Diabetes Prediction as Food Recommendation System Using Content-Based Filtering Based on Android

Authors

  • Sufyan Hanif Ariyana Politeknik Negeri Semarang
  • Parsumo Rahardjo
  • Sukamto

DOI:

https://doi.org/10.32497/orbith.v21i2.6714

Keywords:

Type 2 Diabetes, Machine Learning, Support Vector Classifier, Content-Based Filtering, Android Application

Abstract

Type 2 diabetes is a chronic condition with rising global prevalence, influenced by abnormal Body Mass Index (BMI) and poor dietary habits. This study aims to develop a machine learning-based system for predicting diabetes risk and providing personalized dietary recommendations based on BMI and prediction results. The methodology is self-designed and illustrated through a flowchart consisting of six stages: data collection, data preparation, modeling, evaluation, rule-based, and deployment. Diabetes-related data was collected from Roemani Hospital (2020–2024), while food data was gathered through web scraping from the FatSecret website. The prediction model uses the Support Vector Classifier (SVC) algorithm and achieves an accuracy of 97.77%. A content-based filtering method is used for food recommendation, producing a Mean Absolute Error (MAE) of 0.9362. The system is deployed as an Android application, offering personalized food suggestions to help users control dietary habits and lower their risk of type 2 diabetes.

References

[1] A. Azriful, Y. Adnan, E. Bujawati, S. Alam, and N. Nildawati, “Mengungkap Fakta Faktor Risiko Diabetes Melitus Di Indonesia,” Media Penelitian dan Pengembangan Kesehatan, vol. 34, no. 4, pp. 814–823, Nov. 2024, doi: 10.34011/jmp2k.v34i4.1988.

[2] D. Jauhanita, A. Sriatmi, and M. I. Kartasurya, “Manajemen Diabetes Melitus pada Remaja: Evaluasi Terhadap Pendekatan Nutrisi dan Intervensi Gizi dalam Tinjauan Sistematis,” MAHESA : Malahayati Health Student Journal, vol. 4, no. 5, pp. 1946–1964, May 2024, doi: 10.33024/mahesa.v4i5.14460.

[3] U. Saranianingsi, S. Rammang, E. Hidayat, I. Keperawatan, and U. Widya Nusantara, “Hubungan Pola Makan dan Aktivitas Fisik terhadap Peningkatan Kadar Gula Darah Pasien Diabetes Melitus Tipe 2 di Puskesmas Biromaru,” https://jptam.org, vol. 9, pp. 2894–2899, 2025.

[4] Dakhaz Mustafa Abdullah and Adnan Mohsin Abdulazeez, “Machine Learning Applications based on SVM Classification: A Review,” Qubahan Academic Journal, vol. 3, no. 4, pp. 206–218, Nov. 2021, doi: 10.48161/Issn.2709-8206.

[5] Luqyana Zakiya Almas, Yuliana Susanti, and Sri Sulistijowati Handajani, “Penerapan Algoritma K-Nearest Neighbors dalam Sistem Rekomendasi Makanan Berdasarkan Kebutuhan Nutrisi dengan Content-Based Filtering,” Statistika, vol. 24, no. 1, pp. 115–122, May 2024, doi: 10.29313/statistika.v24i1.3558.

[6] R. Zainuddin and P. Labdullah, “Efektivitas Isometric Handgrip Exercise dalam Menurunkan Tekanan Darah pada Pasien Hipertensi Effectiveness Of Isometric Handgrip Exercise In Reducing Blood Pressure In Hypertension Patients,” Jurnal Ilmiah Kesehatan Sandi Husada, 2020, doi: 10.35816/jiskh.v10i2.364.

[7] Hovi Sohibul Wafa, Asep Id Hadiana, and Fajri Rakhmat Umbara, “Prediksi Penyakit Diabetes Menggunakan Algoritma Support Vector Machine (SVM) INFORMASI ARTIKEL ABSTRAK,” INFORMATICS AND DIGITAL EXPERT (INDEX), vol. 4, no. 1, pp. 40–45, 2022, [Online]. Available: https://e-journal.unper.ac.id/index.php/informatics

[8] N. Maulidah, R. Supriyadi, D. Y. Utami, F. N. Hasan, A. Fauzi, and A. Christian, “Prediksi Penyakit Diabetes Melitus Menggunakan Metode Support Vector Machine dan Naive Bayes,” Indonesian Journal on Software Engineering (IJSE), vol. 7, no. 1, pp. 63–68, 2021, [Online]. Available: http://ejournal.bsi.ac.id/ejurnal/index.php/ijse63

[9] Evidently AI Team, “Mean Average Precision (MAP) in ranking and recommendations,” Evidently AI. Accessed: Jul. 01, 2025. [Online]. Available: https://www.evidentlyai.com/ranking-metrics/mean-average-precision-map#how-to-calculate-map

[10] Ardhi Supratman, Indarmawan Nugroho, and Rifki Dwi Kurniawan, “Penerapan Metode Rule Based System Untuk Menentukan Jenis Tanaman,” INNOVATIVE: Journal Of Social Science Research, vol. 4, no. 2, pp. 7879–7890, 2024.

[11] F. F. Zakiyah, V. Indrawati, S. Sulandjari, and S. A. Pratama, “Asupan karbohidrat, serat, dan vitamin D dengan kadar glukosa darah pada pasien rawat inap diabetes mellitus,” Jurnal Gizi Klinik Indonesia, vol. 20, no. 1, p. 21, Jul. 2023, doi: 10.22146/ijcn.83275.

[12] A. Susilowati, B. Rachmat, R. Ayu Larasati, P. Penelitian dan Pengembangan Upaya Kesehatan Masyarakat, B. Penelitian dan Pengembangan Kesehatan, and K. R. Kesehatan Jl Percetakan, “Hubungan Pola Konsumsi Serat Dengan Kontrol Glikemik Pada Diabetes Tipe 2 [T2d] Di Kecamatan Bogor Tengah (Relationship Of Fiber Consumption Patterns To Glycemic Control In Type 2 Diabetes [T2d] In Central Bogor Sub-District),” Penel Gizi Makan, no. 1, 2020.

[13] I. B. Nafisah, “Analisis Hubungan Antara Indeks Massa Tubuh (Bmi), Ketidakpuasan Tubuh Dan Lingkungan Sosial Terhadap Perilaku Diet Tidak Sehat Pada Gadis Remaja,” JURNAL KESEHATAN TAMBUSAI, vol. 5, no. 2, 2024.

[14] V. Fresinsya and A. Qoiriah, “Meal-Planning Berbasis Status Gizi dengan Metode Klasifikasi K-nearest neighbors (KNN) untuk Pasien Obesitas,” Journal of Informatics and Computer Science, vol. 06, 2024.

[15] N. Sofi and R. Dharmawan, “Perancangan Aplikasi Bengkel Csm Berbasis Android Menggunakan Framework Flutter (Bahasa Dart),” JTS, vol. 1, no. 2, 2022.

Downloads

Published

2025-07-31

Issue

Vol. 21 No. 2 (2025): Juli 2025

Section

Engineering Articles

License

Authors who publish with this journal agree to the following terms:

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).