Journal of Korean Biological Nursing Science

Korean society of Biological Nursing Science (한국기초간호학회)
권호 표지
DOI QR코드

DOI QR Code

Development and validation of machine learning models to predict prediabetes using dietary intake data in young adults in Korea: a cross-sectional study

  • Received : 2024.10.11
  • Accepted : 2024.10.30
  • Published : 2024.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: This study aimed to develop and compare machine learning models for predicting prediabetes in young adults in Korea using dietary intake data and to identify the most effective model. Methods: Data from the ninth Korea National Health and Nutrition Examination Survey were used, with 823 participants aged 19-35 years selected after excluding those with missing data. Logistic regression, k-nearest neighbors, and random forest models were applied to predict prediabetes, and the analysis was conducted using the Orange 3.5 program. Five-fold cross-validation was performed to reduce performance variability, and test data were used for final model validation. Results: In the dataset, 14%-15% of participants were classified as having prediabetes. The random forest model showed the highest performance in terms of classification accuracy, harmonic mean of precision and recall, and precision. Logistic regression had the highest performance regarding the model's ability to distinguish between individuals with and without prediabetes. Age, thiamine intake, and water intake emerged as the most important predictors. Conclusion: This study demonstrated the utility of using dietary intake data to predict prediabetes in young adults. The random forest model provided the highest prediction accuracy, supporting early detection and intervention, which could help to reduce unnecessary treatment. This highlights nurses' important role in educating patients about lifestyle changes and implementing preventive care. Future studies should incorporate additional factors, such as psychological and lifestyle variables, to improve the model's performance.

Keywords

Acknowledgement

The author would like to express their sincere gratitude to the Korea Disease Control and Prevention Agency for providing the essential data for this study, as well as to all the participants of the Korea National Health and Nutrition Examination Survey for their valuable contributions.

References

  1. World Health Organization. Diabetes [Internet]. Geneva: World Health Organization; 2023 [cited 2024 Sep 9]. Available from: https://www.who.int/health-topics/diabetes/diabetes#tab= tab_1
  2. Choi HH, Choi G, Yoon H, Ha KH, Kim DJ. Rising incidence of diabetes in young adults in South Korea: a national cohort study. Diabetes & Metabolism Journal. 2022;46(5):803-807. https://doi.org/10.4093/dmj.2021.0236
  3. Lee KA, Kim DJ, Han K, Chon S, Moon MK. Screening for prediabetes and diabetes in Korean nonpregnant adults: a position statement of the Korean Diabetes Association, 2022. Diabetes & Metabolism Journal. 2022;46(6):819-826. https://doi.org/10.4093/dmj.2022.0364
  4. Jang BN, Nari F, Kim S, Park EC. Association between relative handgrip strength and prediabetes among South Korean adults. PLoS One. 2020;15(10). https://doi.org/10.1371/journal.pone.0240027
  5. Bostock-Cox B. Understanding the link between obesity and diabetes. Nursing Standard. 2017;31(44):52-62. https://doi.org/10.7748/ns.2017.e10106
  6. Puccinelli PJ, da Costa TS, Seffrin A, de Lira CAB, Vancini RL, Nikolaidis PT, et al. Reduced level of physical activity during COVID-19 pandemic is associated with depression and anxiety levels: an internet-based survey. BMC Public Health. 2021;21:10470. https://doi.org/10.1186/s12889-021-10470-z
  7. Nour TY, Altintaş KH. Effect of the COVID-19 pandemic on obesity and its risk factors: a systematic review. BMC Public Health. 2023;23:15833. https://doi.org/10.1186/s12889-023-15833-2
  8. Saravia L, Moliterno P, Skapino E, Moreno LA. Food diary, food frequency questionnaire, and 24-hour dietary recall. In: Betim Cazarin CB, editors. Basic Protocols in Foods and Nutrition. Methods and Protocols in Food Science. New York, NY: Humana; 2022 p. 223-247.
  9. Foster E, Lee C, Imamura F, Hollidge SE, Westgate KL, Venables MC, et al. Validity and reliability of an online self-report 24-h dietary recall method (Intake24): a doubly labelled water study and repeated-measures analysis. Journal of Nutritional Science. 2019;8:e29. https://doi.org/10.1017/jns.2019.20
  10. Bantle JP, Wylie-Rosett J, Albright AL, Apovian CM, Clark NG, Franz MJ, et al. Nutrition recommendations and interventions for diabetes: a position statement of the American Diabetes Association. Diabetes Care. 2008;31(Suppl 1):S61-S78. https://doi.org/10.2337/dc08-S061
  11. Neuenschwander M, Ballon A, Weber KS, Norat T, Aune D, Schwingshackl L, et al. Role of diet in type 2 diabetes incidence: umbrella review of meta-analyses of prospective observational studies. BMJ. 2019;366:l2368. https://doi.org/10.1136/bmj.l2368
  12. Al-Jarrah OY, Yoo PD, Muhaidat S, Karagiannidis GK, Taha K. Efficient machine learning for big data: a review. Big Data Research. 2015;2(3):87-93. https://doi.org/10.1016/j.bdr.2015.04.001
  13. Korea Disease Control and Prevention Agency. The Korea National Health and Nutrition Examination Survey (KNHANES), 2022 [Internet]. Cheongju: Korea Disease Control and Prevention Agency; 2022 [cited 2024 Sep 9]. Available from: https://knhanes.kdca.go.kr/knhanes/sub03/sub03_06_02.do.
  14. Kim G. ORANGE for artificial intelligence and data analysis. 1st ed. Seoul: Hankyungsa; 2024.
  15. University of Ljubljana, Bioinformatics Laboratory. Orange data mining: data mining fruitful and fun [Internet]. University of Ljubljana [cited 2024 Oct 1]. Available from: https://orangedatamining.com
  16. Bharathidason S, Venkataeswaran CJ. Improving classification accuracy based on random forest model with uncorrelated high performing trees. International Journal of Computer Applications. 2014;101(26):26-30. https://doi.org/10.5120/17749-8829
  17. Marchese Robinson RL, Palczewska A, Palczewski JA, Kidley N. Comparison of the predictive performance and interpretability of random forest and linear models on benchmark data sets. Journal of Chemical Information and Modeling. 2017;57(8):1773-1792. https://doi.org/10.1021/acs.jcim.6b00753
  18. Norton M, Uryasev S. Maximization of AUC and buffered AUC in binary classification. Mathematical Programming. 2018;174:575-612. https://doi.org/10.1007/s10107-018-1312-2
  19. Marius OU, Ibezimako MJ. Estimation of AUC and its significance in the assessment of classification models. Journal of Natural Sciences Research. 2019;9(9):17-29. https://doi.org/10.7176/JNSR/9-9-03
  20. Lu T. Research on the variable selection methods based on random forests. 2022 7th International Conference on Computational Intelligence and Applications (ICCIA); 2022 Jun 24-26; Nanjing, China. IEEE; 2022. p. 59-64.
  21. Han H, Guo X, Yu H. Variable selection using mean decrease accuracy and mean decrease Gini based on random forest. 2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS); 2016 Aug 26-28; Beijing, China. IEEE; 2016. p. 219-224.
  22. Chow H, Shi M, Cheng A, Gao Y, Chen G, Song X, et al. Age-related hyperinsulinemia leads to insulin resistance in neurons and cell-cycle-induced senescence. Nature Neuroscience. 2019;22(12):1806-1819. https://doi.org/10.1038/s41593-019-0505-1
  23. Jääskeläinen T, Koponen P, Lundqvist A, Borodulin K, Koskinen S. Lifestyle of young adults-changes and accumulation. European Journal of Public Health. 2019;29(Suppl 4). https://doi.org/10.1093/eurpub/ckz185.113
  24. Abdullah KM, Arefeen A, Shamsi A, Alhumaydhi F, Naseem I. Insight into the in vitro antiglycation and in vivo antidiabetic effects of thiamine: implications of vitamin B1 in controlling diabetes. ACS Omega. 2021;6(19):12605-12614. https://doi.org/10.1021/acsomega.1c00631
  25. Seal A, Colburn AT, Suh HG, Kavouras S. The acute effect of adequate water intake on glucose regulation in low drinkers. Annals of Nutrition and Metabolism. 2022;77(suppl 4):33-36. https://doi.org/10.1159/000520479
  26. Park MH, Chung SJ, Shim JE, Jang SH, Nam KS. Effects of macronutrients in mixed meals on postprandial glycemic response. Journal of Nutrition and Health. 2018;51(1):31-39. https://doi.org/10.4163/jnh.2018.51.1.31
  27. Osadchiy T, Poliakov I, Olivier P, Rowland M, Foster E. Progressive 24-hour recall: usability study of short retention intervals in web-based dietary assessment surveys. Journal of Medical Internet Research. 2020;22(2):1-12. https://doi.org/10.2196/13266