Yonsei Med J.  2013 Nov;54(6):1321-1330. 10.3349/ymj.2013.54.6.1321.

Osteoporosis Risk Prediction for Bone Mineral Density Assessment of Postmenopausal Women Using Machine Learning

• Yoo TK
• Kim SK
• Kim DW
• Choi JY
• Lee WH
• Oh E
• Park EC

• KMID: 1798126
• DOI: http://doi.org/10.3349/ymj.2013.54.6.1321

Abstract

PURPOSE
A number of clinical decision tools for osteoporosis risk assessment have been developed to select postmenopausal women for the measurement of bone mineral density. We developed and validated machine learning models with the aim of more accurately identifying the risk of osteoporosis in postmenopausal women compared to the ability of conventional clinical decision tools.
MATERIALS AND METHODS
We collected medical records from Korean postmenopausal women based on the Korea National Health and Nutrition Examination Surveys. The training data set was used to construct models based on popular machine learning algorithms such as support vector machines (SVM), random forests, artificial neural networks (ANN), and logistic regression (LR) based on simple surveys. The machine learning models were compared to four conventional clinical decision tools: osteoporosis self-assessment tool (OST), osteoporosis risk assessment instrument (ORAI), simple calculated osteoporosis risk estimation (SCORE), and osteoporosis index of risk (OSIRIS).
RESULTS
SVM had significantly better area under the curve (AUC) of the receiver operating characteristic than ANN, LR, OST, ORAI, SCORE, and OSIRIS for the training set. SVM predicted osteoporosis risk with an AUC of 0.827, accuracy of 76.7%, sensitivity of 77.8%, and specificity of 76.0% at total hip, femoral neck, or lumbar spine for the testing set. The significant factors selected by SVM were age, height, weight, body mass index, duration of menopause, duration of breast feeding, estrogen therapy, hyperlipidemia, hypertension, osteoarthritis, and diabetes mellitus.
CONCLUSION
Considering various predictors associated with low bone density, the machine learning methods may be effective tools for identifying postmenopausal women at high risk for osteoporosis.

Keyword

Screening; machine learning; risk assessment; clinical decision tools; support vector machines

MeSH Terms

Aged
*Artificial Intelligence
Bone Density/*physiology
Female
Humans
Middle Aged
Osteoporosis, Postmenopausal

Figure

• 

  Fig. 1 Performance results (AUC) of the machine learning and conventional methods using 10-fold cross validation. Error bars indicate the standard deviation of the mean. AUC, area under the curve; SVM, support vector machines; RF, random forests; ANN, artificial neural networks; LR, logistic regression; OST, osteoporosis self-assessment tool; ORAI, osteoporosis risk assessment instrument; SCORE, simple calculated osteoporosis risk estimation; OSIRIS, osteoporosis index of risk.

• 

  Fig. 2 Receiver operating characteristic curves (ROC) of support vector machines (SVM), logistic regression (LR), and osteoporosis self-assessment tool (OST) in predicting osteoporosis risk at any site among total hip, femoral neck, or lumbar spine.

Reference

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

2. Kanis JA. Assessment of fracture risk and its application to screening for postmenopausal osteoporosis: synopsis of a WHO report. WHO Study Group. Osteoporos Int. 1994; 4:368–381.

3. Nayak S, Roberts MS, Greenspan SL. Cost-effectiveness of different screening strategies for osteoporosis in postmenopausal women. Ann Intern Med. 2011; 155:751–761.

4. Elliot-Gibson V, Bogoch ER, Jamal SA, Beaton DE. Practice patterns in the diagnosis and treatment of osteoporosis after a fragility fracture: a systematic review. Osteoporos Int. 2004; 15:767–778.

5. Raisz LG. Clinical practice. Screening for osteoporosis. N Engl J Med. 2005; 353:164–171.

6. Trémollieres FA, Pouillès JM, Drewniak N, Laparra J, Ribot CA, Dargent-Molina P. Fracture risk prediction using BMD and clinical risk factors in early postmenopausal women: sensitivity of the WHO FRAX tool. J Bone Miner Res. 2010; 25:1002–1009.

7. Choi YJ, Oh HJ, Kim DJ, Lee Y, Chung YS. The prevalence of osteoporosis in Korean adults aged 50 years or older and the higher diagnosis rates in women who were beneficiaries of a national screening program: the Korea National Health and Nutrition Examination Survey 2008-2009. J Bone Miner Res. 2012; 27:1879–1886.

8. Cui LH, Choi JS, Shin MH, Kweon SS, Park KS, Lee YH, et al. Prevalence of osteoporosis and reference data for lumbar spine and hip bone mineral density in a Korean population. J Bone Miner Metab. 2008; 26:609–617.

9. Choi HS, Oh HJ, Choi H, Choi WH, Kim JG, Kim KM, et al. Vitamin D insufficiency in Korea--a greater threat to younger generation: the Korea National Health and Nutrition Examination Survey (KNHANES) 2008. J Clin Endocrinol Metab. 2011; 96:643–651.

10. Khosla S, Melton LJ 3rd. Clinical practice. Osteopenia. N Engl J Med. 2007; 356:2293–2300.

11. Koh LK, Sedrine WB, Torralba TP, Kung A, Fujiwara S, Chan SP, et al. A simple tool to identify asian women at increased risk of osteoporosis. Osteoporos Int. 2001; 12:699–705.

12. Richy F, Gourlay M, Ross PD, Sen SS, Radican L, De Ceulaer F, et al. Validation and comparative evaluation of the osteoporosis self-assessment tool (OST) in a Caucasian population from Belgium. QJM. 2004; 97:39–46.

13. Rud B, Hilden J, Hyldstrup L, Hróbjartsson A. The Osteoporosis Self-Assessment Tool versus alternative tests for selecting postmenopausal women for bone mineral density assessment: a comparative systematic review of accuracy. Osteoporos Int. 2009; 20:599–607.

14. Hofbauer LC, Brueck CC, Singh SK, Dobnig H. Osteoporosis in patients with diabetes mellitus. J Bone Miner Res. 2007; 22:1317–1328.

15. Hsieh CH, Lu RH, Lee NH, Chiu WT, Hsu MH, Li YC. Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks. Surgery. 2011; 149:87–93.

16. Larrañaga P, Calvo B, Santana R, Bielza C, Galdiano J, Inza I, et al. Machine learning in bioinformatics. Brief Bioinform. 2006; 7:86–112.

17. Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995; 20:273–297.

18. Breiman L. Random forests. Mach Learn. 2001; 45:5–32.

19. Dreiseitl S, Ohno-Machado L. Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform. 2002; 35:352–359.

20. Bishop CM. Pattern Recognition and Machine Learning. 4th ed. New York: Springer;2006.

21. Ordóñez C, Matías JM, de Cos Juez JF, García PJ. Machine learning techniques applied to the determination of osteoporosis incidence in post-menopausal women. Math Comput Model. 2009; 50:673–679.

22. De Cos Juez FJ, Suárez-Suárez MA, Sánchez Lasheras F, Murcia-Mazón A. Application of neural networks to the study of the influence of diet and lifestyle on the value of bone mineral density in post-menopausal women. Math Comput Model. 2011; 54:1665–1670.

23. Lix LM, Yogendran MS, Leslie WD, Shaw SY, Baumgartner R, Bowman C, et al. Using multiple data features improved the validity of osteoporosis case ascertainment from administrative databases. J Clin Epidemiol. 2008; 61:1250–1260.

24. Walid M, Ahmad S, Fadi C, Dima R. Intelligent predictive osteoporosis system. Int J Comput Appl. 2011; 32:28–30.

25. Ministry for Health, Welfare and Family Affairs. The Fifth Korea National Health and Nutrition Examination Survey (KNHANES V), 2010-Health Examination. accessed on 2012, December 26. Available at: http://knhanes.cdc.go.kr/.

26. Batista GEAPA, Monard MC. An analysis of four missing data treatment methods for supervised learning. Appl Artif Intell. 2003; 17:519–533.

27. Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. IJCAI. 1995; 14:1137–1143.

28. Saeys Y, Inza I, Larrañaga P. A review of feature selection techniques in bioinformatics. Bioinformatics. 2007; 23:2507–2517.

29. Dash M, Liu H. Consistency-based search in feature selection. Artif Intell. 2003; 151:155–176.

30. Kotsiantis S, Kanellopoulos D, Pintelas P. Handling imbalanced datasets: a review. GESTS Int T Comput Sci Eng. 2006; 30:25–36.

31. Sun Y, Kamel MS, Wong AKC, Wang Y. Cost-sensitive boosting for classification of imbalanced data. Pattern Recogn. 2007; 40:3358–3378.

32. Fluss R, Faraggi D, Reiser B. Estimation of the Youden Index and its associated cutoff point. Biom J. 2005; 47:458–472.

33. Agranoff D, Fernandez-Reyes D, Papadopoulos MC, Rojas SA, Herbster M, Loosemore A, et al. Identification of diagnostic markers for tuberculosis by proteomic fingerprinting of serum. Lancet. 2006; 368:1012–1021.

34. Schwartz EN, Steinberg DM. Prescreening tools to determine who needs DXA. Curr Osteoporos Rep. 2006; 4:148–152.

35. Patel VL, Shortliffe EH, Stefanelli M, Szolovits P, Berthold MR, Bellazzi R, et al. The coming of age of artificial intelligence in medicine. Artif Intell Med. 2009; 46:5–17.

36. Yeun EJ. A study on the health promoting lifestyle practices of middle-aged women in Korea. J Korean Soc Health Educ Promot. 2000; 17:41–59.

37. Ferrar L, Jiang G, Armbrecht G, Reid DM, Roux C, Glüer CC, et al. Is short vertebral height always an osteoporotic fracture? The Osteoporosis and Ultrasound Study (OPUS). Bone. 2007; 41:5–12.

38. Khosla S, Melton LJ 3rd, Atkinson EJ, O'Fallon WM, Klee GG, Riggs BL. Relationship of serum sex steroid levels and bone turn-over markers with bone mineral density in men and women: a key role for bioavailable estrogen. J Clin Endocrinol Metab. 1998; 83:2266–2274.

39. Lipworth L, Bailey LR, Trichopoulos D. History of breast-feeding in relation to breast cancer risk: a review of the epidemiologic literature. J Natl Cancer Inst. 2000; 92:302–312.

40. Kim KC, Shin DH, Lee SY, Im JA, Lee DC. Relation between obesity and bone mineral density and vertebral fractures in Korean postmenopausal women. Yonsei Med J. 2010; 51:857–863.

41. MacGregor GA, Cappuccio FP. The kidney and essential hypertension: a link to osteoporosis? J Hypertens. 1993; 11:781–785.

42. Yu W, Liu T, Valdez R, Gwinn M, Khoury MJ. Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes. BMC Med Inform Decis Mak. 2010; 10:16.

43. Yang ZR, Chou KC. Bio-support vector machines for computational proteomics. Bioinformatics. 2004; 20:735–741.

44. Liu HX, Zhang RS, Luan F, Yao XJ, Liu MC, Hu ZD, et al. Diagnosing breast cancer based on support vector machines. J Chem Inf Comput Sci. 2003; 43:900–907.

45. Van Staa TP, Leufkens HG, Abenhaim L, Zhang B, Cooper C. Use of oral corticosteroids and risk of fractures. J Bone Miner Res. 2000; 15:993–1000.

46. Lips P, Hosking D, Lippuner K, Norquist JM, Wehren L, Maalouf G, et al. The prevalence of vitamin D inadequacy amongst women with osteoporosis: an international epidemiological investigation. J Intern Med. 2006; 260:245–254.

47. Choi JY, Shin A, Park SK, Chung HW, Cho SI, Shin CS, et al. Genetic polymorphisms of OPG, RANK, and ESR1 and bone mineral density in Korean postmenopausal women. Calcif Tissue Int. 2005; 77:152–159.