<![CDATA[Diabetes mellitus is a chronic disease characterized by high blood sugar levels which can cause various serious complications, including damage to the eyes, kidneys, heart and nerves. In Indonesia, this disease is one of the main causes of death, the increasing number of diabetes mellitus sufferers requires more efficient and accurate diagnostic methods to help manage and treat this disease. This research focuses on the application of Artificial Neural Networks (ANN) using the Perceptron method in diagnosing diabetes mellitus patients at Raden Mattaher Regional Hospital, Jambi. This system is designed to increase the accuracy of diagnosis, making it easier for doctors and medical personnel to determine the appropriate medical action. This research includes collecting symptom data such as age, family history of diabetes, feeling easily thirsty and hungry, physical data including checking the patient's weight, blood pressure and wounds. and laboratory results which include blood sugar, HbA1c and autoimmune tests from the patient. The data is then processed using the Perceptron method on ANN to produce a model for diagnosing types of diabetes, namely type 1, type 2 and gestational diabetes. The implementation of this method is carried out with the help of Matlab software. The research results show that the application of the perceptron method in ANN has a fairly high accuracy value in determining the target output and atctual output with a value of 100% using training data of 96 data from 120 data and 24 test data from 120 data. ]]>
Copyrights © 2025
