A cohort study on the predictive capability of body composition for diabetes mellitus using machine learning

Authors

Mohammad Ali Nematollahi 1, Amir Askarinejad 2, Arefeh Asadollahi 3, Mehdi Bazrafshan 4, Shirin Sarejloo 5, Mana Moghadami 2, Sarvin Sasannia 6, Mojtaba Farjam 3, Reza Homayounfar 3, Babak Pezeshki 3, Mitra Amini 7, Mohamad Roshanzamir 8, Roohallah Alizadehsani 9, Hanieh Bazrafshan 10, Hamed Bazrafshan Drissi 4, Ru-San Tan 11, U Rajendra Acharya 12, Mohammed Shariful Sheikh Islam 13 14 15

  1. 1Department of Computer Sciences, Fasa University, Fasa, Iran.
  2. 2Student research committee, Shiraz University of Medical Science, Shiraz, Iran.
  3. 3Noncommunicable Diseases Research Center, Fasa University of Medical Sciences, Fasa, Iran.
  4. 4Cardiovascular Research Center, Shiraz University of Medical Sciences, Shiraz, Zand St, PO Box: 71348-14336, Shiraz, Iran.
  5. 5Cardiology research Fellow at Northern Health, Northern Hospital, Melbourne, VIC Australia.
  6. 6School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran.
  7. 7Clinical Education Research Center, Shiraz University of Medical Sciences, Shiraz, Iran.
  8. 8Department of Computer Engineering, Faculty of Engineering, Fasa University, Fasa, 74617-81189 Iran.
  9. 9Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, Australia.
  10. 10Department of Neurology, Clinical Neurology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran.
  11. 11National Heart Centre Singapore, Singapore, Singapore.
  12. 12School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia.
  13. 13Institute for Physical Activity and Nutrition, School of Exercise and Nutrition Sciences, Deakin University, Geelong, VIC Australia.
  14. 14Cardiovascular Division, The George Institute for Global Health, Newtown, Australia.
  15. 15Sydney Medical School, University of Sydney, Camperdown, Australia.

Abstract

Purpose: We applied machine learning to study associations between regional body fat distribution and diabetes mellitus in a population of community adults in order to investigate the predictive capability. We retrospectively analyzed a subset of data from the published Fasa cohort study using individual standard classifiers as well as ensemble learning algorithms.

Methods: We measured segmental body composition using the Tanita Analyzer BC-418 MA (Tanita Corp, Japan). The following features were input to our machine learning model: fat-free mass, fat percentage, basal metabolic rate, total body water, right arm fat-free mass, right leg fat-free mass, trunk fat-free mass, trunk fat percentage, sex, age, right leg fat percentage, and right arm fat percentage. We performed classification into diabetes vs. no diabetes classes using linear support vector machine, decision tree, stochastic gradient descent, logistic regression, Gaussian naïve Bayes, k-nearest neighbors (k = 3 and k = 4), and multi-layer perceptron, as well as ensemble learning using random forest, gradient boosting, adaptive boosting, XGBoost, and ensemble voting classifiers with Top3 and Top4 algorithms. 4661 subjects (mean age 47.64 ± 9.37 years, range 35 to 70 years; 2155 male, 2506 female) were analyzed and stratified into 571 and 4090 subjects with and without a self-declared history of diabetes, respectively.

Results: Age, fat mass, and fat percentages in the legs, arms, and trunk were positively associated with diabetes; fat-free mass in the legs, arms, and trunk, were negatively associated. Using XGBoost, our model attained the best excellent accuracy, precision, recall, and F1-score of 89.96%, 90.20%, 89.65%, and 89.91%, respectively.

Conclusions: Our machine learning model showed that regional body fat compositions were predictive of diabetes status.

Keywords: Body composition; Cohort study; Diabetes; Machine learning.

How to Cite

Nematollahi MA, Askarinejad A, Asadollahi A, Bazrafshan M, Sarejloo S, Moghadami M, Sasannia S, Farjam M, Homayounfar R, Pezeshki B, Amini M, Roshanzamir M, Alizadehsani R, Bazrafshan H, Bazrafshan Drissi H, Tan RS, Acharya UR, Islam MSS. A cohort study on the predictive capability of body composition for diabetes mellitus using machine learning. J Diabetes Metab Disord. 2023 Nov 27;23(1):773-781. doi: 10.1007/s40200-023-01350-x. PMID: 38932891; PMCID: PMC11196543.

Metrics

A cohort study on the predictive capability of body composition for diabetes mellitus using machine learning