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

Autor: Nematollahi MA; Department of Computer Sciences, Fasa University, Fasa, Iran., Askarinejad A; Student research committee, Shiraz University of Medical Science, Shiraz, Iran., Asadollahi A; Noncommunicable Diseases Research Center, Fasa University of Medical Sciences, Fasa, Iran., Bazrafshan M; Cardiovascular Research Center, Shiraz University of Medical Sciences, Shiraz, Zand St, PO Box: 71348-14336, Shiraz, Iran., Sarejloo S; Cardiology research Fellow at Northern Health, Northern Hospital, Melbourne, VIC Australia., Moghadami M; Student research committee, Shiraz University of Medical Science, Shiraz, Iran., Sasannia S; School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran., Farjam M; Noncommunicable Diseases Research Center, Fasa University of Medical Sciences, Fasa, Iran., Homayounfar R; Noncommunicable Diseases Research Center, Fasa University of Medical Sciences, Fasa, Iran., Pezeshki B; Noncommunicable Diseases Research Center, Fasa University of Medical Sciences, Fasa, Iran., Amini M; Clinical Education Research Center, Shiraz University of Medical Sciences, Shiraz, Iran., Roshanzamir M; Department of Computer Engineering, Faculty of Engineering, Fasa University, Fasa, 74617-81189 Iran., Alizadehsani R; Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, Australia., Bazrafshan H; Department of Neurology, Clinical Neurology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran., Bazrafshan Drissi H; Cardiovascular Research Center, Shiraz University of Medical Sciences, Shiraz, Zand St, PO Box: 71348-14336, Shiraz, Iran., Tan RS; National Heart Centre Singapore, Singapore, Singapore., Acharya UR; School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia., Islam MSS; Institute for Physical Activity and Nutrition, School of Exercise and Nutrition Sciences, Deakin University, Geelong, VIC Australia.; Cardiovascular Division, The George Institute for Global Health, Newtown, Australia.; Sydney Medical School, University of Sydney, Camperdown, Australia.
Jazyk: angličtina
Zdroj: Journal of diabetes and metabolic disorders [J Diabetes Metab Disord] 2023 Nov 27; Vol. 23 (1), pp. 773-781. Date of Electronic Publication: 2023 Nov 27 (Print Publication: 2024).
DOI: 10.1007/s40200-023-01350-x
Abstrakt: 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.
Competing Interests: Conflict of interestThe authors declare no competing interests.
(© The Author(s), under exclusive licence to Tehran University of Medical Sciences 2023. 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.)
Databáze: MEDLINE
Externí odkaz: