Neural networks to predict Body Mass Index according to height and waist circumference
Keywords:
abdominal circumference, body mass index, body weigh, computational neural networks, computer-assisted decision making, heightAbstract
Introduction: The Body Mass Index (BMI) is an indicator of risk of suffering from diseases associated with excess body fat.
Objective: To evaluate the neural network as a predictor of BMI according to height and waist circumference.
Methods: Analytical, and cross-sectional study of 2004 Venezuelan adults belonging to the Prevalence of Metabolic Syndrome study of the City of Maracaibo. The variables were BMI, height and waist circumference. Multilayer perceptron-type neural networks were used, evaluated using scatter-plots, receiver operating characteristic curve and classification tables.
Results: For quantitative BMI, the relative error was 0.191 and 0.180 in training and testing, respectively. For BMI categories, the percentage of incorrect predictions in training and testing were 25.50% and 20.80%, respectively. The neural network developed to quantitatively predict the BMI from height and waist circumference had an R2 coefficient of 0.812 and qualitatively, an area under the curve of 0.968, 0.919, 0.844 and 0.950 for low weight, normal weight, overweight, and obesity, respectively. The neural network to predict BMI categories had percentages of correct predictions of 37.50%, 74%, 79.80% and 84.40% for underweight, normal weight, overweight, and obesity, respectively.
Conclusions: The use of multilayer perceptron-type neural networks is efficient to predict the BMI quantitatively and qualitatively from height and waist circumference.
Downloads
References
Wu Y, Li D, Vermund SH. Advantages and limitations of the body mass index (BMI) to assess adult obesity [Internet]. Int J Environ Res Public Health. 2024;21(6):757. DOI: 10.3390/ijerph21060757
Wondmkun YT. Obesity, insulin resistance, and type 2 diabetes: Associations and therapeutic implications [Internet]. Diabetes Metab Syndr Obes. 2020;13:3611-6. DOI: 10.2147/dmso.s275898
Stone TW, McPherson M, Gail Darlington L. Obesity and cancer: Existing and new hypotheses for a causal connection [Internet]. EBioMedicine. 2018;30:14-28. DOI: 10.1016/j.ebiom.2018.02.022
Bellows CF, Zhang Y, Chen J, Frazier ML, Kolonin MG. Circulation of progenitor cells in obese and lean colorectal cancer patients [Internet]. Cancer Epidemiol Biomarkers Prev. 2011; 20(11):2461-8. DOI: 10.1158/1055-9965.epi-11-0556
Held C, Hadziosmanovic N, Aylward PE, Hagström E, Hochman JS, Stewart RAH, et al. Body mass index and association with cardiovascular outcomes in patients with stable coronary heart disease - A STABILITY substudy [Internet]. J Am Heart Assoc. 2022;11(3): e023667. DOI: 10.1161/jaha.121.023667
Leppänen T, Kulkas A, Mervaala E, Töyräs J. Increase in body mass index decreases duration of apneas and hypopneas in obstructive sleep apnea [Internet]. Respir Care. 2019;64(1):77-84. DOI: 10.4187/respcare.06297
Vaishnav B. Gastroesophageal reflux disease and its association with body mass index: Clinical and endoscopic study [Internet]. J Clin Diagn Res. 2017; DOI: 10.7860/jcdr/2017/24151.9562
Zhu L, Zhou B, Zhu X, Cheng F, Pan Y, Zhou Y, et al. Association between body mass index and female infertility in the United States: Data from national health and nutrition examination survey 2013-2018 [Internet]. Int J Gen Med. 2022;15:1821-31. DOI: 10.2147/ijgm.s349874
CDC. Adult BMI calculator [Internet]. Centers for Disease Control and Prevention. 2024. [acceso: 26/09/2024]. Disponible en: https://www.cdc.gov/healthyweight/assessing/bmi/adult_bmi/english-_bmi_calculator/bmi_calculator.html
Overweight and obesity: prevalence Venezuela 2010-2022 [Internet]. Statista. 2023. [acceso: 26/09/2024]. Disponible en: https://www.statista.com/statistics/1466625/overweight-obesity-prevalence-venezuela/
Bikku T. Multi-layered deep learning perceptron approach for health risk prediction [Internet]. J Big Data. 2020;7(1):[aprox. 24 p.]. DOI: 10.1186/s40537-020-00316-7
Salazar J, Bermúdez V, Calvo M, Olivar LC, Luzardo E, Navarro C, et al. Optimal cutoff for the evaluation of insulin resistance through triglyceride-glucose index: A cross-sectional study in a Venezuelan population [Internet]. F1000Res. 2018; 6:1337. DOI: 10.12688/f1000research.12170.3
Nuttall FQ. Body mass index: Obesity, BMI, and health A critical review [Internet]. Nutr Today. 2015;50(3):117-28. DOI: 10.1097/nt.0000000000000092
Alexander DLJ, Tropsha A, Winkler DA. Beware of R2: Simple, unambiguous assessment of the prediction accuracy of QSAR and QSPR models [Internet]. J Chem Inf Model. 2015;55(7):1316-22. DOI: 10.1021/acs.jcim.5b00206
Kurisu K, Yamazaki T, Yoshiuchi K. Predicting extremely low body weight from 12-lead electrocardiograms using a deep neural network [Internet]. Sci Rep. 2024 [acceso: 26/09/2024];14(1):1-8. Disponible en: https://www.nature.com/articles/s41598-024-55453-3
Freitag E, Edgecombe G, Baldwin I, Cottier B, Heland M. Determination of body weight and height measurement for critically ill patients admitted to the intensive care unit: A quality improvement project [Internet]. Aust Crit Care. 2010;23(4):197-207. DOI: 10.1016/j.aucc.2010.04.003
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Alberto Guevara Tirado
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who have publications with this Journal accept the following terms:
- The authors will retain their copyright and guarantee the Journal the right of first publication of their work, which will simultaneously be subject to the Creative Commons Attribution License. The content presented here can be shared, copied and redistributed in any medium or format; Can be adapted, remixed, transformed or created from the material, using the following terms: Attribution (giving appropriate credit to the work, providing a link to the license, and indicating if changes have been made); non-commercial (you cannot use the material for commercial purposes) and share-alike (if you remix, transform or create new material from this work, you can distribute your contribution as long as you use the same license as the original work).
- The authors may adopt other non-exclusive license agreements for the distribution of the published version of the work (for example: depositing it in an institutional electronic archive or publishing it in a monographic volume) as long as the initial publication in this Journal is indicated.
- Authors are allowed and recommended to disseminate their work through the Internet (e.g., in institutional electronic archives or on their website) before and during the submission process, which can produce interesting exchanges and increase citations. of the published work.
