Home⇛Journal of Interdisciplinary Perspectives⇛vol. 3 no. 8 (2025)

Predictive Modeling of Diabetes Classification using Binomial Logistic Regression on Biomedical Indicators

Jojie E. Campugan | Melani G. Aguaras

Discipline: health studies

 

Abstract:

Diabetes mellitus remains a significant health and economic burden globally, with early detection frequently delayed in resource-limited settings such as the Philippines. Addressing this gap, the present study aimed to develop a predictive model for classifying individuals as diabetic or non-diabetic using biomedical indicators, including Body Mass Index (BMI), Low-Density Lipoprotein (LDL), Glycated Hemoglobin (HbA1c), and Triglycerides. Guided by Roy Baumeister’s Self-Regulation Theory of Illness Behavior, the study employed a multi-method classification approach involving binomial logistic regression, K-means clustering, and decision tree analysis. A total of 947 participants aged 24 to 79 years were included. K-means clustering categorized participants into two distinct groups based on biomarker profiles, differentiating those at higher and lower risk of diabetes. Logistic regression identified BMI as the most significant predictor (X2(1) = 104.44, p < .001), followed by HbA1c (X2(1) = 51.80, p < .001), Triglycerides (X2(1) = 12.44, p < .001), and LDL (X2(1) = 9.15, p = .002). The model demonstrated excellent predictive performance, with an McFadden R² of 0.80 and a Nagelkerke R² of 0.85. Decision tree analysis confirmed BMI as the primary classifier, with HbA1c enhancing classification accuracy, thereby highlighting the combined diagnostic utility of both. These findings suggest that incorporating BMI and HbA1c thresholds as accessible, cost-effective screening tools within barangay health systems could improve early identification of individuals at risk for diabetes. Integrating predictive analytics with behavior modification programs based on self-regulation theory may empower communities to adopt preventive health measures. The study recommends prioritizing risk-based screening protocols, subsidizing access to essential biomarker testing, and integrating predictive modeling frameworks into primary healthcare. This multi-method model presents a robust, scalable tool to enhance diabetes risk prediction and support targeted health interventions in underserved Philippine communities.



References:

  1. Aldubayan, M. A., Pigsborg, K., Gormsen, S. M. O., Serra, F., Palou, M., Mena, P., Wetzels, M., Calleja, A., Caimari, A., Del Bas, J., Gutierrez, B., Magkos, F., & Hjorth, M. F. (2022). Empowering consumers to PREVENT diet-related diseases through OMICS sciences (PREVENTOMICS): Protocol for a parallel double-blinded randomised intervention trial to investigate biomarker-based nutrition plans for weight loss. BMJ Open, 12(3), e051285. https://doi.org/10.1136/bmjopen-2021-051285
  2. Adua, et al., (2021). Predictive model and feature importance for early detection of type II diabetes mellitus. Translational Medicine Communications, 6(1), 17. https://doi.org/10.1186/s41231-021-00096-z
  3. Bandi, M., Masimukku, A. K., Vemula, R., & Vallu, S. (2024). Predictive analytics in healthcare: Enhancing patient outcomes through data-driven forecasting and decision making. International Numeric Journal of Machine Learning and Robots, 8(8), 1–20. https://injmr.com/index.php/fewfewf/article/view/144 
  4. Bansal, M., Goyal, A., & Choudhary, A. (2022). A comparative analysis of K-Nearest Neighbor, Genetic, Support Vector Machine, Decision Tree, and Long Short Term Memory algorithms in machine learning. Decision Analytics Journal, 3, 100071. https://doi.org/10.1016/j.dajour.2022.100071
  5. Baron, G. (2024). Diabetes a growing concern among Filipinos—DOH. Daily Tribune. https://tinyurl.com/ys7van7t 
  6. Bayman, E. O., & Dexter, F. (2021). Multicollinearity in Logistic Regression Models. Anesthesia & Analgesia, 133(2), 362–365. https://doi.org/10.1213/ANE.0000000000005593 
  7. Beaudart, C., Li, N., Hiligsmann, M., & Silverman, S. (2021). Effective risk communication and improving adherence. In E. Dennison (Ed.), Osteoporosis Treatment (pp. 115–143). Springer International Publishing. https://doi.org/10.1007/978-3-030-78128-6_8
  8. Cando, L. F., et al (2024). Current status of diabetes mellitus care and management in the Philippines. Diabetes & Metabolic Syndrome: Clinical Research & Reviews, 18(2), 102951. https://doi.org/10.1016/j.dsx.2024.102951
  9. Daily Tribune. (2024). 4.3M Filipinos living with diabetes — DOH. https://tribune.net.ph/2024/11/23/43m-filipinos-living-with-diabetes-doh
  10. Diabetes, U. K. (2006). What is diabetes? Accessed March 21.
  11. Greene, D., Palmer, M. J., & Relman, D. A. (2023). Motivating proactive biorisk management. Health Security, 21(1), 46–60. https://doi.org/10.1089/hs.2022.0101
  12. Han, F., Shi, X., Pan, J., Wu, K., Zhu, Q., Yuan, C., Xiao, W., Ding, Y., Yu, X., Jiao, X., Hu, L., Lu, G., & Li, W. (2023). Elevated serum HbA1c levels, rather than a previous history of diabetes, predict disease severity and clinical outcomes in acute pancreatitis. BMJ Open Diabetes Research & Care, 11(1), e003070. https://doi.org/10.1136/bmjdrc-2022-003070 
  13. Harris, J. K. (2021). Primer on binary logistic regression. Family Medicine and Community Health, 9(Suppl 1), e001290. https://doi.org/10.1136/fmch-2021-001290
  14. Hello Doctor. (2023). Diabetes statistics in the Philippines – Where do we stand? Hello Doctor Philippines. Retrieved May 29, 2025, from https://tinyurl.com/45k4nsy4 
  15. Hossain, Md. J., Al‐Mamun, Md., & Islam, Md. R. (2024). Diabetes mellitus, the fastest growing global public health concern: Early detection should be focused. Health Science Reports, 7(3), e2004. https://doi.org/10.1002/hsr2.2004 
  16. Johnson, J. E. (1999). Self-regulation theory and coping with physical illness. Research in Nursing & Health, 22(6), 435–448. https://doi.org/10.1002/(SICI)1098-240X(199912)22:6<435::AID-NUR2>3.0.CO;2-Q 
  17. Leary, M. R., & Tangney, J. P. (2003). The self as an organizing construct in the behavioral and social sciences. Handbook of self and identity, 15, 3–14.MIT License. (2013, 2017). Released by Mark Otto and Andrew Fong. https://opensource.org/licenses/MIT 
  18. Okosun, I. S., Davis-Smith, M., & Seale, J. P. (2012). Awareness of diabetes risks is associated with healthy lifestyle behavior in diabetes free American adults: Evidence from a nationally representative sample. Primary Care Diabetes, 6(2), 87–94. https://doi.org/10.1016/j.pcd.2011.12.005
  19. Ojulari, L. S., Sulaiman, S. E., Ayinde, T. O., & Kadir, E. R. (2023). Handgrip strength as a screening tool for diabetes in resource-constrained settings: A potential solution to overcome barriers to diagnosis. Endocrinology (including Diabetes Mellitus and Metabolic Disease). https://doi.org/10.1101/2023.10.19.23297260 
  20. Pagaddu, J. V. A. (2021). An insight on poverty reduction and health inequalities in the Philippines: Social determinants, constraints, and opportunities. Book of Life Publication. ISBN 978-621-419-265-6.
  21. Patel, M. (2025). Diabetes prediction dataset [Data set]. Kaggle. https://www.kaggle.com/datasets/marshalpatel3558/diabetes-prediction-dataset-legit-dataset 
  22. Pendrill, L. R., Melin, J., Stavelin, A., & Nordin, G. (2023). Modernising Receiver Operating Characteristic (ROC) Curves. Algorithms, 16(5), 253. https://doi.org/10.3390/a16050253 
  23. Pillai, B. (2021). Cultural Barriers. In H. Tohid & H. Maibach (Eds.), International Medical Graduates in the United States (pp. 117–124). Springer International Publishing. https://doi.org/10.1007/978-3-030-62249-7_7 
  24. Ryan, P. (2009). Integrated theory of health behavior change: Background and intervention development. Clinical Nurse Specialist, 23(3), 161–170. https://doi.org/10.1097/NUR.0b013e3181a42373 
  25. Şahi̇N, M., & Aybek, E. (2020). Jamovi: An easy-to-use statistical software for social scientists. International Journal of Assessment Tools in Education, 6(4), 670–692. https://doi.org/10.21449/ijate.661803 
  26. Sinaga, K. P., & Yang, M.-S. (2020). Unsupervised K-Means Clustering Algorithm. IEEE Access, 8, 80716–80727. https://doi.org/10.1109/ACCESS.2020.2988796 
  27. Thoolen, B. J., Ridder, D. D., Bensing, J., Gorter, K., & Rutten, G. (2009). Beyond good intentions: The role of proactive coping in achieving sustained behavioural change in the context of diabetes management. Psychology & Health, 24(3), 237–254. https://doi.org/10.1080/08870440701864504 
  28. Tolabing, MA. C. C., et al,. (2022). Prevalence of limited health literacy in the Philippines: First national survey. HLRP: Health Literacy Research and Practice, 6(2). https://doi.org/10.3928/24748307-20220419-01 
  29. Yilmaz, G. S. (2024). Does a financing scheme matter for access to healthcare service? In N. Rezaei (Ed.), Integrated Science for Sustainable Development Goal 3 (Vol. 24, pp. 49–74). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-64292-0_3 
  30. World Health Organization. (2024). Diabetes. https://www.who.int/en/news-room/fact-sheets/detail/diabetes 

Tools


Copyright © 2025  KITE Digital Educational Solutions |  Exclusively distributed by CE-Logic