Skip to main content

Advertisement

SpringerLink
Log in

Development and validation of common data model-based fracture prediction model using machine learning algorithm

  • Original Article
  • Published:
Osteoporosis International Aims and scope Submit manuscript

Abstract

Summary

The need for an accurate country-specific real-world-based fracture prediction model is increasing. Thus, we developed scoring systems for osteoporotic fractures from hospital-based cohorts and validated them in an independent cohort in Korea. The model includes history of fracture, age, lumbar spine and total hip T-score, and cardiovascular disease.

Purpose

Osteoporotic fractures are substantial health and economic burden. Therefore, the need for an accurate real-world-based fracture prediction model is increasing. We aimed to develop and validate an accurate and user-friendly model to predict major osteoporotic and hip fractures using a common data model database.

Methods

The study included 20,107 and 13,353 participants aged ≥ 50 years with data on bone mineral density using dual-energy X-ray absorptiometry from the CDM database between 2008 and 2011 from the discovery and validation cohort, respectively. The main outcomes were major osteoporotic and hip fracture events. DeepHit and Cox proportional hazard models were used to identify predictors of fractures and to build scoring systems, respectively.

Results

The mean age was 64.5 years, and 84.3% were women. During a mean of 7.6 years of follow-up, 1990 major osteoporotic and 309 hip fracture events were observed. In the final scoring model, history of fracture, age, lumbar spine T-score, total hip T-score, and cardiovascular disease were selected as predictors for major osteoporotic fractures. For hip fractures, history of fracture, age, total hip T-score, cerebrovascular disease, and diabetes mellitus were selected. Harrell’s C-index for osteoporotic and hip fractures were 0.789 and 0.860 in the discovery cohort and 0.762 and 0.773 in the validation cohort, respectively. The estimated 10-year risks of major osteoporotic and hip fractures were 2.0%, 0.2% at score 0 and 68.8%, 18.8% at their maximum scores, respectively.

Conclusion

We developed scoring systems for osteoporotic fractures from hospital-based cohorts and validated them in an independent cohort. These simple scoring models may help predict fracture risks in real-world practice.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Data availability

The data that support the findings of this study are available from the corresponding authors, JHK and KSK, upon reasonable request.

References

  1. Hagino H, Jackson M, Gitlin M, Wessler Z (2021) Estimating the future clinical and economic benefits of improving osteoporosis diagnosis and treatment among women in Japan: a simulation projection model from 2020 to 2040. Arch Osteoporos 16:156

    Article  PubMed  Google Scholar 

  2. Cui L, Jackson M, Wessler Z, Gitlin M, Xia W (2021) Estimating the future clinical and economic benefits of improving osteoporosis diagnosis and treatment among women in China: a simulation projection model from 2020 to 2040. Arch Osteoporos 16:118

    Article  PubMed  Google Scholar 

  3. Park C, Ha YC, Jang S, Jang S, Yoon HK, Lee YK (2011) The incidence and residual lifetime risk of osteoporosis-related fractures in Korea. J Bone Miner Metab 29:744–751

    Article  PubMed  Google Scholar 

  4. Gdalevich M, Cohen D, Yosef D, Tauber C (2004) Morbidity and mortality after hip fracture: the impact of operative delay. Arch Orthop Trauma Surg 124:334–340

    Article  PubMed  Google Scholar 

  5. Abrahamsen B, Van Staa T, Ariely R, Olson M, Cooper C (2009) Excess mortality following hip fracture: a systematic epidemiological review. Osteoporos Int 20:1633–1650

    Article  CAS  PubMed  Google Scholar 

  6. Kanis JA, Harvey NC, Johansson H, Liu E, Vandenput L, Lorentzon M, Leslie WD, McCloskey EV (2020) A decade of FRAX: how has it changed the management of osteoporosis? Aging Clin Exp Res 32:187–196

    Article  PubMed  Google Scholar 

  7. Nguyen ND, Frost SA, Center JR, Eisman JA, Nguyen TV (2007) Development of a nomogram for individualizing hip fracture risk in men and women. Osteoporos Int 18:1109–1117

    Article  CAS  PubMed  Google Scholar 

  8. Nguyen ND, Frost SA, Center JR, Eisman JA, Nguyen TV (2008) Development of prognostic nomograms for individualizing 5-year and 10-year fracture risks. Osteoporos Int 19:1431–1444

    Article  CAS  PubMed  Google Scholar 

  9. Hippisley-Cox J, Coupland C (2009) Predicting risk of osteoporotic fracture in men and women in England and Wales: prospective derivation and validation of QFractureScores. BMJ 339:b4229

    Article  PubMed  PubMed Central  Google Scholar 

  10. Kanis JA, Oden A, Johnell O, Johansson H, De Laet C, Brown J, Burckhardt P, Cooper C, Christiansen C, Cummings S, Eisman JA, Fujiwara S, Glüer C, Goltzman D, Hans D, Krieg MA, La Croix A, McCloskey E, Mellstrom D, Melton LJ 3rd, Pols H, Reeve J, Sanders K, Schott AM, Silman A, Torgerson D, van Staa T, Watts NB, Yoshimura N (2007) The use of clinical risk factors enhances the performance of BMD in the prediction of hip and osteoporotic fractures in men and women. Osteoporos Int 18:1033–1046

    Article  CAS  PubMed  Google Scholar 

  11. Sambrook PN, Flahive J, Hooven FH, Boonen S, Chapurlat R, Lindsay R, Nguyen TV, Díez-Perez A, Pfeilschifter J, Greenspan SL, Hosmer D, Netelenbos JC, Adachi JD, Watts NB, Cooper C, Roux C, Rossini M, Siris ES, Silverman S, Saag KG, Compston JE, LaCroix A, Gehlbach S (2011) Predicting fractures in an international cohort using risk factor algorithms without BMD. J Bone Miner Res 26:2770–2777

    Article  PubMed  Google Scholar 

  12. Dhiman P, Andersen S, Vestergaard P, Masud T, Qureshi N (2018) Does bone mineral density improve the predictive accuracy of fracture risk assessment? A prospective cohort study in Northern Denmark. BMJ Open 8:e018898

    Article  PubMed  PubMed Central  Google Scholar 

  13. Li G, Thabane L, Papaioannou A, Adachi JD (2015) Comparison between frailty index of deficit accumulation and fracture risk assessment tool (FRAX) in prediction of risk of fractures. Bone 77:107–114

    Article  PubMed  PubMed Central  Google Scholar 

  14. Engels A, Reber KC, Lindlbauer I, Rapp K, Büchele G, Klenk J, Meid A, Becker C, König HH (2020) Osteoporotic hip fracture prediction from risk factors available in administrative claims data – A machine learning approach. PLoS One 15:e0232969

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Stang PE, Ryan PB, Racoosin JA, Overhage JM, Hartzema AG, Reich C, Welebob E, Scarnecchia T, Woodcock J (2010) Advancing the science for active surveillance: rationale and design for the Observational Medical Outcomes Partnership. Ann Intern Med 153:600–606

    Article  PubMed  Google Scholar 

  16. Informatics OHDSa (2020) The Book of OHDSI.

  17. Reich C, Ryan PB, Stang PE, Rocca M (2012) Evaluation of alternative standardized terminologies for medical conditions within a network of observational healthcare databases. J Biomed Inform 45:689–696

    Article  PubMed  Google Scholar 

  18. Wang Q, Reps JM, Kostka KF, Ryan PB, Zou Y, Voss EA, Rijnbeek PR, Chen R, Rao GA, Morgan Stewart H, Williams AE, Williams RD, Van Zandt M, Falconer T, Fernandez-Chas M, Vashisht R, Pfohl SR, Shah NH, Kasthurirathne SN, You SC, Jiang Q, Reich C, Zhou Y (2020) Development and validation of a prognostic model predicting symptomatic hemorrhagic transformation in acute ischemic stroke at scale in the OHDSI network. PLoS One 15:e0226718

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. Khalilia M, Choi M, Henderson A, Iyengar S, Braunstein M, Sun J (2015) Clinical predictive modeling development and deployment through FHIR web services. AMIA Annu Symp Proc 2015:717–726

    PubMed  PubMed Central  Google Scholar 

  20. Kong SH KS, Kim Y, Kim JH, Kim K, Shin CS (2022) Development and validation of common data model-based fracture prediction model using machine learning algorithm. figshare.dataset.2022. Deposited 17 June 2022 10.6084/m9.figshare.20085884

  21. Rietschel C (2018) Automated feature selection for survival analysis with deep learning. In:University of Oxford

  22. Lee C, Zame W, Yoon J, van der Schaar M (2018) DeepHit: a deep learning approach to survival analysis with competing risks. Proceedings of the AAAI Conference on Artificial Intelligence 32

  23. Saumya Jetley NAL, Namhoon Lee, Philip Torr (2018) Learn to pay attention. In: International Conference on Learning Representations.

  24. Sullivan LM, Massaro JM, D’Agostino RB Sr (2004) Presentation of multivariate data for clinical use: the Framingham Study risk score functions. Stat Med 23:1631–1660

    Article  PubMed  Google Scholar 

  25. Leisman DE, Harhay MO, Lederer DJ, Abramson M, Adjei AA, Bakker J, Ballas ZK, Barreiro E, Bell SC, Bellomo R, Bernstein JA, Branson RD, Brusasco V, Chalmers JD, Chokroverty S, Citerio G, Collop NA, Cooke CR, Crapo JD, Donaldson G, Fitzgerald DA, Grainger E, Hale L, Herth FJ, Kochanek PM, Marks G, Moorman JR, Ost DE, Schatz M, Sheikh A, Smyth AR, Stewart I, Stewart PW, Swenson ER, Szymusiak R, Teboul JL, Vincent JL, Wedzicha JA, Maslove DM (2020) Development and reporting of prediction models: guidance for authors from editors of respiratory, Sleep, and Critical Care Journals. Crit Care Med 48:623–633

    Article  PubMed  PubMed Central  Google Scholar 

  26. Lee SH, Khang YH, Lim KH, Kim BJ, Koh JM, Kim GS, Kim H, Cho NH (2010) Clinical risk factors for osteoporotic fracture: a population-based prospective cohort study in Korea. J Bone Miner Res 25:369–378

    Article  PubMed  Google Scholar 

  27. Kim HY, Jang EJ, Park B, Kim TY, Shin SA, Ha YC, Jang S (2016) Development of a Korean Fracture Risk Score (KFRS) for predicting osteoporotic fracture risk: analysis of data from the Korean National health insurance service. PLoS One 11:e0158918

    Article  PubMed  PubMed Central  Google Scholar 

  28. Kung AW, Lee KK, Ho AY, Tang G, Luk KD (2007) Ten-year risk of osteoporotic fractures in postmenopausal Chinese women according to clinical risk factors and BMD T-scores: a prospective study. J Bone Miner Res 22:1080–1087

    Article  PubMed  Google Scholar 

  29. Rietschel C, Yoon J, van der Schaar M (2018) Feature selection for survival analysis with competing risks using deep learning. arXiv preprint arXiv:1811.09317

  30. Kong SH, Shin CS (2021) Applications of machine learning in bone and mineral research. Endocrinol Metab (Seoul) 36:928–937

    Article  PubMed  Google Scholar 

  31. Kong SH, Ahn D, Kim BR, Srinivasan K, Ram S, Kim H, Hong AR, Kim JH, Cho NH, Shin CS (2020) A novel fracture prediction model using machine learning in a community-based cohort. JBMR Plus 4:e10337

    Article  PubMed  PubMed Central  Google Scholar 

  32. Batchelor F, Hill K, Mackintosh S, Said C (2010) What works in falls prevention after stroke?: a systematic review and meta-analysis. Stroke 41:1715–1722

    Article  PubMed  Google Scholar 

  33. Moylan KC, Binder EF (2007) Falls in older adults: risk assessment, management and prevention. Am J Med 120:493.e491-493.e496

    Article  Google Scholar 

  34. Zhou R, Zhou H, Cui M, Chen L, Xu J (2014) The association between aortic calcification and fracture risk in postmenopausal women in China: the prospective Chongqing osteoporosis study. PLoS One 9:e93882

    Article  PubMed  PubMed Central  Google Scholar 

  35. Laroche M, Pécourneau V, Blain H, Breuil V, Chapurlat R, Cortet B, Sutter B, Degboe Y (2017) Osteoporosis and ischemic cardiovascular disease. Joint Bone Spine 84:427–432

    Article  CAS  PubMed  Google Scholar 

  36. Szulc P, Samelson EJ, Kiel DP, Delmas PD (2009) Increased bone resorption is associated with increased risk of cardiovascular events in men: the MINOS study. J Bone Miner Res 24:2023–2031

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  37. Wiklund P, Nordström A, Jansson JH, Weinehall L, Nordström P (2012) Low bone mineral density is associated with increased risk for myocardial infarction in men and women. Osteoporos Int 23:963–970

    Article  CAS  PubMed  Google Scholar 

  38. Register TC, Hruska KA, Divers J, Bowden DW, Palmer ND, Carr JJ, Wagenknecht LE, Hightower RC, Xu J, Smith SC, Dietzen DJ, Langefeld CD, Freedman BI (2014) Sclerostin is positively associated with bone mineral density in men and women and negatively associated with carotid calcified atherosclerotic plaque in men from the African American-Diabetes Heart Study. J Clin Endocrinol Metab 99:315–321

    Article  CAS  PubMed  Google Scholar 

  39. Arko B, Prezelj J, Kocijancic A, Komel R, Marc J (2005) Association of the osteoprotegerin gene polymorphisms with bone mineral density in postmenopausal women. Maturitas 51:270–279

    Article  CAS  PubMed  Google Scholar 

  40. Ärnlöv J, Carlsson AC, Sundström J, Ingelsson E, Larsson A, Lind L, Larsson TE (2013) Serum FGF23 and risk of cardiovascular events in relation to mineral metabolism and cardiovascular pathology. Clin J Am Soc Nephrol 8:781–786

    Article  PubMed  PubMed Central  Google Scholar 

  41. Bai J, Gao Q, Wang C, Dai J (2020) Diabetes mellitus and risk of low-energy fracture: a meta-analysis. Aging Clin Exp Res 32:2173–2186

    Article  PubMed  Google Scholar 

  42. Luan L, Li R, Wang Z, Hou X, Gu W, Wang X, Yan S, Xu D (2016) Stroke increases the risk of hip fracture: a systematic review and meta-analysis. Osteoporos Int 27:3149–3154

    Article  CAS  PubMed  Google Scholar 

  43. Vinik AI, Camacho P, Reddy S, Valencia WM, Trence D, Matsumoto AM, Morley JE (2017) Aging, diabetes, and falls. Endocr Pract 23:1117–1139

    Article  PubMed  Google Scholar 

  44. Thrailkill KM, Lumpkin CK Jr, Bunn RC, Kemp SF, Fowlkes JL (2005) Is insulin an anabolic agent in bone? Dissecting the diabetic bone for clues. Am J Physiol Endocrinol Metab 289:E735-745

    Article  CAS  PubMed  Google Scholar 

  45. Starup-Linde J (2013) Diabetes, biochemical markers of bone turnover, diabetes control, and bone. Front Endocrinol (Lausanne) 4:21

    Article  PubMed  Google Scholar 

  46. Kim GL, Yi YH, Hwang HR, Kim J, Park Y, Kim YJ, Lee JG, Tak YJ, Lee SH, Lee SY, Cho YH, Park EJ, Lee Y (2021) The risk of osteoporosis and osteoporotic fracture following the use of irritable bowel syndrome medical treatment: an analysis using the OMOP CDM database. J Clin Med 10

  47. Compston J (2018) Type 2 diabetes mellitus and bone. J Intern Med 283:140–153

    Article  CAS  PubMed  Google Scholar 

  48. Marshall D, Johnell O, Wedel H (1996) Meta-analysis of how well measures of bone mineral density predict occurrence of osteoporotic fractures. BMJ 312:1254–1259

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  49. Cummings SR, Bates D, Black DM (2002) Clinical use of bone densitometryscientific review. JAMA 288:1889–1897

    Article  PubMed  Google Scholar 

  50. Banefelt J, Timoshanko J, Söreskog E, Ortsäter G, Moayyeri A, Åkesson KE, Spångéus A, Libanati C (2022) Total hip bone mineral density as an indicator of fracture risk in bisphosphonate-treated patients in a real-world setting. J Bone Miner Res 37:52–58

    Article  CAS  PubMed  Google Scholar 

  51. Leslie WD, Martineau P, Bryanton M, Lix LM (2019) Which is the preferred site for bone mineral density monitoring as an indicator of treatment-related anti-fracture effect in routine clinical practice? A registry-based cohort study. Osteoporos Int 30:1445–1453

    Article  CAS  PubMed  Google Scholar 

  52. Leslie WD, Majumdar SR, Morin SN, Lix LM (2016) Change in bone mineral density is an indicator of treatment-related antifracture effect in routine clinical practice: a registry-based cohort study. Ann Intern Med 165:465–472

    Article  PubMed  Google Scholar 

  53. Ioannidis G, Flahive J, Pickard L, Papaioannou A, Chapurlat RD, Saag KG, Silverman S, Anderson FA Jr, Gehlbach SH, Hooven FH, Boonen S, Compston JE, Cooper C, Díez-Perez A, Greenspan SL, Lacroix AZ, Lindsay R, Netelenbos JC, Pfeilschifter J, Rossini M, Roux C, Sambrook PN, Siris ES, Watts NB, Adachi JD (2013) Non-hip, non-spine fractures drive healthcare utilization following a fracture: the Global Longitudinal Study of Osteoporosis in Women (GLOW). Osteoporos Int 24:59–67

    Article  CAS  PubMed  Google Scholar 

Download references

Funding

The study was funded by the National Research Foundation of Korea (2020R1A2C2011587, 2021R1A2C2003410) and the Bio Industrial Strategic Technology Development Program (20003883) by the Ministry of Trade, Industry & Energy (MOTIE, Korea).

Author information

Authors and Affiliations

  1. Department of Internal Medicine, Seoul National University Bundang Hospital, Seongnam, Korea

    Sung Hye Kong

  2. Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Korea

    Sung Hye Kong, Jung Hee Kim & Chan Soo Shin

  3. Department of Integrative Medicine, Seoul National University Hospital, Seoul, 03080, Korea

    Sihyeon Kim, Yisak Kim & Kwangsoo Kim

  4. Interdisciplinary Program in Bioengineering, Seoul National University Graduate School, Seoul, Korea

    Yisak Kim

  5. Department of Internal Medicine, Seoul National University Hospital, Seoul, 03080, Korea

    Jung Hee Kim & Chan Soo Shin

Authors
  1. Sung Hye Kong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sihyeon Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yisak Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jung Hee Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kwangsoo Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Chan Soo Shin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Jung Hee Kim or Kwangsoo Kim.

Ethics declarations

Ethical approval

For this type of study, formal consent is not required.

Informed consent

Informed consent was waived because of the retrospective nature of the study.

Competing interests

SHK, SK, YK, JHK, KSK, and CSS declare that they have no conflict of interest.

Additional information

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Sung Hye Kong and Sihyeon Kim equally contributed to the manuscript.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 86 KB)

Rights and permissions

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kong, S.H., Kim, S., Kim, Y. et al. Development and validation of common data model-based fracture prediction model using machine learning algorithm. Osteoporos Int 34, 1437–1451 (2023). https://doi.org/10.1007/s00198-023-06787-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00198-023-06787-7

Keywords

Search

Navigation