Interpretable Multiclass Obesity Classification Using Optimized Logistic Regression Based on Anthropometric and Lifestyle Data
DOI:
https://doi.org/10.65780/bima.v1i2.11Keywords:
Obesity Classification, Logistic Regression, Machine Learning, Lifestyle Factors, InterpretabilityAbstract
Obesity is a global public health challenge associated with increased risks of chronic diseases and significant socioeconomic burdens. Conventional obesity classification relies predominantly on body mass index (BMI), which is static and insufficient to capture the multidimensional nature of lifestyle and behavioral factors. This study aims to develop an adaptive and interpretable machine learning–based framework for multiclass obesity classification that addresses the limitations of BMI-centered approaches. An optimized Logistic Regression model is proposed and evaluated using anthropometric and lifestyle-related features, including dietary habits and physical activity patterns. The methodology involves comprehensive data preprocessing, feature encoding, stratified data splitting, hyperparameter optimization, and performance evaluation using confusion matrix analysis, learning curves, and SHAP-based interpretability. Experimental results demonstrate that the optimized Logistic Regression model achieves a high classification accuracy of 94.26% on the test dataset, accompanied by stable generalization performance, as indicated by a relatively small generalization gap between training and validation data. Learning curve analysis confirms robust learning behavior without significant overfitting, while SHAP analysis reveals that both anthropometric and lifestyle features contribute meaningfully to classification decisions. The findings indicate that Logistic Regression offers a balanced trade-off between predictive performance, generalization ability, and interpretability. This study demonstrates that an interpretable, data-driven machine learning approach can serve as a reliable alternative to conventional obesity classification frameworks and support decision-making in health-related applications.
Downloads
References
[1] D. Mohajan and H. K. Mohajan, “Obesity and Its Related Diseases: A New Escalating Alarming in Global Health,” JIMR, vol. 2, no. 3, pp. 12–23, Mar. 2023.
[2] J. Hecker, K. Freijer, M. Hiligsmann, and S. M. a. A. Evers, “Burden of disease study of overweight and obesity; the societal impact in terms of cost-of-illness and health-related quality of life,” BMC Public Health, vol. 22, no. 1, p. 46, Dec. 2022, doi: 10.1186/s12889-021-12449-2.
[3] E. Młynarska et al., “Obesity as a Multifactorial Chronic Disease: Molecular Mechanisms, Systemic Impact, and Emerging Digital Interventions,” Current Issues in Molecular Biology, vol. 47, no. 10, Sep. 2025, doi: 10.3390/cimb47100787.
[4] E. Młynarska et al., “Obesity as a Multifactorial Chronic Disease: Molecular Mechanisms, Systemic Impact, and Emerging Digital Interventions,” Current Issues in Molecular Biology, vol. 47, no. 10, Sep. 2025, doi: 10.3390/cimb47100787.
[5] V. Nikitenko, V. Voronkova, Y. Kozar, R. Oleksenko, O. Yanchevskyi, and I. Korobko, “Digital Healthcare in the Context of Challenges and Opportunities of Technological Progress in the Countries of the European Union,” Revista de la Universidad del Zulia, vol. 14, no. 40, pp. 315–333, 2023.
[6] M. Dirik, “Application of machine learning techniques for obesity prediction: a comparative study,” Journal of Complexity in Health Sciences, vol. 6, no. 2, pp. 16–34, Dec. 2023, doi: 10.21595/chs.2023.23193.
[7] A. A. Huang, S. Y. Huang, A. A. Huang, and S. Y. Huang, “Perspective Chapter: Enhancing Regression Analysis with Splines and Machine Learning – Evaluation of How to Capture Complex Non-Linear Multidimensional Variables,” in Nonlinear Systems and Matrix Analysis - Recent Advances in Theory and Applications, IntechOpen, 2024. doi: 10.5772/intechopen.1005288.
[8] Z. Helforoush and H. Sayyad, “Prediction and classification of obesity risk based on a hybrid metaheuristic machine learning approach,” Front. Big Data, vol. 7, p. 1469981, Sep. 2024, doi: 10.3389/fdata.2024.1469981.
[9] E. O. Abiodun, A. Alabdulatif, O. I. Abiodun, M. Alawida, A. Alabdulatif, and R. S. Alkhawaldeh, “A systematic review of emerging feature selection optimization methods for optimal text classification: the present state and prospective opportunities,” Neural Comput & Applic, vol. 33, no. 22, pp. 15091–15118, Nov. 2021, doi: 10.1007/s00521-021-06406-8.
[10] Z. Helforoush and H. Sayyad, “Prediction and classification of obesity risk based on a hybrid metaheuristic machine learning approach,” Front. Big Data, vol. 7, p. 1469981, Sep. 2024, doi: 10.3389/fdata.2024.1469981.
[11] “Un-Compromised Credibility: Social Media Based Multi-Class Hate Speech Classification for Text.” Accessed: Jan. 27, 2026. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9503413
[12] H. G. G. Bag et al., “Estimation of Obesity Levels through the Proposed Predictive Approach Based on Physical Activity and Nutritional Habits,” Diagnostics, vol. 13, no. 18, Sep. 2023, doi: 10.3390/diagnostics13182949.
[13] “Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues.” Accessed: Jan. 27, 2026. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10288574
[14] A. Ferrulli, “Obesity: Classification and Diagnosis,” in Thyroid, Obesity and Metabolism, L. Luzi, Ed., Cham: Springer International Publishing, 2021, pp. 73–93. doi: 10.1007/978-3-030-80267-7_6.
[15] Y. Wu, D. Li, and S. H. Vermund, “Advantages and Limitations of the Body Mass Index (BMI) to Assess Adult Obesity,” International Journal of Environmental Research and Public Health, vol. 21, no. 6, Jun. 2024, doi: 10.3390/ijerph21060757.
[16] M. Yackobovitch-Gavan, M. Phillip, and S. Shalitin, “Comparison of WHO and CDC growth charts for defining weight status in the young population in Israel: a population-based cross-sectional study,” Isr J Health Policy Res, vol. 14, no. 1, p. 37, Jun. 2025, doi: 10.1186/s13584-025-00699-z.
