Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Pediatrics

Development and validation of a machine learning model for predicting pediatric metabolic syndrome using anthropometric and bioelectrical impedance parameters

International Journal of Obesity volume 49, pages 1159–1165 (2025)Cite this article

Subjects

Abstract

Objective

Metabolic syndrome (MS) is a risk factor for cardiovascular diseases, and its prevalence is increasing among children and adolescents. This study developed a machine learning model to predict MS using anthropometric and bioelectrical impedance analysis (BIA) parameters, highlighting its ability to handle complex, nonlinear variable relationships more effectively than traditional methods such as logistic regression.

Methods

The study included 359 youths from the Korea National Health and Nutrition Examination Survey (KNHANES; 16 MS, 343 normal) and 174 youths from real-world clinical data (66 MS, 108 normal). Model 1 used anthropometric data, Model 2 used BIA parameters, and Model 3 combined both. The eXtreme Gradient Boosting trained the models, and area under the receiver operating characteristic curve (AUC) evaluated performance. Shapley value analysis was applied to assess the contribution of each parameter to the model’s prediction.

Results

The AUCs for Models 1, 2, and 3 were 0.75, 0.66, and 0.90, respectively, in the KNHANES dataset, and 0.56, 0.61, and 0.74, respectively, in the real-world dataset. In pairwise comparison, Model 3 outperformed both Model 1 and Model 2 in both the KNHANES dataset (Model 1 vs. Model 3, p = 0.026; Model 2 vs. Model 3, p = 0.033) and the real-world dataset (Model 1 vs. Model 3, p = 0.035; Model 2 vs. Model 3, p = 0.008). Body fat mass was identified as the most significant contributor to Model 3.

Conclusion

The integrated model using both anthropometric and BIA parameters demonstrated strong predictability for pediatric MS, underlining its potential as an effective screening tool for MS in both clinical and general populations.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Study design and participant selection flowchart.
Fig. 2: AUCs for each model using data from KNHANES and YSH.
Fig. 3: Mean absolute SHAP values and dot summary plot for the contribution of variables in Model 3 from KNHANES.

Similar content being viewed by others

Data availability

The data used in this study are available on the KNHANES website (https://knhanes.kdca.go.kr/knhanes/main.do). The datasets generated during the current study are not publicly available due to considerations of safeguarding participants’ privacy, but they are available from the corresponding author upon reasonable request.

References

  1. DeBoer MD. Assessing and managing the metabolic syndrome in children and adolescents. Nutrients. 2019;11:1788.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Noubiap JJ, Nansseu JR, Lontchi-Yimagou E, Nkeck JR, Nyaga UF, Ngouo AT, et al. Global, regional, and country estimates of metabolic syndrome burden in children and adolescents in 2020: a systematic review and modelling analysis. Lancet Child Adolesc Health. 2022;6:158–70.

    Article  PubMed  Google Scholar 

  3. Park SI, Suh J, Lee HS, Song K, Choi Y, Oh JS, et al. Ten-year trends of metabolic syndrome prevalence and nutrient intake among Korean children and adolescents: a population-based study. Yonsei Med J. 2021;62:344–51.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Morrison JA, Friedman LA, Wang P, Glueck CJ. Metabolic syndrome in childhood predicts adult metabolic syndrome and type 2 diabetes mellitus 25 to 30 years later. J Pediatr. 2008;152:201–6.

    Article  CAS  PubMed  Google Scholar 

  5. Despres JP, Lemieux I. Abdominal obesity and metabolic syndrome. Nature. 2006;444:881–7.

    Article  CAS  PubMed  Google Scholar 

  6. Kim MY, An S, Shim YS, Lee HS, Hwang JS. Waist-height ratio and body mass index as indicators of obesity and cardiometabolic risk in Korean children and adolescents. Ann Pediatr Endocrinol Metab. 2024;29:182–90.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Kim JH, Yun S, Hwang SS, Shim JO, Chae HW, Lee YJ, et al. The 2017 Korean National Growth Charts for children and adolescents: development, improvement, and prospects. Korean J Pediatr. 2018;61:135–49.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Lee J, Kang SC, Kwon O, Hwang SS, Moon JS, Kim J. Reference values for waist circumference and waist-height ratio in Korean children and adolescents. J Obes Metab Syndr. 2022;31:263–71.

    Article  PubMed  PubMed Central  Google Scholar 

  9. Marra M, Sammarco R, De Lorenzo A, Iellamo F, Siervo M, Pietrobelli A, et al. Assessment of body composition in health and disease using bioelectrical impedance analysis (BIA) and dual energy X-ray absorptiometry (DXA): a critical overview. Contrast Media Mol Imaging. 2019;2019:3548284.

    Article  PubMed  PubMed Central  Google Scholar 

  10. Ramirez-Velez R, Correa-Bautista JE, Sanders-Tordecilla A, Ojeda-Pardo ML, Cobo-Mejia EA, Castellanos-Vega RDP, et al. Percentage of body fat and fat mass index as a screening tool for metabolic syndrome prediction in Colombian University students. Nutrients. 2017;9:1009.

    Article  PubMed  PubMed Central  Google Scholar 

  11. Radetti G, Fanolla A, Grugni G, Lupi F, Sartorio A. Indexes of adiposity and body composition in the prediction of metabolic syndrome in obese children and adolescents: which is the best? Nutr Metab Cardiovasc Dis. 2019;29:1189–96.

    Article  PubMed  Google Scholar 

  12. Higgins V, Adeli K. Pediatric metabolic syndrome: pathophysiology and laboratory assessment. EJIFCC. 2017;28:25–42.

    CAS  PubMed  PubMed Central  Google Scholar 

  13. Ortega-Cortes R, Trujillo X, Hurtado Lopez EF, Lopez Beltran AL, Colunga Rodriguez C, Barrera-de Leon JC, et al. Models predictive of metabolic syndrome components in obese pediatric patients. Arch Med Res. 2016;47:40–8.

    Article  PubMed  Google Scholar 

  14. Daniel Tavares L, Manoel A, Henrique Rizzi Donato T, Cesena F, Andre Minanni C, Miwa Kashiwagi N, et al. Prediction of metabolic syndrome: a machine learning approach to help primary prevention. Diabetes Res Clin Pract. 2022;191:110047.

    Article  PubMed  Google Scholar 

  15. Shin H, Shim S, Oh S. Machine learning-based predictive model for prevention of metabolic syndrome. PLoS ONE. 2023;18:e0286635.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Kim SH, Park Y, Song YH, An HS, Shin JI, Oh JH, et al. Blood pressure reference values for normal weight Korean children and adolescents: data from the Korea National Health and Nutrition Examination Survey 1998-2016: The Korean Working Group of Pediatric Hypertension. Korean Circ J. 2019;49:1167–80.

    Article  PubMed  PubMed Central  Google Scholar 

  17. Xu X, Xu N, Wang Y, Chen J, Chen L, Zhang S, et al. The longitudinal associations between bone mineral density and appendicular skeletal muscle mass in Chinese community-dwelling middle aged and elderly men. PeerJ. 2021;9:e10753.

    Article  PubMed  PubMed Central  Google Scholar 

  18. Cook S, Weitzman M, Auinger P, Nguyen M, Dietz WH. Prevalence of a metabolic syndrome phenotype in adolescents: findings from the third National Health and Nutrition Examination Survey, 1988-1994. Arch Pediatr Adolesc Med. 2003;157:821–7.

    Article  PubMed  Google Scholar 

  19. Jung SH. Sample size calculation for comparing two ROC curves. Pharm Stat. 2024;23:557–69.

    Article  PubMed  Google Scholar 

  20. Columb M, Atkinson M. Statistical analysis: sample size and power estimations. Bja Education. 2016;16:159–61.

    Article  Google Scholar 

  21. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321–57.

    Article  Google Scholar 

  22. Rodriguez JD, Perez A, Lozano JA. Sensitivity analysis of kappa-fold cross validation in prediction error estimation. IEEE Trans Pattern Anal Mach Intell. 2010;32:569–75.

    Article  PubMed  Google Scholar 

  23. Varoquaux G. Cross-validation failure: small sample sizes lead to large error bars. Neuroimage. 2018;180:68–77.

    Article  PubMed  Google Scholar 

  24. Chen T, Guestrin C. Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '16). New York, NY, USA: ACM; 2016. pp. 785–94.

  25. DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44:837–45.

    Article  CAS  PubMed  Google Scholar 

  26. Bender R, Lange S. Adjusting for multiple testing–when and how? J Clin Epidemiol. 2001;54:343–9.

    Article  CAS  PubMed  Google Scholar 

  27. Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4765–74.

  28. Zhang C, Zou X, Lin C. Fusing XGBoost and SHAP models for maritime accident prediction and causality interpretability analysis. J Mar Sci Eng. 2022;10:1154.

    Article  CAS  Google Scholar 

  29. Piramuthu S. Input data for decision trees. Expert Syst Appl. 2008;34:1220–6.

    Article  Google Scholar 

  30. Son JW, Han BD, Bennett JP, Heymsfield S, Lim S. Development and clinical application of bioelectrical impedance analysis method for body composition assessment. Obes Rev. 2025;26:e13844.

    Article  PubMed  Google Scholar 

  31. Ferreira AP, Ferreira CB, Brito CJ, Pitanga FJ, Moraes CF, Naves LA, et al. Prediction of metabolic syndrome in children through anthropometric indicators. Arq Bras Cardiol. 2011;96:121–5.

    Article  PubMed  Google Scholar 

  32. Lee YC, Lee YH, Chuang PN, Kuo CS, Lu CW, Yang KC. The utility of visceral fat level measured by bioelectrical impedance analysis in predicting metabolic syndrome. Obes Res Clin Pract. 2020;14:519–23.

    Article  PubMed  Google Scholar 

  33. Wu H, Ballantyne CM. Metabolic inflammation and insulin resistance in obesity. Circ Res. 2020;126:1549–64.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  34. Srikanthan P, Karlamangla AS. Relative muscle mass is inversely associated with insulin resistance and prediabetes. Findings from the third National Health and Nutrition Examination Survey. J Clin Endocrinol Metab. 2011;96:2898–903.

    Article  CAS  PubMed  Google Scholar 

  35. Kobayashi K. Adipokines: therapeutic targets for metabolic syndrome. Curr Drug Targets. 2005;6:525–9.

    Article  CAS  PubMed  Google Scholar 

  36. Piche ME, Poirier P, Lemieux I, Despres JP. Overview of epidemiology and contribution of obesity and body fat distribution to cardiovascular disease: an update. Prog Cardiovasc Dis. 2018;61:103–13.

    Article  PubMed  Google Scholar 

  37. Ahmed B, Sultana R, Greene MW. Adipose tissue and insulin resistance in obese. Biomed Pharmacother. 2021;137:111315.

    Article  CAS  PubMed  Google Scholar 

  38. Song K, Seol EG, Yang H, Jeon S, Shin HJ, Chae HW, et al. Bioelectrical impedance parameters add incremental value to waist-to-hip ratio for prediction of metabolic dysfunction associated steatotic liver disease in youth with overweight and obesity. Front Endocrinol. 2024;15:1385002.

    Article  Google Scholar 

  39. Boncan DAT, Yu Y, Zhang M, Lian J, Vardhanabhuti V. Machine learning prediction of hepatic steatosis using body composition parameters: a UK Biobank Study. NPJ Aging. 2024;10:4.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  40. Stump CS, Henriksen EJ, Wei Y, Sowers JR. The metabolic syndrome: role of skeletal muscle metabolism. Ann Med. 2006;38:389–402.

    Article  CAS  PubMed  Google Scholar 

  41. Ko BJ, Chang Y, Jung HS, Yun KE, Kim CW, Park HS, et al. Relationship between low relative muscle mass and coronary artery calcification in healthy adults. Arterioscler Thromb Vasc Biol. 2016;36:1016–21.

    Article  CAS  PubMed  Google Scholar 

  42. Carvalho CJ, Longo GZ, Kakehasi AM, Pereira PF, Segheto KJ, Juvanhol LL, et al. Association between skeletal mass indices and metabolic syndrome in Brazilian adults. J Clin Densitom. 2021;24:118–28.

    Article  PubMed  Google Scholar 

  43. Adejumo EN, Adejumo AO, Azenabor A, Ekun AO, Enitan SS, Adebola OK, et al. Anthropometric parameter that best predict metabolic syndrome in South west Nigeria. Diabetes Metab Syndr. 2019;13:48–54.

    Article  PubMed  Google Scholar 

  44. Alberti KG, Zimmet P, Shaw J. Group IDFETFC. The metabolic syndrome—a new worldwide definition. Lancet. 2005;366:1059–62.

    Article  PubMed  Google Scholar 

  45. Ramirez-Manent JI, Jover AM, Martinez CS, Tomas-Gil P, Marti-Lliteras P, Lopez-Gonzalez AA. Waist circumference is an essential factor in predicting insulin resistance and early detection of metabolic syndrome in adults. Nutrients. 2023;15:257.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  46. Song K, Yang J, Lee HS, Kim SJ, Lee M, Suh J, et al. Changes in the prevalences of obesity, abdominal obesity, and non-alcoholic fatty liver disease among Korean children during the COVID-19 outbreak. Yonsei Med J. 2023;64:269–77.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  47. Park KG, Park KS, Kim MJ, Kim HS, Suh YS, Ahn JD, et al. Relationship between serum adiponectin and leptin concentrations and body fat distribution. Diabetes Res Clin Pract. 2004;63:135–42.

    Article  CAS  PubMed  Google Scholar 

  48. Lee JS, Jung JM, Choi J, Seo WK, Shin HJ. Major adverse cardiovascular events in Korean congenital heart disease patients: a nationwide age- and sex-matched case-control study. Yonsei Med J. 2022;63:1069–77.

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

The authors would like to thank InBody Corporation for providing the BIA equipment.

Funding

This work was supported by the Korea Health Technology R&D Projects through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea [grant numbers: RS-2023-KH134423, RS-2023-KH134396]. This work was also supported by the Basic Medical Science Facilitation Program through the Catholic Medical Center of the Catholic University of Korea, funded by the Catholic Education Foundation.

Author information

Author notes

  1. These authors contributed equally: Youngha Choi, Kanghyuck Lee.

  2. These authors jointly supervised this work: Taehoon Ko, Kyungchul Song.

Authors and Affiliations

  1. Department of Pediatrics, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul, Republic of Korea

    Youngha Choi, Joon Young Kim, Hyun Wook Chae & Kyungchul Song

  2. Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea

    Kanghyuck Lee & Taehoon Ko

  3. Department of Pediatrics, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin-si, Republic of Korea

    Eun Gyung Seol & Eun Byoul Lee

  4. Department of Medical Sciences, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea

    Taehoon Ko

  5. CMC Institute for Basic Medical Science, The Catholic Medical Center of The Catholic University of Korea, Seoul, Republic of Korea

    Taehoon Ko

Authors
  1. Youngha Choi
    View author publications

    Search author on:PubMed Google Scholar

  2. Kanghyuck Lee
    View author publications

    Search author on:PubMed Google Scholar

  3. Eun Gyung Seol
    View author publications

    Search author on:PubMed Google Scholar

  4. Joon Young Kim
    View author publications

    Search author on:PubMed Google Scholar

  5. Eun Byoul Lee
    View author publications

    Search author on:PubMed Google Scholar

  6. Hyun Wook Chae
    View author publications

    Search author on:PubMed Google Scholar

  7. Taehoon Ko
    View author publications

    Search author on:PubMed Google Scholar

  8. Kyungchul Song
    View author publications

    Search author on:PubMed Google Scholar

Contributions

YC and KL conceptualized and designed the study, carried out the analyses, and drafted the initial manuscript. EGS, JYK, and EBL designed the data collection instruments, and collected data. HWC contributed to the important intellectual content during manuscript drafting and revision. TK and KS contributed to the important intellectual content during manuscript drafting and revision, reviewed and revised the manuscript. YC and KL contributed equally to this work as co-first authors. TK and KS contributed equally to this work as co-corresponding authors. All authors approved the final manuscript as submitted and agree to be accountable for all aspects of the work.

Corresponding authors

Correspondence to Taehoon Ko or Kyungchul Song.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval and consent to participate

All methods were performed in accordance with the relevant guidelines and regulations. This study was conducted according to the Declaration of Helsinki and was approved by the Institutional Review Board of Yonsei University Gangnam Severance Hospital (IRB No. 3-2024-0220). For KNHANES participants, informed consent was obtained as part of the national survey protocol. For Yongin Severance Hospital patients, the requirement for informed consent was waived by the IRB due to the retrospective nature of the study.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Choi, Y., Lee, K., Seol, E.G. et al. Development and validation of a machine learning model for predicting pediatric metabolic syndrome using anthropometric and bioelectrical impedance parameters. Int J Obes 49, 1159–1165 (2025). https://doi.org/10.1038/s41366-025-01761-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41366-025-01761-1

Search

Advanced search

Quick links