Implementasi Algoritma K-nearest Neighbor (KNN) Menggunakan Rapid Miner Untuk Prediksi Penyakit Diabetes Berdasarkan Dataset Pima Indian

Tetta Thirza Herdyawan (Universitas Pamulang)
Dimas Cahyo Saputra (Universitas Pamulang)
Gabriel Carol Aldosion (Universitas Pamulang)
Salsha Sabilla Nurhidayat (Universitas Pamulang)
Sukrinah (Universitas Pamulang)

Journal of Information Technology and Informatics Engineering
Vol 1 No 1 (2025): Journal of Information Technology and Informatics Engineering (JITIE)

The objective of this research is to use the publicly accessible Pima Indian dataset to use the K-Nearest Neighbor (KNN) algorithm for diabetes prediction. A straightforward yet powerful classification technique, the KNN method is particularly useful for processing medical data. RapidMiner software was utilized for this study's analysis method, which included data pre-processing, training and test data separation, and classification model validation. Numerous health indicators, including age, blood pressure, body mass index, and glucose levels, are included in the Pima Indian dataset and are utilized as predictive features. The test results demonstrate that the KNN algorithm can categorize patients with or without diabetes with a reasonably high degree of accuracy. Accuracy, precision, recall, and confusion matrix metrics were used to assess the model's performance. As a result, using KNN to this dataset may be a way to help the decision support system for diabetes early diagnosis.