Enhancing Gradient Boosting Performance for Obesity Prediction Through Body Mass Index Feature Engineering

Bima Sakti Khaharrasul; Usman Sudibyo

doi:10.57152/malcom.v6i4.2960

Authors

Bima Sakti Khaharrasul Universitas Dian Nuswantoro
Usman Sudibyo Universitas Dian Nuswantoro

DOI:

https://doi.org/10.57152/malcom.v6i4.2960

Keywords:

Body Mass Index, Data-Centric AI, Feature Engineering, Gradient Boosting, Obesity Classification

Abstract

Tree-based algorithms like Gradient Boosting face architectural limitations in implicitly mapping non-linear feature interactions (such as height-to-weight ratios), reducing accuracy across ambiguous obesity classification boundaries. Adopting a data-centric AI paradigm, this study aims to resolve this by executing a Domain-Knowledge Injection of the Body Mass Index (BMI) feature explicitly during preprocessing. Utilizing a self-reported survey dataset of 2,111 records and 17 attributes, the experiment compares a baseline control framework (without BMI) against the proposed model (with BMI) using a default Gradient Boosting Classifier and Stratified 5-Fold Cross-Validation. The dataset contains seven categories of body weight/obesity. Stratification techniques ensure that each fold maintains the same class ratios or percentages as the original dataset. This prevents bias arising from dominant or underrepresented classes during testing. The results show that global model accuracy surged from 95.04% to 98.34% (a +3.3% absolute increase), with a stable mean cross-validation accuracy of 97.06%. At a granular level, the engineered BMI feature acts as a rigid physical anchor that eliminates the ambiguity of overlapping behavioral data. This study concludes that structural interventions within the data pipeline via domain-informed feature extraction are significantly more effective and computationally efficient for optimizing model accuracy than expanding algorithmic complexity.

Downloads

Download data is not yet available.

References

V. J. Antipatis and T. P. Gill, “Obesity as a global problem,” Int. Textb. Obes., pp. 1–22, 2001.

WHO`, “Obesity and Overweight,” 2025, [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/obesity-and-overweight

M. J. Davies et al., “Type 2 diabetes mellitus,” Nat. Rev. Dis. Prim., vol. 12, no. 1, p. 13, 2026, doi: 10.1038/s41572-026-00687-w.

K. Khunti et al., “Diabetes and Multiple Long-term Conditions: A Review of Our Current Global Health Challenge,” Diabetes Care, vol. 46, no. 12, pp. 2092–2101, 2023, doi: 10.2337/dci23-0035.

M. A. Nagi et al., “Economic costs of obesity: a systematic review,” Int. J. Obes., vol. 48, no. 1, pp. 33–43, 2024, doi: 10.1038/s41366-023-01398-y.

WHO, “World Obesity Atlas 2023,” World Obes. Fed., no. March, pp. 5–25, 2023, [Online]. Available: www.johnclarksondesign.co.uk

F. Haghayegh et al., “Revolutionary Point-of-Care Wearable Diagnostics for Early Disease Detection and Biomarker Discovery through Intelligent Technologies,” Adv. Sci., vol. 11, no. 36, 2024, doi: 10.1002/advs.202400595.

M. C. Roberts, K. E. Holt, G. Del Fiol, A. A. Baccarelli, and C. G. Allen, “Precision public health in the era of genomics and big data,” Nat. Med., vol. 30, no. 7, pp. 1865–1873, 2024, doi: 10.1038/s41591-024-03098-0.

M. Moltrer, L. Pala, C. Cosentino, E. Mannucci, C. M. Rotella, and B. Cresci, “Body mass index (BMI), waist circumference (WC), waist-to-height ratio (WHtR) e waist body mass index (wBMI): Which is better?,” Endocrine, vol. 76, no. 3, pp. 578–583, Jun. 2022, doi: 10.1007/s12020-022-03030-x.

WHO, “World Health Organization, The Asia-Pacific perspective: redefining obesity and its treatment.,” 2000, Health Communication Australia, Sydney.

F. Q. Nuttall, “Body Mass Index: Obesity, BMI, and Health: A Critical Review.,” Nutr. Today, vol. 50, no. 3, pp. 117–128, May 2015, doi: 10.1097/NT.0000000000000092.

J. P. Bennett and S. Lim, “The critical role of body composition assessment in advancing research and clinical health risk assessment across the lifespan,” J. Obes. Metab. Syndr., vol. 34, no. 2, p. 120, 2025.

J. P. Bennett, M. Lee, and M. Tallquist, “Emerging Applications in the Measurement of Body Composition and Their Relationships to Disease Risk,” no. May 2023.

S. Essahraui et al., “Human behavior analysis: A comprehensive survey on techniques, applications, challenges, and future directions,” IEEE Access, 2025.

G. Airlangga, “Machine Learning-Based Obesity Classification?: A Comparative Study Using Self-Reported Survey Data and Ensemble Learning Models Abstrak,” vol. 11, no. 1, pp. 347–361, 2025.

Y. Görmez, F. H. Yagin, B. Yagin, and Y. Aygun, “Prediction of obesity levels based on physical activity and eating habits with a machine learning model integrated with explainable artificial intelligence,” no. July, pp. 1–15, 2025, doi: 10.3389/fphys.2025.1549306.

W. M. Shaban, H. El-Din Moustafa, and M. M. El-Seddek, “Machine learning framework for predicting susceptibility to obesity,” Sci. Rep., vol. 15, no. 1, pp. 1–34, 2025, doi: 10.1038/s41598-025-20505-9.

S. M. Ganie, B. B. Reddy, H. K, and M. Rege, “An investigation of ensemble learning techniques for obesity risk prediction using lifestyle data,” Decis. Anal. J., vol. 14, p. 100539, 2025, doi: https://doi.org/10.1016/j.dajour.2024.100539.

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, 2024.

Y. Wu, D. Li, and S. H. Vermund, “Advantages and Limitations of the Body Mass Index (BMI) to Assess Adult Obesity.,” Int. J. Environ. Res. Public Health, vol. 21, no. 6, Jun. 2024, doi: 10.3390/ijerph21060757.

S. Albahra et al., “Artificial Intelligence and Machine Learning Overview in Pathology & Laboratory Medicine: A General Review of Data Preprocessing and Basic Supervised Concepts,” Semin. Diagn. Pathol., vol. 40, Feb. 2023, doi: 10.1053/j.semdp.2023.02.002.

S. B. Heymsfield et al., “Bimagrumab plus semaglutide alone or in combination for the treatment of obesity: a randomized phase 2 trial.,” Nat. Med., vol. 32, no. 3, pp. 869–882, Mar. 2026, doi: 10.1038/s41591-026-04204-0.

D. Zha et al., “Data-centric Artificial Intelligence: A Survey,” ACM Comput. Surv., vol. 57, no. 5, 2025, doi: 10.1145/3711118.

D. Mohajan and H. K. Mohajan, “Body mass index (BMI) is a popular anthropometric tool to measure obesity among adults,” J. Innov. Med. Res., vol. 2, no. 4, pp. 25–33, 2023.

A. I. Adler and A. Painsky, “Feature Importance in Gradient Boosting Trees with Cross-Validation Feature Selection,” 2022. doi: 10.3390/e24050687.

Centers for Disease Control and Prevention., “About Adult BMI.” [Online]. Available: https://www.cdc.gov/bmi/adult-calculator/