ISSN 0253-2778

CN 34-1054/N

open
Free to Publish. Free to Read.
Open AccessOpen Access JUSTC Life Sciences 17 January 2024

Association study on bone metabolism in type 2 diabetes by using machine learning

  • 1.

    National Engineering Laboratory for Brain-inspired Intelligence Technology and Application, School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China

  • 2.

    Department of Endocrinology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei 230001, China

  • 3.

    Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei 230088, China

  • 4.

    Department of Geriatric Medicine, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei 230001, China

  • 5.

    CAS Key Laboratory of Brain Function and Diseases, School of Life Sciences, University of Science and Technology of China, Hefei 230027,China

Cite this:
https://doi.org/10.52396/JUSTC-2023-0089
More Information
  • Author Bio:

    Jiatong Hu received her master’s degree from the School of Information Science and Technology, University of Science and Technology of China, under the supervision of Prof. Ji Liu. Her research mainly focused on the association study of bone metabolism in type 2 diabetes using machine learning techniques, as well as investigating the gender differences in type 2 diabetes

    Wei Wang received his Ph.D degree in Neurobiology from the University of Science and Technology of China (USTC). He is currently a Chief Physician in the Department of Endocrinology, the First Affiliated Hospital of USTC. His main research interests include diabetes and its complications

    Ji Liu received his Ph.D degree in Neurobiology from the University of Science and Technology of China (USTC) and his M.D. degree in Endocrinology from the University of Amsterdam. He is currently a Professor at USTC. His research interests include type 2 diabetes, the neural mechanism of feeding and energy metabolism

  • Corresponding author: E-mail: hfww2001@ustc.edu.cn; E-mail: lj1257@ustc.edu.cn
  • Received Date: 17 May 2023
  • Accepted Date: 01 November 2023
    • Available Online: 17 January 2024
    Abstract

  • Abstract

    Type 2 diabetes mellitus is often accompanied by serious complications, including bone metabolic diseases, liver diseases, and kidney diseases, which are affected by the course of disease, sex, age and individual differences and cannot be a unified treatment paradigm. Therefore, for the in-depth analysis of clinical data, looking for the correlation of type 2 diabetes complication data has important guiding significance for the treatment of type 2 diabetes and its complications. In this paper, multiple linear regression models were established based on the clinical data of type 2 diabetes patients in Anhui Province. Our results suggest that the main factors affecting bone complications of type 2 diabetes include body shape indexes, creatinine, uric acid, triglycerides and blood pressure. Interestingly, the bone mineral density of lumbar vertebrae in patients with type 2 diabetes was increased, suggesting that there was a risk of lumbar hyperosteogeny.

    Graphical abstract

    Thermodynamic diagram of the multiple linear regression equation coefficient and p value.

    Abstract

    Type 2 diabetes mellitus is often accompanied by serious complications, including bone metabolic diseases, liver diseases, and kidney diseases, which are affected by the course of disease, sex, age and individual differences and cannot be a unified treatment paradigm. Therefore, for the in-depth analysis of clinical data, looking for the correlation of type 2 diabetes complication data has important guiding significance for the treatment of type 2 diabetes and its complications. In this paper, multiple linear regression models were established based on the clinical data of type 2 diabetes patients in Anhui Province. Our results suggest that the main factors affecting bone complications of type 2 diabetes include body shape indexes, creatinine, uric acid, triglycerides and blood pressure. Interestingly, the bone mineral density of lumbar vertebrae in patients with type 2 diabetes was increased, suggesting that there was a risk of lumbar hyperosteogeny.

    • Public Summary

    • In-depth analysis of type 2 diabetes in Anhui Province suggested that the risk factors for bone complications included body shape indexes, creatinine, uric acid, triglycerides and blood pressure.
    • Interestingly, the bone mineral density of lumbar vertebrae in patients with type 2 diabetes was increased, suggesting that there was a risk of lumbar hyperosteogeny.

    FullText(HTML)
  • loading
    • References(28)
  • [1]
    Gregg E W, Li Y, Wang J, et al. Changes in diabetes-related complications in the United States, 1990–2010. The New England Journal of Medicine, 2014, 370 (16): 1514–1523. doi: 10.1056/NEJMoa1310799
    [2]
    King P, Peacock I, Donnelly R. The UK prospective diabetes study (UKPDS): clinical and therapeutic implications for type 2 diabetes. British Journal of Clinical Pharmacology, 1999, 48 (5): 643–648. doi: 10.1046/j.1365-2125.1999.00092.x
    [3]
    Sharma U, Pal D, Prasad R. Alkaline phosphatase: an overview. Indian Journal of Clinical Biochemistry, 2014, 29 (3): 269–278. doi: 10.1007/s12291-013-0408-y
    [4]
    Sabarudin A, Sakti S P, Aulanni’am, et al. Recent advances in nephropathy biomarker detections using paper-based analytical devices. Analytical Sciences, 2022, 38 (1): 39–54. doi: 10.2116/analsci.21SAR10
    [5]
    van Hoeven K H, Factor S M. The diabetic heart: clinical, experimental and pathological features. Acta Cardiologica, 1991, 46 (3): 329–339.
    [6]
    Wang J, Shu Y Q. Research progress in the pathogenesis of type 2 diabetic osteoporosis. Clinical Journal of Traditional Chinese Medicine, 2012, 24 (2): 183–184. (in Chinese) doi: 10.16448/j.cjtcm.2012.02.037
    [7]
    Sheu A, Greenfield J R, White C P, et al. Assessment and treatment of osteoporosis and fractures in type 2 diabetes. Trends in Endocrinology & Metabolism, 2022, 33 (5): 333–344. doi: 10.1016/j.tem.2022.02.006
    [8]
    Cai G Y, Ge X L, Wei L, et al. Observation of level of bone gla protein in serum. Chinese Journal of Osteoporosis, 1999, 5 (2): 29–32.(in Chinese)
    [9]
    Takashi Y, Kawanami D. The role of bone-derived hormones in glucose metabolism, diabetic kidney disease, and cardiovascular disorders. International Journal of Molecular Sciences, 2022, 23 (4): 2376. doi: 10.3390/ijms23042376
    [10]
    Krege J H, Lane N E, Harris J M, et al. PINP as a biological response marker during teriparatide treatment for osteoporosis. Osteoporosis International, 2014, 25 (9): 2159–2171. doi: 10.1007/s00198-014-2646-0
    [11]
    Delmas P D. Biochemical markers of bone turnover in Paget’s disease of bone. Journal of Bone and Mineral Research, 1999, 14: 66–69. doi: 10.1002/jbmr.5650140213
    [12]
    Mei C L, Wang N. Modern Regression Analysis Method (Chinese Edition). Beijing: Science Press, 2012 .
    [13]
    Wang J, Wang F, Liu Y, et al. Multiple linear regression and artificial neural network to predict blood glucose in overweight patients. Experimental and Clinical Endocrinology & Diabetes, 2016, 124 (1): 34–38. doi: 10.1055/s-0035-1565175
    [14]
    García-Martín A, Reyes-García R, García-Castro J M, et al. Role of serum FSH measurement on bone resorption in postmenopausal women. Endocrine, 2012, 41: 302–308. doi: 10.1007/s12020-011-9541-7
    [15]
    Cabrera C D, Henríquez M S, Traba M L, et al. Biochemical markers of bone formation in the study of postmenopausal osteoporosis. Osteoporosis International, 1998, 8 (2): 147–151. doi: 10.1007/BF02672511
    [16]
    Shan P F, Wu X P, Zhang H, et al. Bone mineral density and its relationship with body mass index in postmenopausal women with type 2 diabetes mellitus in mainland China. Journal of Bone and Mineral Metabolism, 2009, 27 (2): 190–197. doi: 10.1007/s00774-008-0023-9
    [17]
    Im J A, Yu B P, Jeon J Y, et al. Relationship between osteocalcin and glucose metabolism in postmenopausal women. Clinica Chimica Acta, 2008, 396 (1/2): 66–69. doi: 10.1016/j.cca.2008.07.001
    [18]
    Wei J, Karsenty G. An overview of the metabolic functions of osteocalcin. Current Osteoporosis Reports, 2015, 13 (3): 180–185. doi: 10.1007/s11914-015-0267-y
    [19]
    Rossini M, Gatti D, Zamberlan N, et al. Long-term effects of a treatment course with oral alendronate of postmenopausal osteoporosis. Journal of Bone and Mineral Research, 1994, 9 (11): 1833–1837. doi: 10.1002/jbmr.5650091121
    [20]
    Conte C, Epstein S, Napoli N. Insulin resistance and bone: a biological partnership. Acta Diabetologica, 2018, 55 (4): 305–314. doi: 10.1007/s00592-018-1101-7
    [21]
    Masaki H, Miki T. Bone and calcium metabolism in elderly women. Clinical Calcium, 2011, 21 (9): 1361–1367.
    [22]
    Keizman D, Ish-Shalom M, Berliner S, et al. Low uric acid levels in serum of patients with ALS: further evidence for oxidative stress? Journal of the Neurological Sciences, 2009, 285 (1/2): 95–99. doi: 10.1016/j.jns.2009.06.002
    [23]
    Ahn S H, Lee S H, Kim B J, et al. Higher serum uric acid is associated with higher bone mass, lower bone turnover, and lower prevalence of vertebral fracture in healthy postmenopausal women. Osteoporosis International, 2013, 24 (12): 2961–2970. doi: 10.1007/s00198-013-2377-7
    [24]
    Cui R, Zhou L, Li Z, et al. Assessment risk of osteoporosis in Chinese people: relationship among body mass index, serum lipid profiles, blood glucose, and bone mineral density. Clinical Interventions in Aging, 2016, 11: 887–895. doi: 10.2147/CIA.S103845
    [25]
    Ha J, Jo K, Lim D J, et al. Parathyroid hormone and vitamin D are associated with the risk of metabolic obesity in a middle-aged and older Korean population with preserved renal function: A cross-sectional study. PLoS ONE, 2017, 12 (4): e0175132. doi: 10.1371/journal.pone.0175132
    [26]
    Tintut Y, Parhami F, Tsingotjidou A, et al. 8-Isoprostaglandin E2 enhances receptor-activated NFκB ligand (RANKL)-dependent osteoclastic potential of marrow hematopoietic precursors via the cAMP pathway. The Journal of Biological Chemistry, 2002, 277 (16): 14221–14226. doi: 10.1074/jbc.M111551200
    [27]
    Go J H, Song Y M, Park J H, et al. Association between serum cholesterol level and bone mineral density at lumbar spine and femur neck in postmenopausal Korean women. Korean Journal of Family Medicine, 2012, 33 (3): 166–173. doi: 10.4082/kjfm.2012.33.3.166
    [28]
    He L, Huang L. Correlation between hypertension and primary osteoporosis. Modern Chinese Clinical Medicine, 2008, 15 (2): 1–3. (in Chinese)
    • Supplements(0)
    • Related Articles
    • Track Citations
  • 加载中

Catalog

    |
    Get Citation
    PDF
    XML

    Figure  1.  The pipeline of MLR and SVR models for clinical datasets.

    Figure  2.  F-statistic in the multivariate linear regression model.

    Figure  3.  (a) Thermodynamic diagram of multiple linear regression equation coefficient (red represents positive correlation, blue represents negative correlation, and the darker the color, the larger the absolute value of the coefficient); (b) p value thermodynamic diagram of bone metabolism index and other data (the darker the color, the smaller the p value).

    Figure  4.  Thermodynamic diagram of the final equation coefficient of stepwise multiple linear regression. Red represents a positive correlation, and blue represents a negative correlation. The darker the color is, the larger the absolute value of the coefficient. *: p<0.05,**: p<0.01,***: p<0.001.

    Figure  5.  Differences in support vector regression model scores before and after screening.

    [1]
    Gregg E W, Li Y, Wang J, et al. Changes in diabetes-related complications in the United States, 1990–2010. The New England Journal of Medicine, 2014, 370 (16): 1514–1523. doi: 10.1056/NEJMoa1310799
    [2]
    King P, Peacock I, Donnelly R. The UK prospective diabetes study (UKPDS): clinical and therapeutic implications for type 2 diabetes. British Journal of Clinical Pharmacology, 1999, 48 (5): 643–648. doi: 10.1046/j.1365-2125.1999.00092.x
    [3]
    Sharma U, Pal D, Prasad R. Alkaline phosphatase: an overview. Indian Journal of Clinical Biochemistry, 2014, 29 (3): 269–278. doi: 10.1007/s12291-013-0408-y
    [4]
    Sabarudin A, Sakti S P, Aulanni’am, et al. Recent advances in nephropathy biomarker detections using paper-based analytical devices. Analytical Sciences, 2022, 38 (1): 39–54. doi: 10.2116/analsci.21SAR10
    [5]
    van Hoeven K H, Factor S M. The diabetic heart: clinical, experimental and pathological features. Acta Cardiologica, 1991, 46 (3): 329–339.
    [6]
    Wang J, Shu Y Q. Research progress in the pathogenesis of type 2 diabetic osteoporosis. Clinical Journal of Traditional Chinese Medicine, 2012, 24 (2): 183–184. (in Chinese) doi: 10.16448/j.cjtcm.2012.02.037
    [7]
    Sheu A, Greenfield J R, White C P, et al. Assessment and treatment of osteoporosis and fractures in type 2 diabetes. Trends in Endocrinology & Metabolism, 2022, 33 (5): 333–344. doi: 10.1016/j.tem.2022.02.006
    [8]
    Cai G Y, Ge X L, Wei L, et al. Observation of level of bone gla protein in serum. Chinese Journal of Osteoporosis, 1999, 5 (2): 29–32.(in Chinese)
    [9]
    Takashi Y, Kawanami D. The role of bone-derived hormones in glucose metabolism, diabetic kidney disease, and cardiovascular disorders. International Journal of Molecular Sciences, 2022, 23 (4): 2376. doi: 10.3390/ijms23042376
    [10]
    Krege J H, Lane N E, Harris J M, et al. PINP as a biological response marker during teriparatide treatment for osteoporosis. Osteoporosis International, 2014, 25 (9): 2159–2171. doi: 10.1007/s00198-014-2646-0
    [11]
    Delmas P D. Biochemical markers of bone turnover in Paget’s disease of bone. Journal of Bone and Mineral Research, 1999, 14: 66–69. doi: 10.1002/jbmr.5650140213
    [12]
    Mei C L, Wang N. Modern Regression Analysis Method (Chinese Edition). Beijing: Science Press, 2012 .
    [13]
    Wang J, Wang F, Liu Y, et al. Multiple linear regression and artificial neural network to predict blood glucose in overweight patients. Experimental and Clinical Endocrinology & Diabetes, 2016, 124 (1): 34–38. doi: 10.1055/s-0035-1565175
    [14]
    García-Martín A, Reyes-García R, García-Castro J M, et al. Role of serum FSH measurement on bone resorption in postmenopausal women. Endocrine, 2012, 41: 302–308. doi: 10.1007/s12020-011-9541-7
    [15]
    Cabrera C D, Henríquez M S, Traba M L, et al. Biochemical markers of bone formation in the study of postmenopausal osteoporosis. Osteoporosis International, 1998, 8 (2): 147–151. doi: 10.1007/BF02672511
    [16]
    Shan P F, Wu X P, Zhang H, et al. Bone mineral density and its relationship with body mass index in postmenopausal women with type 2 diabetes mellitus in mainland China. Journal of Bone and Mineral Metabolism, 2009, 27 (2): 190–197. doi: 10.1007/s00774-008-0023-9
    [17]
    Im J A, Yu B P, Jeon J Y, et al. Relationship between osteocalcin and glucose metabolism in postmenopausal women. Clinica Chimica Acta, 2008, 396 (1/2): 66–69. doi: 10.1016/j.cca.2008.07.001
    [18]
    Wei J, Karsenty G. An overview of the metabolic functions of osteocalcin. Current Osteoporosis Reports, 2015, 13 (3): 180–185. doi: 10.1007/s11914-015-0267-y
    [19]
    Rossini M, Gatti D, Zamberlan N, et al. Long-term effects of a treatment course with oral alendronate of postmenopausal osteoporosis. Journal of Bone and Mineral Research, 1994, 9 (11): 1833–1837. doi: 10.1002/jbmr.5650091121
    [20]
    Conte C, Epstein S, Napoli N. Insulin resistance and bone: a biological partnership. Acta Diabetologica, 2018, 55 (4): 305–314. doi: 10.1007/s00592-018-1101-7
    [21]
    Masaki H, Miki T. Bone and calcium metabolism in elderly women. Clinical Calcium, 2011, 21 (9): 1361–1367.
    [22]
    Keizman D, Ish-Shalom M, Berliner S, et al. Low uric acid levels in serum of patients with ALS: further evidence for oxidative stress? Journal of the Neurological Sciences, 2009, 285 (1/2): 95–99. doi: 10.1016/j.jns.2009.06.002
    [23]
    Ahn S H, Lee S H, Kim B J, et al. Higher serum uric acid is associated with higher bone mass, lower bone turnover, and lower prevalence of vertebral fracture in healthy postmenopausal women. Osteoporosis International, 2013, 24 (12): 2961–2970. doi: 10.1007/s00198-013-2377-7
    [24]
    Cui R, Zhou L, Li Z, et al. Assessment risk of osteoporosis in Chinese people: relationship among body mass index, serum lipid profiles, blood glucose, and bone mineral density. Clinical Interventions in Aging, 2016, 11: 887–895. doi: 10.2147/CIA.S103845
    [25]
    Ha J, Jo K, Lim D J, et al. Parathyroid hormone and vitamin D are associated with the risk of metabolic obesity in a middle-aged and older Korean population with preserved renal function: A cross-sectional study. PLoS ONE, 2017, 12 (4): e0175132. doi: 10.1371/journal.pone.0175132
    [26]
    Tintut Y, Parhami F, Tsingotjidou A, et al. 8-Isoprostaglandin E2 enhances receptor-activated NFκB ligand (RANKL)-dependent osteoclastic potential of marrow hematopoietic precursors via the cAMP pathway. The Journal of Biological Chemistry, 2002, 277 (16): 14221–14226. doi: 10.1074/jbc.M111551200
    [27]
    Go J H, Song Y M, Park J H, et al. Association between serum cholesterol level and bone mineral density at lumbar spine and femur neck in postmenopausal Korean women. Korean Journal of Family Medicine, 2012, 33 (3): 166–173. doi: 10.4082/kjfm.2012.33.3.166
    [28]
    He L, Huang L. Correlation between hypertension and primary osteoporosis. Modern Chinese Clinical Medicine, 2008, 15 (2): 1–3. (in Chinese)
    Recommended articles
    TrendMD
    Volume 53 Issue 12 page: 1205
    Cover

    Article Metrics

    Article views (231) PDF downloads(684)
    Proportional views

    Copyright © Editorial Office of JUSTC, All Rights Reserved. 皖ICP备05002528号

    Supported by: Beijing Renhe Information Technology Co. Ltd    

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return