patient data processing and medical decision-making.]]>
Copyrights © 2026
