An application of CART algorithms for detection of an association between VDR polymorphisms and reduced bone density in individuals with type 2 diabetes: a population-based cross-sectional study
-
Maryam Ghodsi
,
Bagher Larijani
,
Shahin Roshani
,
Mahsa Mohammad Amoli
,
Farideh Razi
,
Abbas Ali Keshtkar
,
Patricia Khashayar
,
Fariba Zarrabi
,
Mohammad Reza Mohajeri-Tehrani
Abstract
Background. An important part of preventing major common diseases is identifying genetic factors that contribute to their occurrence. For the first time in our knowledge, we investigated the association between polymorphisms of five vitamin D receptor (VDR) genes (ApaI, BsmI, FokI, EcoRV, and TaqI) and low bone density/osteopenia/osteoporosis in individuals with type 2 diabetes using classification and regression tree (CART) algorithms.
Methods. Data from 158 participants with T2D were used to develop the CART analysis. The binary output variable was "bone state" with low or normal values. Age and BMI (continuous variables), vitamin D deficiency (yes/no), and gender (binary variables), as well as polymorphisms of the five VDR genes (categorical variables) all played a role in the explanatory model. A 10-fold cross-validation process was used for model validation.
Results. Participants were divided into three groups based on their sex. In all groups, age was the major factor predicting the low state in the final obtained tree model. The second most significant predictor in each model was BMI in both sexes (accuracy:75.32% and, AUC:0.748), EcoRV polymorphism in women (accuracy:78.79 %, AUC: 0.794), and TaqI polymorphism in men (accuracy:71.19%, AUC: 0.651).
Conclusion Model validation of the final tree models demonstrated that the use of CART algorithms could be a valuable technique for identifying individuals with T2D who are at risk for early-onset osteoporosis based on their polymorphism of the studied VDR genes. Our recommendation is to conduct more population-based studies. We hope this study will serve as a basis for future research.
Man SC, Chiriac M, Militaru MS, Trifa AP, Goia-Socol M, Georgescu CE. Association of Col1a1 Sp1 and Fok-I Vdr Genetic Polymorphisms in Young Male Idiopathic Osteoporosis. Acta endocrinologica. 2017;13(2):224-7.
Bellazzi R, Ferrazzi F, Sacchi L. Predictive data mining in clinical medicine: a focus on selected methods and applications. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. 2011;1(5):416-30.
Horst-Sikorska W, Dytfeld J, Wawrzyniak A, Marcinkowska M, Michalak M, Franek E, et al. Vitamin D receptor gene polymorphisms, bone mineral density and fractures in postmenopausal women with osteoporosis. Mol Biol Rep. 2013;40(1):383-90.
Pouresmaeili F, Kamalidehghan B, Kamarehei M, Goh YM. A comprehensive overview on osteoporosis and its risk factors. Ther Clin Risk Manag. 2018;14:2029-49.
Angel B, Lera L, Marquez C, Albala C. The association of VDR polymorphisms and type 2 diabetes in older people living in community in Santiago de Chile. Nutr Diabetes. 2018;8(1):31.
Al-Daghri NM, Al-Attas O, Alokail MS, Alkharfy KM, Draz HM, Agliardi C, et al. Vitamin D receptor gene polymorphisms and HLA DRB1*04 cosegregation in Saudi type 2 diabetes patients. J Immunol. 2012;188(3):1325-32.
Ortlepp JR, Lauscher J, Hoffmann R, Hanrath P, Joost HG. The vitamin D receptor gene variant is associated with the prevalence of type 2 diabetes mellitus and coronary artery disease. Diabetic medicine : a journal of the British Diabetic Association. 2001;18(10):842-5.
Malik R, Farooq R, Mehta P, Ishaq S, Din I, Shah P, et al. Association of Vitamin D Receptor Gene Polymorphism in Adults With Type 2 Diabetes in the Kashmir Valley2017.
Neyestani TR, Djazayery A, Shab-Bidar S, Eshraghian MR, Kalayi A, Shariatzadeh N, et al. Vitamin D Receptor Fok-I polymorphism modulates diabetic host response to vitamin D intake: need for a nutrigenetic approach. Diabetes Care. 2013;36(3):550-6.
Gnanaprakash V, Bodhini D, Kanthimathi S, Ginivenisha K, Shanthirani CS, Anjana RM, et al. Association of Vitamin D receptor (TaqI, BsmI, and FokI) polymorphisms with prediabetes and Type 2 diabetes in Asian Indians. Journal of Diabetology. 2019;10(1):29.
Shab-Bidar S, Neyestani TR, Djazayery A. Vitamin D Receptor Gene Polymorphisms, Metabolic Syndrome, and Type 2 Diabetes in Iranian Subjects: No Association with Observed SNPs. International journal for vitamin and nutrition research Internationale Zeitschrift fur Vitamin- und Ernahrungsforschung Journal international de vitaminologie et de nutrition. 2016;86(1-2):71-80.
Malecki MT, Frey J, Moczulski D, Klupa T, Kozek E, Sieradzki J. Vitamin D receptor gene polymorphisms and association with type 2 diabetes mellitus in a Polish population. Experimental and clinical endocrinology & diabetes : official journal, German Society of Endocrinology [and] German Diabetes Association. 2003;111(8):505-9.
Breiman L, Friedman J, Olshen R, Stone C. Classification and Regression Trees (Wadsworth and Brooks/Cole, Pacific Grove, CA). CA Mathematical Reviews (MathSciNet): MR86b. 1984;62101.
Speybroeck N, Berkvens D, Mfoukou-Ntsakala A, Aerts M, Hens N, Van Huylenbroeck G, et al. Classification trees versus multinomial models in the analysis of urban farming systems in Central Africa. Agr Syst. 2004;80(2):133-49.
Keshtkar A, Khashayar P, Mohammadi Z, Etemad K, Dini M, Aghaei Meybodi H, et al. A Suggested Prototype for Assessing Bone Health. Arch Iran Med. 2015;18(7):411-5.
Demmer RT, Zuk AM, Rosenbaum M, Desvarieux M. Prevalence of diagnosed and undiagnosed type 2 diabetes mellitus among US adolescents: results from the continuous NHANES, 1999-2010. American journal of epidemiology. 2013;178(7):1106-13.
DeShields SC, Cunningham TD. Comparison of osteoporosis in US adults with type 1 and type 2 diabetes mellitus. J Endocrinol Invest. 2018;41(9):1051-60.
Dimai HP. Use of dual-energy X-ray absorptiometry (DXA) for diagnosis and fracture risk assessment; WHO-criteria, T- and Z-score, and reference databases. Bone. 2017;104:39-43.
Holick MF, Binkley NC, Bischoff-Ferrari HA, Gordon CM, Hanley DA, Heaney RP, et al. Evaluation, treatment, and prevention of vitamin D deficiency: an Endocrine Society clinical practice guideline. The Journal of clinical endocrinology and metabolism. 2011;96(7):1911-30.
Donders AR, van der Heijden GJ, Stijnen T, Moons KG. Review: a gentle introduction to imputation of missing values. Journal of clinical epidemiology. 2006;59(10):1087-91.
Lang TA, Altman DG. Basic statistical reporting for articles published in biomedical journals: the "Statistical Analyses and Methods in the Published Literature" or the SAMPL Guidelines. Int J Nurs Stud. 2015;52(1):5-9.
Prasad DVV, Venkataramana L, Balasubramanian P, Priyankha B, Rajagopal S, Dattuluri R, editors. An efficient pre-processing method for improved classification of diabetics using decision tree and artificial neural network. AIP Conference Proceedings; 2019: AIP Publishing LLC.
Khosla S, Riggs BL. Pathophysiology of age-related bone loss and osteoporosis. Endocrinology and metabolism clinics of North America. 2005;34(4):1015-30, xi.
Odegard PS, Janci MM, Foeppel MP, Beach JR, Trence DL. Prevalence and correlates of dietary supplement use in individuals with diabetes mellitus at an academic diabetes care clinic. The Diabetes Educator. 2011;37(3):419-25.
Vestergaard P. Discrepancies in bone mineral density and fracture risk in patients with type 1 and type 2 diabetes—a meta-analysis. Osteoporosis Int. 2007;18(4):427-44.
Aleti S, Pal R, Dutta P, Dhibar DP, Prakash M, Khandelwal N, et al. Prevalence and predictors of osteopenia and osteoporosis in patients with type 2 diabetes mellitus: a cross-sectional study from a tertiary care institute in North India. International Journal of Diabetes in Developing Countries. 2020:1-7.
Lee JH, Kim JH, Hong AR, Kim SW, Shin CS. Optimal body mass index for minimizing the risk for osteoporosis and type 2 diabetes. Korean J Intern Med. 2020;35(6):1432-42.
Purnell JQ. Definitions, Classification, and Epidemiology of Obesity. In: Feingold KR, Anawalt B, Boyce A, Chrousos G, de Herder WW, Dhatariya K, et al., editors. Endotext. South Dartmouth (MA): MDText. com, Inc.; 2000.
Křenek P, Benešová Y, Bienertová-Vašků J, Vašků A. The impact of five VDR polymorphisms on multiple sclerosis risk and progression: a case-control and genotype-phenotype study. Journal of Molecular Neuroscience. 2018;64(4):559-66.
Mohammadi Z, Fayyazbakhsh F, Ebrahimi M, Amoli MM, Khashayar P, Dini M, et al. Association between vitamin D receptor gene polymorphisms (Fok1 and Bsm1) and osteoporosis: a systematic review. J Diabetes Metab Disord. 2014;13(1):98.
Szymczak-Tomczak A, Krela-Kazmierczak I, Kaczmarek-Rys M, Hryhorowicz S, Stawczyk-Eder K, Szalata M, et al. Vitamin D receptor (VDR) TaqI polymorphism, vitamin D and bone mineral density in patients with inflammatory bowel diseases. Adv Clin Exp Med. 2019;28(7):955-60.
Ahmad I, Jafar T, Mahdi F, Ameta K, Arshad M, Das SK, et al. Association of vitamin D receptor gene polymorphism (TaqI and Apa1) with bone mineral density in North Indian postmenopausal women. Gene. 2018;659:123-7.
Zimmerman RK, Balasubramani GK, Nowalk MP, Eng H, Urbanski L, Jackson ML, et al. Classification and Regression Tree (CART) analysis to predict influenza in primary care patients. BMC Infectious Diseases. 2016;16(1):503.
Henrard S, Speybroeck N, Hermans C. Classification and regression tree analysis vs. multivariable linear and logistic regression methods as statistical tools for studying haemophilia. Haemophilia : the official journal of the World Federation of Hemophilia. 2015;21(6):715-22.
| Files | ||
| Issue | Vol 8 No 1 (2022) | |
| Section | Original Article(s) | |
| DOI | https://doi.org/10.18502/jbe.v8i1.10406 | |
| Keywords | ||
| Data mining Osteoporosis Bone density Type 2 Diabetes Vitamin D receptor | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
