Prediksi Risiko Diabetes dengan Dataset BRFSS: Perspektif Recall dan Feature Importance: Diabetes Risk Prediction with BRFSS: A Recall and Feature Importance Perspective

Aisy Intan Herita; Dedy Kurniawan; Ken Ditha Tania

doi:10.57152/malcom.v6i4.3115

Authors

Aisy Intan Herita Universitas Sriwijaya
Dedy Kurniawan Universitas Sriwijaya
Ken Ditha Tania Universitas Sriwijaya

DOI:

https://doi.org/10.57152/malcom.v6i4.3115

Keywords:

BRFSS, Diabetes Melitus, Kepentingan Fitur, Pembelajaran Mesin, Recall

Abstract

Diabetes melitus tetap menjadi salah satu permasalahan kesehatan kronis global yang memerlukan deteksi dini untuk mengurangi risiko komplikasi. Machine learning telah banyak diterapkan untuk memprediksi diabetes menggunakan data survei kesehatan populasi seperti Behavioral Risk Factor Surveillance System (BRFSS), tetapi sebagian penelitian masih menitikberatkan accuracy meskipun data mengalami ketidakseimbangan kelas. Kondisi tersebut dapat menyebabkan kemampuan model dalam mengenali kasus positif kurang teridentifikasi secara optimal. Penelitian ini membandingkan lima algoritma, yaitu Support Vector Machine, Logistic Regression, Random Forest, XGBoost, dan Naive Bayes, menggunakan BRFSS 2015 dengan recall sebagai kriteria utama pemilihan model, bukan sekadar metrik evaluasi, serta menerapkan feature importance pada model dengan kemampuan deteksi terbaik. Tahapan penelitian meliputi praproses, penyederhanaan label menjadi biner, pembagian data 80:20, SMOTE, pelatihan model baseline, dan optimasi hyperparameter menggunakan GridSearchCV. Hasil menunjukkan SVM memperoleh recall tertinggi sebesar 77%, diikuti Logistic Regression sebesar 76%. Optimasi meningkatkan recall Random Forest dari 31% menjadi 65% dan XGBoost dari 23% menjadi 61%. Feature importance mengidentifikasi GenHlth, usia, BMI, HighBP, dan HighChol sebagai fitur dominan. Pendekatan ini menempatkan kemampuan deteksi kasus positif sebagai dasar seleksi model dan interpretasi fitur

Downloads

Download data is not yet available.

References

I. Ontario, “Correspondence and mortality among,” vol. 11, no. April, pp. 229–231, 2023, doi: 10.1016/S2213-8587(22)00358-8.

M. Knip et al., “SARS-CoV-2 and type 1 diabetes in children in Finland?: an observational study,” no. April, pp. 251–260, 2020, doi: 10.1016/S2213-8587(23)00041-4.

M. C. Ibrahim, “Comparison of Diabetes Prediction Data Using Machine Learning Perbandingan Data Prediksi Diabetes Menggunakan Machine Learning,” vol. 5, no. October, pp. 1423–1436, 2025.

M. Ahmed and H. Saeed, “Diabetes type 2 classification using machine learning algorithms with up ? sampling technique,” J. Electr. Syst. Inf. Technol., vol. 5, 2023, doi: 10.1186/s43067-023-00074-5.

E. Sonuç, “Turkish Journal of Electrical Engineering and Computer Sciences A practical framework for early detection of diabetes using ensemble machine learning models,” vol. 31, no. 4, 2023, doi: 10.55730/1300-0632.4013.

N. A. Pratama and D. W. Utomo, “Deteksi Diabetes Mellitus dengan Menggunakan Teknik Ensemble XGBoost dan LightGBM,” vol. 11, no. 1, pp. 1–12, 2026.

A. Kutay Yüksel, M. S. Güzel, and A. K. Yuksel, “Efficient Diabetes Prediction Using Random Forests and Minimal Health Indicators on the BRFSS Dataset,” J. Artif. Intell. Hum. Sci., vol. 2, no. 1, pp. 34–43, 2025, [Online]. Available: https://www.kaggle.com/datasets/alexteboul/diabetes-health-indicators-dataset/

B. Nguyen and Y. Zhang, “A Comparative Study of Diabetes Prediction Based on Lifestyle Factors Using Machine Learning,” 2025, [Online]. Available: http://arxiv.org/abs/2503.04137

M. A. Muhammad, J. Sani, and M. M. Ahmed, “Exploring Explainable Machine Learning for Predicting and Interpreting Self-Reported Diabetes among Tennessee Adults?: Insights from the 2023 Behavioral Risk Factor Surveillance System ( BRFSS ),” 2025, doi: 10.1177/21501319251400546.

K. Abnoosian, R. Farnoosh, and M. H. Behzadi, “Prediction of diabetes disease using an ensemble of machine learning multi ? classifier models,” BMC Bioinformatics, pp. 1–24, 2023, doi: 10.1186/s12859-023-05465-z.

A. Davinka, S. Depari, K. D. Tania, and P. E. Sevtiyuni, “Penerapan Metode Machine Learning Dan Teknik SMOTE untuk Prediksi Diabetes,” vol. 7, pp. 436–447, 2025, doi: 10.30865/json.v7i2.9032.

D. Dey et al., “The proper application of logistic regression model in complex survey data: a systematic review,” BMC Med. Res. Methodol., vol. 25, no. 1, 2025, doi: 10.1186/s12874-024-02454-5.

P. N. Thotad, G. R. Bharamagoudar, and B. S. Anami, “Diabetes & Metabolic Syndrome?: Clinical Research & Reviews Diabetes disease detection and classi fi cation on Indian demographic and health survey data using machine learning methods,” Diabetes Metab. Syndr. Clin. Res. Rev., vol. 17, no. 1, p. 102690, 2023, doi: 10.1016/j.dsx.2022.102690.

G. R. A. X. Anitha, M. E. Grace, M. Kanaga, and J. A. R. Jennifer, “Random Oversampling ? Based Diabetes Classification via Machine Learning Algorithms,” Int. J. Comput. Intell. Syst., vol. 3, 2024, doi: 10.1007/s44196-024-00678-3.

D. Das, Aayushman, S. Kumar, M. A. Hussain, and B. R. Reddy, “Diabetes Prediction using Ensemble Learning Techniques,” Procedia Comput. Sci., vol. 258, pp. 3155–3164, 2025, doi: 10.1016/j.procs.2025.04.573.

X. Feng, Y. Cai, and R. Xin, “Optimizing diabetes classification with a machine learning ? based framework,” BMC Bioinformatics, pp. 1–20, 2023, doi: 10.1186/s12859-023-05467-x.

A. Febrian, D. Hastono, A. V. Vitianingsih, P. Pamudi, and A. Lidya, “Diabetes Mellitus Disease Prediction Using Logistic Regression ( LR ) and Support Vector Machine ( SVM ) Methods,” vol. 5, no. 1, pp. 54–64, 2025.

M. Tools, “Efficient prediction of early-stage diabetes using XGBoost classifier with random forest feature selection technique,” 2023.

H. El Massari, N. Gherabi, F. Qanouni, and S. Mhammedi, “Diabetes Prediction Using Machine Learning with Feature Engineering and Hyperparameter Tuning,” vol. 15, no. 8, pp. 171–179, 2024.

S. M. Takalloo, H. Mohseni, H. M. Khosravi, and M. Mirzaei, “The effect of data balancing approaches on the prediction of metabolic syndrome using non ? invasive parameters based on random,” BMC Bioinformatics, pp. 1–14, 2024, doi: 10.1186/s12859-024-05633-9.

T. Sharma and M. Shah, “A comprehensive review of machine learning techniques on diabetes detection,” 2021.

M. Kutlu and E. Ai, “ADBa Machine Learning Interpretability in Diabetes Risk Assessment?: A SHAP Analysis,” 2024.

V. Chang, M. Ashok, K. Hall, L. Golightly, and Q. Ariel, “Healthcare Analytics An assessment of machine learning models and algorithms for early prediction and diagnosis of diabetes using health indicators ?,” Healthc. Anal., vol. 2, no. September, p. 100118, 2022, doi: 10.1016/j.health.2022.100118.

J. Kaliappan et al., “Analyzing classification and feature selection strategies for diabetes prediction across diverse diabetes datasets”.

R. Sistem, M. D. Anasanti, K. Hilyati, and A. Novtariany, “Exploring feature selection techniques on Classification Algorithms for Predicting Type 2 Diabetes at Early Stage,” vol. 5, no. 158, pp. 832–839, 2026.

A. Kashem, R. Karim, P. Das, S. D. Datta, and M. Alharthai, “Compressive strength prediction of sustainable concrete incorporating rice husk ash (RHA) using hybrid machine learning algorithms and parametric analyses,” Case Stud. Constr. Mater., vol. 20, no. March, p. e03030, 2024, doi: 10.1016/j.cscm.2024.e03030.

M. T. Moghaddam, Y. Jahani, Z. Arefzadeh, A. Dehghan, and M. Khaleghi, “Predicting diabetes in adults?: identifying important features in unbalanced data over a 5-year cohort study using machine learning algorithm,” 2024.

Y. Zhao and R. Yue, “Aging adipose tissue, insulin resistance, and type 2 diabetes,” Biogerontology, vol. 25, no. 1, pp. 53–69, 2024, doi: 10.1007/s10522-023-10067-6.

B. Arneth, “Mechanisms of Insulin Resistance in Patients with Obesity,” Endocrines, vol. 5, no. 2, pp. 153–165, 2024, doi: 10.3390/endocrines5020011.

Z. Zhai et al., “The hypertension and hyperlipidemia status among type 2 diabetic patients in the community and influencing factors analysis of glycemic control,” Diabetol. Metab. Syndr., vol. 15, no. 1, pp. 1–12, 2023, doi: 10.1186/s13098-023-01013-0.

J. Dalal et al., “Clinical and Demographic Characteristics of Patients with Coexistent Hypertension, Type 2 Diabetes Mellitus, and Dyslipidemia: A Retrospective Study from India,” Drugs - Real World Outcomes, vol. 11, no. 1, pp. 167–176, 2024, doi: 10.1007/s40801-023-00400-3.

M. A. Muhammad, J. Sani, and M. M. Ahmed, “Exploring Explainable Machine Learning for Predicting and Interpreting Self-Reported Diabetes among Tennessee Adults: Insights from the 2023 Behavioral Risk Factor Surveillance System (BRFSS),” J. Prim. Care Community Heal., vol. 16, 2025, doi: 10.1177/21501319251400546.