Web-based Application for Diagnosis of Diabetes using Learning Vector Quantization (LVQ)

Juni Wijayanti Puspita (Mathematics Department, Tadulako University)
Kevin Jieventius Yanto (Mathematics Department, Tadulako University)
Andi Moh. Ridho Pettalolo (Mathematics Department, Tadulako University)
Moh. Ali Akbar Dg. Matona (Mathematics Department, Tadulako University)
Handayani Lilies (Graduate School of Natural Science and Technology, Kanazawa University)

IJoICT (International Journal on Information and Communication Technology)
Vol. 10 No. 1 (2024): Vol. 10 No.1 June 2024

Diabetes is a chronic disease that causes the most deaths in the world. This disease can cause long-term complications that develop gradually, such as heart attacks, strokes, and problems with the kidneys, eyes, skin, and blood vessels. Therefore, early diagnosis of diabetes is crucial for patients to know their diabetes status. In this study, we designed a web-based application for diabetes diagnosis using Learning Vector Quantization (LVQ). The dataset was collected from Kaggle's Diabetes Dataset which contains eight attributes, namely pregnancy, glucose, blood pressure, insulin, skin thickness, BMI, diabetes lineage function, and age, with two classes, namely negative diabetes (healthy) and positive diabetes. The results show that the best accuracy is 73.1% with a learning rate of 0.001. These findings can help patients detect diabetes problems early.