Prediction of the Risk of Bone Mineral Density Decrease in Type 2 Diabetes Mellitus Patients Based on Traditional Multivariate Logistic Regression and Machine Learning: A Preliminary Study

Overview

Journal Diabetes Metab Syndr Obes

Publisher Dove Medical Press

Specialty Endocrinology

Date 2023 Sep 25

PMID 37744700

Authors

Junli Zhang

Zhenghui Xu

Yu Fu

Lu Chen

Affiliations

Soon will be listed here.

Abstract

Purpose: There remains a lack of a machine learning (ML) model incorporating body composition to assess the risk of bone mineral density (BMD) decreases in type 2 diabetes mellitus (T2DM) patients. We aimed to use ML algorithms and the traditional multivariate logistic regression to establish prediction models for BMD decreases in T2DM patients over 50 years of age, and compare the performance of the two methods.

Patients And Methods: This cross-sectional study was conducted among 450 patients with T2DM from 1 August 2016 to 31 December 2022. The participants were divided into a normal BMD group and a decreased BMD group. Traditional multivariate logistic regression and six ML algorithms were selected to construct male and female models. Two nomograms were constructed to evaluate the risk of BMD decreases in the male and female T2DM patients, respectively. The ML models with the highest area under the curve (AUC) were compared with the traditional multivariate logistic regression models in terms of discriminant ability and clinical applicability.

Results: The optimal ML model was the extreme gradient boost (XGBoost) model. The AUCs of the traditional multivariate logistic regression and the XGBoost models were 0.722 and 0.800 in the male testing dataset, respectively, and 0.876 and 0.880 in the female testing dataset, respectively. The decision curve analysis results suggested that using the XGBoost models to predict the risk of BMD decreases obtained more net benefits compared with the traditional models in both sexes.

Conclusion: We preliminarily proved that the XGBoost models outperformed most other ML models in both sexes and achieved higher accuracy than traditional analyses. Due to the limited sample size in the study, it is necessary to validate our findings in larger prospective cohort studies.

References

de Souza Dorna M, Costa N, de Oliveira E, Sassaki L, Romeiro F, de Paiva S . Association between phase angle, anthropometric measurements, and lipid profile in HCV-infected patients. Clinics (Sao Paulo). 2014; 68(12):1555-8. PMC: 3840369. DOI: 10.6061/clinics/2013(12)13. View

Silva A, Matias C, Santos D, Rocha P, Minderico C, Sardinha L . Increases in intracellular water explain strength and power improvements over a season. Int J Sports Med. 2014; 35(13):1101-5. DOI: 10.1055/s-0034-1371839. View

Liu H, Wang G, Wu T, Hu J, Mu Y, Gu W . Association of skin autofluorescence with low bone density/osteoporosis and osteoporotic fractures in type 2 diabetes mellitus. J Diabetes. 2022; 14(9):571-585. PMC: 9512774. DOI: 10.1111/1753-0407.13309. View

Pan Y, Xu J . Association between muscle mass, bone mineral density and osteoporosis in type 2 diabetes. J Diabetes Investig. 2021; 13(2):351-358. PMC: 8847116. DOI: 10.1111/jdi.13642. View

Yoo T, Kim S, Kim D, Choi J, Lee W, Oh E . Osteoporosis risk prediction for bone mineral density assessment of postmenopausal women using machine learning. Yonsei Med J. 2013; 54(6):1321-30. PMC: 3809875. DOI: 10.3349/ymj.2013.54.6.1321. View

Prakash K, Choudhary R, Singh G . Lean Body Mass, Body Fat Percentage, and Handgrip Strength as Predictors of Bone Mineral Density in Postmenopausal Women. J Midlife Health. 2022; 12(4):299-303. PMC: 8849155. DOI: 10.4103/jmh.jmh_21_21. View

Jang H . Diabetes and Muscle Dysfunction in Older Adults. Ann Geriatr Med Res. 2020; 23(4):160-164. PMC: 7370755. DOI: 10.4235/agmr.19.0038. View

Cui L, Shin M, Kweon S, Park K, Lee Y, Chung E . Relative contribution of body composition to bone mineral density at different sites in men and women of South Korea. J Bone Miner Metab. 2007; 25(3):165-71. DOI: 10.1007/s00774-006-0747-3. View

Casale M, von Hurst P, Beck K, Shultz S, Kruger M, OBrien W . Lean Mass and Body Fat Percentage Are Contradictory Predictors of Bone Mineral Density in Pre-Menopausal Pacific Island Women. Nutrients. 2016; 8(8). PMC: 4997383. DOI: 10.3390/nu8080470. View

10.

Manolagas S, OBrien C, Almeida M . The role of estrogen and androgen receptors in bone health and disease. Nat Rev Endocrinol. 2013; 9(12):699-712. PMC: 3971652. DOI: 10.1038/nrendo.2013.179. View

11.

Yosibash Z, Trabelsi N, Buchnik I, Myers K, Salai M, Eshed I . Hip Fracture Risk Assessment in Elderly and Diabetic Patients: Combining Autonomous Finite Element Analysis and Machine Learning. J Bone Miner Res. 2023; 38(6):876-886. DOI: 10.1002/jbmr.4805. View

12.

Godos J, Giampieri F, Chisari E, Micek A, Paladino N, Forbes-Hernandez T . Alcohol Consumption, Bone Mineral Density, and Risk of Osteoporotic Fractures: A Dose-Response Meta-Analysis. Int J Environ Res Public Health. 2022; 19(3). PMC: 8835521. DOI: 10.3390/ijerph19031515. View

13.

Alswat K . Gender Disparities in Osteoporosis. J Clin Med Res. 2017; 9(5):382-387. PMC: 5380170. DOI: 10.14740/jocmr2970w. View

14.

. 2. Classification and Diagnosis of Diabetes: . Diabetes Care. 2019; 43(Suppl 1):S14-S31. DOI: 10.2337/dc20-S002. View

15.

Ha J, Jeong C, Han K, Lim Y, Kim M, Kwon H . Comparison of fracture risk between type 1 and type 2 diabetes: a comprehensive real-world data. Osteoporos Int. 2021; 32(12):2543-2553. DOI: 10.1007/s00198-021-06032-z. View

16.

Kang D, Guo L, Guo T, Wang Y, Liu T, Feng X . Association of body composition with bone mineral density in northern Chinese men by different criteria for obesity. J Endocrinol Invest. 2014; 38(3):323-31. DOI: 10.1007/s40618-014-0167-5. View

17.

Wu X, Park S . A Prediction Model for Osteoporosis Risk Using a Machine-Learning Approach and Its Validation in a Large Cohort. J Korean Med Sci. 2023; 38(21):e162. PMC: 10226854. DOI: 10.3346/jkms.2023.38.e162. View

18.

Melton 3rd L . How many women have osteoporosis now?. J Bone Miner Res. 1995; 10(2):175-7. DOI: 10.1002/jbmr.5650100202. View

19.

Mao Y, Xu L, Xue T, Liang J, Lin W, Wen J . Novel nomogram for predicting the 3-year incidence risk of osteoporosis in a Chinese male population. Endocr Connect. 2021; 10(9):1111-1124. PMC: 8494413. DOI: 10.1530/EC-21-0330. View

20.

Beaudart C, Bruyere O, Geerinck A, Hajaoui M, Scafoglieri A, Perkisas S . Equation models developed with bioelectric impedance analysis tools to assess muscle mass: A systematic review. Clin Nutr ESPEN. 2020; 35:47-62. DOI: 10.1016/j.clnesp.2019.09.012. View