Application of Data Mining Approach in the Classification of Diabetes Mellitus Using the Naïve Bayes Algorithm

Acep Irham Gufroni(1*), Rahmi Nur Shofa(2), Riza Lukmanulhakim(3),

(1) Universitas Siliwangi
(2) Universitas Siliwangi
(3) Universitas Siliwangi
(*) Corresponding Author

Abstract


Diabetes mellitus is a metabolic disorder disease caused by the pancreas that cannot produce enough insulin or the body cannot use insulin effectively. Diabetes mellitus is usually caused by high blood sugar levels. The purpose of this study is to determine whether the performance results of the Naïve Bayes algorithm can produce a very good classification in the classification of diabetes mellitus. The Naïve Bayes algorithm was chosen because this algorithm is very suitable for use on many datasets and always provides a high level of accuracy with the large number of datasets used. This study used data from internal medicine polyclinic patients in 2019 and 2020, with a total of 908 data. The classification process in this study is carried out by entering data into RapidMiner and making a process design, then the data will be tested using the Naïve Bayes algorithm. The results of the classification process using the Naïve Bayes algorithm show an accuracy of 93.70% and get an AUC value of 0.989

Full Text:

Pdf

References


M. Rifqi, “Aplikasi Data Mining Untuk Diagnosis Penyakit Diabetes Menggunakan Algoritma C4.5 Dan Naïve Bayes Classification,” 2016.

Harliani, “Efektifitas Penyuluhan Terhadap Peningkangkatan Pengetahuan Dan Penurunan Kadar Gula Darah Pada Penderita Diabetes Melitus,” Glob. Heal. Sci., vol. 3, no. 1, pp. 339–345, 2018.

A. Ridwan, “Penerapan Algoritma Naïve Bayes Untuk Klasifikasi Penyakit Diabetes Mellitus,” vol. IV, no. September, pp. 15–21, 2020.

Aris Faizal and Benyamin, “Penerapan Data Mining untuk Identifikasi Penyakit Diabetes Melitus dengan Menggunakan Metode Klasifikasi,” vol. 1, no. 1, pp. 1–6, 2019.

J. I. Marzuki, K. Mataram, and N. T. Bar, “Komparasi Akurasi Metode Correlated Naive Bayes Classifier Dan Naive Bayes Classifier Untuk Diagnosis Penyakit Diabetes”, (Jurnal Nasional Informatika dan Teknolog,” pp. 6–11.

N. Nurdiana and A. Algifari, “Studi Komparasi Algoritma Id3 Dan Algoritma Naive Bayes Untuk Klasifikasi Penyakit Diabetes Mellitus,” INFOTECH J., vol. 6, no. 2, pp. 18–23, 2020, [Online]. Available: https://ejournal.unma.ac.id/index.php/infotech/article/view/816

N. M. Putry and B. N. Sari, “Komparasi Algoritma KNN Dan Naïve Bayes Untuk Klasifikasi Diagnosis Penyakit Diabetes Melitus,” Evolusi J. Sains dan Manaj., vol. 10, no. 1, pp. 45–57, 2022, [Online]. Available: https://ejournal.bsi.ac.id/ejurnal/index.php/evolusi/article/view/12514/5403

M. Irfan, W. Uriawan, O. T. Kurahman, M. A. Ramdhani, and I. A. Dahlia, “Comparison of Naive Bayes and K-Nearest Neighbor methods to predict divorce issues,” IOP Conf. Ser. Mater. Sci. Eng., vol. 434, no. 1, 2018, doi: 10.1088/1757-899X/434/1/012047.




DOI: https://doi.org/10.30645/ijistech.v6i3.247

Refbacks

  • There are currently no refbacks.







Jumlah Kunjungan:

View My Stats

Published Papers Indexed/Abstracted By: