Development of prognostic clinical and genetic models of the risk of low bone mineral density using neural network training

BACKGROUND: Osteoporosis is a common age-related disease with disabling consequences, the early diagnosis of which is difficult due to its long and hidden course, which often leads to diagnosis only after a fracture. In this regard, great expectations are placed on advanced developments in machine learning technologies aimed at predicting osteoporosis at an early stage of development, including the use of large data sets containing information on genetic and clinical predictors of the disease. Nevertheless, the inclusion of DNA markers in prediction models is fraught with a number of difficulties due to the complex polygenic and heterogeneous nature of the disease. Currently, the predictive power of neural network models is insufficient for their incorporation into modern osteoporosis diagnostic protocols. Studies in this area are sporadic, but are widely demanded, as their results are of great importance for preventive medicine. This leads to the need to search for the most effective machine learning approaches and optimise the selection of genetic markers as input parameters to neural network models.
AIM: to evaluate the effectiveness of machine learning and neural network analysis to develop predictive risk models for osteoporosis based on clinical predictors and genetic markers of osteoporetic fractures.
MATERIALS AND METHODS: The predictive models were trained using a database of genotyping and clinical characteristics of 701 women and 501 men living in the Volga-Ural region of Russia. Anthropometric parameters, data on gender, bone mineral density level, and the results of genotyping of 152 polymorphic loci of candidate genes and replication loci of the GEFOS consortium’s full genome-wide association search were included as input parameters.
RESULTS: It was found that the model for predicting low bone mineral density, including 6 polymorphic variants of the OPG gene (rs2073618, rs2073617, rs7844539, rs3102735, rs3134069) and 5 polymorphic variants of microRNA binding sites in the mRNA of genes involved in bone metabolism (COL11A1 — rs1031820, FGF2 — rs6854081, miR-146 — rs2910164, ZNF239 — rs10793442, SPARC — rs1054204 and VDR — rs11540149) (AUC=0.81 for men and AUC=0.82 for women).
CONCLUSION: The results confirm the promising application of machine learning to predict the risk of osteoporosis at the preclinical stage of the disease based on the analysis of clinical and genetic factors.

1. Pisani P, Renna MD, Conversano F, et al. Major osteoporotic fragility fractures: Risk factor updates and societal impact. World J Orthop. 2016;7(3):171-181 doi: https://doi.org/10.5312/wjo.v7.i3.171

2. Salari N, Ghasemi H, Mohammadi L, et al. The global prevalence of osteoporosis in the world: a comprehensive systematic review and meta-analysis. J Orthop Surg Res. 2021;16(1):609. doi: https://doi.org/10.1186/s13018-021-02772-0

3. Zaigrova NK, Uryas’ev OM, Shahanov AV, Tverdova LV. Vozmozhnosti instrumenta FRAX v diagnostike osteoporoza. Rossijskij mediko-biologicheskij vestnik imeni akademika I.P. Pavlova. 2017;25(1):62-68 (In Russ.) doi: https://doi.org/10.23888/pavlovj2017162-68

4. Verbovoj AF, Pashenceva AV, Sharonova LA. Osteoporoz: sovremennoe sostoyanie problemy. Terapevticheskij arhiv. 2017.89(5):90-97 (In Russ.) doi: https://doi.org/10.5152/eurjrheum.2016.048

5. Lesnyak OM, Baranova IA, Belova KYu, Gladkova EN, Evstigneeva LP. Osteoporoz v Rossijskoj Federacii: epidemiologiya, medikosocial’nye i ekonomicheskie aspekty problemy (obzor literatury). Travmatologiya i ortopediya Rossii. 2018;24(1):155-168.(In Russ.) doi: https://doi.org/10.21823/2311-2905-2018-24-1-155-168

6. Foger-Samwald U, Dovjak P, Azizi-Semrad U, et al. Osteoporosis: Pathophysiology and therapeutic options. EXCLI J. 2020;19:1017-1037 doi: https://doi.org/10.17179/excli2020-2591

7. Makitie RE, Costantini A, Kampe A et al. New insights into monogenic causes of osteoporosis. Front. Endocrinol (Lausanne). 2019;10:70. doi: https://doi.org/10.3389/fendo.2019.00070

8. Estrada K, Styrkarsdottir U, Evangelou E. et al. Genome-wide metaanalysis identifies 56 bone mineral density loci and reveals 14 loci associated with risk of fracture. Nat Genet. 2012;44(5):491-501 doi: https://doi.org/10.1038/ng.2249

9. Howard GM, Nguyen TV, Harris M, et al. Genetic and environmental contributions to the association between quantitative ultrasound and bone mineral density measurements: A twin study. J Bone Miner Res. 1998;13(8):1318-1327. doi: https://doi.org/10.1359/jbmr.1998.13.8.1318

10. Rivadeneira F, Styrkarsdottir U, Estrada K, et al. Twenty bonemineral-density loci identified by large-scale meta-analysis of genome-wide association studies. Nat Genet. 2009;41(11):1199-1206. doi: https://doi.org/10.1038/ng.446

11. Yalaev B, Tyurin A, Prokopenko I, et al. Using a polygenic score to predict the risk of developing primary osteoporosis. Int J Mol Sci. 2022;23(17):10021. doi: https://doi.org/10.3390/ijms231710021

12. Ferizi U, Honig S, Chang G. Artificial intelligence, osteoporosis and fragility fractures. Curr Opin Rheumatol. 2019;31(4):368-375. doi: https://doi.org/10.1097/BOR.0000000000000607

13. Kanis JA on behalf of the World Health Organization Scientific Group (World Health Organization Collaborating Centre for Metabolic Bone Diseases, University of Sheffield, UK). Assessment of osteoporosis at the primary health-care level. Technical Report. 2007. World Health Organization Collaborating Centre for Metabolic Bone Diseases, University of Sheffield

14. Kanis J, McCloskey EV, Johansson H, et al. A reference standard for the description of osteoporosis. Bone. 2008;42(3):467-75. doi: https://doi.org/10.1016/j.bone.2007.11.001

15. Ho-Le TP, Center JR, Eisman JA, et al. Prediction of hip fracture in post-menopausal women using artificial neural network approach. Proc Annu Int Conf IEEE Eng Med Biol Soc. 2017;2017:4207-4210. doi: https://doi.org/10.1109/EMBC.2017.8037784

16. Ferizi U, Besser H, Hysi P, et al. Artificial intelligence applied to osteoporosis: a performance comparison of machine learning algorithms in predicting fragility fractures from MRI data. J Magn Reson Imaging. 2019;49(4):1029-1038. doi: https://doi.org/10.1002/jmri.26280

17. Wu Q, Nasoz F, Jung J, et al. Machine learning approaches for the prediction of bone mineral density by using genomic and phenotypic data of 5130 older men. Sci Rep. 2021;11(1):4482. doi: https://doi.org/10.1038/s41598-021-83828-3

18. Lewis CM, Vassos E. Polygenic risk scores: from research tools to clinical instruments. Genome Med. 2020;12(44):1-11. doi: https://doi.org/10.1186/s13073-020-00742-5

19. Choi SW, Mak TSH, O’Reilly PF. Tutorial: a guide to performing polygenic risk score analyses. Nat Protoc. 2020;15(9):2759-2772. doi: https://doi.org/10.1038/s41596-020-0353-1

20. Chen X, Liu G, Wang S, et al. Machine learning analysis of gene expression profile reveals a novel diagnostic signature for osteoporosis. J Orthop Surg Res. 2021;16(1):189. doi: https://doi.org/10.1186/s13018-021-02329-1

21. Kruse C, Eiken P, Vestergaard P. Machine learning principles can improve hip fracture prediction. Calcif Tissue Int. 2017;100(4):348-360. doi: https://doi.org/10.1007/s00223-017-0238-7

22. Rahim F, Zadeh AZ, Javanmardi P, et al. Machine learning algorithms for diagnosis of hip bone osteoporosis: a systematic review and meta-analysis study. Biomed Eng Online. 2023;22(1):68. doi: https://doi.org/10.1186/s12938-023-01132-9

23. Hsieh CH, Lu RH, Lee NH, et al. Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks. Surgery. 2011;149(1):87-93. doi: https://doi.org/10.1016/j.surg.2010.03.023