Comparison of Random Forest and XGBoost for Diabetes Classification with SHAP and LIME Interpretation

  • Mubaraqah Mubaraqah Universitas Teknologi Akba Makassar
  • Annisa Nurul Puteri Universitas Teknologi Akba Makasaar
  • A. Sumardin Universitas Teknologi Akba Makasaar
PDF
DOI https://doi.org/10.31544/jtera.v9.i2.2024.121-130
Published 2025-03-29
Full Text Preview
Download PDF

Abstract

Diabetes Mellitus (DM) merupakan tantangan kesehatan global yang membutuhkan pendekatan inovatif untuk deteksi dini dan manajemen yang efektif. Studi ini bertujuan untuk membandingkan algoritma Random Forest  dan XGBoost  dalam klasifikasi diabetes sambil meningkatkan interpretabilitas model menggunakan teknik AI yang Dapat Dijelaskan (XAI)  seperti SHAP dan LIME. Metodologi ini melibatkan pemrosesan kumpulan data publik yang berisi 70.000 entri dengan 34 fitur medis, melatih model dengan parameter yang dioptimalkan, dan melakukan analisis interpretatif. Hasil menunjukkan bahwa XGBoost mencapai akurasi yang lebih tinggi (90,6%) dengan generalisasi yang lebih baik, sementara Random Forest unggul dalam efisiensi pelatihan. Analisis fitur mengidentifikasi faktor-faktor utama seperti Usia, Kadar Glukosa Darah, dan Penambahan Berat Badan Selama Kehamilan sebagai kontributor signifikan terhadap prediksi. Temuan ini memberikan panduan model yang akurat dan transparan untuk mendukung pengambilan keputusan medis.

Keywords

Machine Learning XAI Diabetes Classification Model Evaluation Model Interpretation

References

P. Saeedi, I. Petersohn, P. Salpea, et al., "Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: Results from the International Diabetes Federation Diabetes Atlas, 9th edition," Diabetes Research and Clinical Practice, vol. 157, p. 107843, 2019, doi: 10.1016/j.diabres.2019.107843.
International Diabetes Federation, IDF Diabetes Atlas, 10th ed., 2021. [Online]. Available: https://diabetesatlas.org.
Reuters, "More than 800 million adults have diabetes globally, many untreated, study suggests," Nov. 13, 2024. [Online]. Available: https://www.reuters.com/business/healthcare-pharmaceuticals/more-than-800-million-adults-have-diabetes-globally-many-untreated-study-2024-11-13/.
World Health Organization, "Diabetes," 2023. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/diabetes.
D. J. Magliano, R. M. Islam, E. L. M. Barr, et al., "Diabetes mellitus, the fastest growing global public health concern," The Lancet, vol. 403, no. 10399, pp. 1234-1245, 2024, doi: 10.1016/S0140-6736(24)00345-2.
Ciputra Hospital, "Komplikasi Diabetes Mellitus," 2022. [Online]. Available: https://ciputrahospital.com/komplikasi-diabetes-mellitus/.
A. Suherman, H. Harun, and D. Deni, "Dampak Diabetes Melitus Tipe 2 pada Fungsi Ginjal: Faktor Risiko, Gejala, dan Pentingnya Manajemen yang Tepat," Jurnal Keperawatan Thamrin, vol. 1, no. 1, pp. 15-16, 2023. [Online]. Available: https://eresources.thamrin.ac.id/1629/2/Winda%20Wardianti_S1%20Keperawatan_2024%20-%20Bab%201.pdf.
W. Wardianti, "Bab 1 Pendahuluan: Diabetes Melitus Tipe 2 dan Komplikasinya," Jurnal Keperawatan Thamrin, vol. 1, no. 1, pp. 1-16, 2024. [Online]. Available: https://eresources.thamrin.ac.id/1629/2/Winda%20Wardianti_S1%20Keperawatan_2024%20-%20Bab%201.pdf.
H. Yin, B. Mukadam, X. Dai, and N. K. Jha, "DiabDeep: Pervasive Diabetes Diagnosis based on Wearable Medical Sensors and Efficient Neural Networks," arXiv preprint arXiv:1910.04925, 2019. [Online]. Available: https://arxiv.org/abs/1910.04925.
Z. Zhang, K. A. Ahmed, M. R. Hasan, T. Gedeon, and M. Z. Hossain, "A Deep Learning Approach to Diabetes Diagnosis," arXiv preprint arXiv:2403.07483, 2024. [Online]. Available: https://arxiv.org/abs/2403.07483.
S. Hardani, "Diagnosa Penyakit Diabetes dengan Metode Forward Chaining," JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 5, no. 2, pp. 231–236, 2020, doi: 10.33480/jitk.v5i2.1132.
Kementerian Kesehatan Republik Indonesia, "RSCM Luncurkan Tes Genomik Pengobatan Presisi Untuk Diabetes, Kolesterol Tinggi, dan Nutrisi," Sehat Negeriku, Dec. 23, 2024. [Online]. Available: https://sehatnegeriku.kemkes.go.id/baca/umum/20241223/4247160/rscm-luncurkan-tes-genomik-pengobatan-presisi-untuk-diabetes-kolesterol-tinggi-nutrisi/.
S. Saru and S. Subashree, "Analysis and prediction of diabetes using machine learning," International Journal of Emerging Technology and Innovative Engineering, vol. 5, no. 4, 2019.
I. Tasin, T. U. Nabil, S. Islam, and R. Khan, "Diabetes prediction using machine learning and explainable AI techniques," Healthcare Technology Letters, vol. 10, no. 1-2, pp. 1-10, 2023.
S. M. Ganie, P. K. D. Pramanik, M. Bashir Malik, S. Mallik, and H. Qin, "An ensemble learning approach for diabetes prediction using boosting techniques," Frontiers in Genetics, vol. 14, p. 1252159, 2023.
Xue, J., Min, F., & Ma, F. (2020, November). Research on diabetes prediction method based on machine learning. In Journal of Physics: Conference Series (Vol. 1684, No. 1, p. 012062). IOP Publishing.
Vijayan, V. V., & Anjali, C. (2015, December). Prediction and diagnosis of diabetes mellitus—A machine learning approach. In 2015 IEEE Recent Advances in Intelligent Computational Systems (RAICS) (pp. 122-127). IEEE.
Zhou, H., Xin, Y., & Li, S. (2023). A diabetes prediction model based on Boruta feature selection and ensemble learning. BMC bioinformatics, 24(1), 224.
Zohair, M., Chandra, R., Tiwari, S., & Agarwal, S. (2024). A model fusion approach for severity prediction of diabetes with respect to binary and multiclass classification. International Journal of Information Technology, 16(3), 1955-1965.
Dash, S., Shakyawar, S. K., Sharma, M., & Kaushik, S. (2019). Big data in healthcare: management, analysis and future prospects. J Big Data 6: 54.
Doğru, A., Buyrukoğlu, S., & Arı, M. (2023). Model pembelajaran super ensemble hibrida untuk prediksi risiko diabetes tahap awal. Teknik & Komputasi Medis & Biologi , 61 (3), 785-797.
Salsabil, M., Azizah, N. L., & Eviyanti, A. (2024). Implementasi Data Mining Dalam Melakukan Prediksi Penyakit Diabetes Menggunakan Metode Random Forest Dan Xgboost. Jurnal Ilmiah Komputasi, 23(1), 51-58.

Issue

Vol. 9 No. 2: December 2024

Section

Articles

License

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

The copyright to this article is transferred to JTERA if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to JTERA. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment. The copyright transfer form will be sent via email before the article published.

The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.

How to Cite

[1]
“Comparison of Random Forest and XGBoost for Diabetes Classification with SHAP and LIME Interpretation”, JTERA, vol. 9, no. 2, pp. 121–130, Mar. 2025, doi: 10.31544/jtera.v9.i2.2024.121-130.