Abstract
Summary
We used quantitative computed tomography and finite element analysis to classify women with and without hip fracture. Highly accurate classifications were achieved indicating the potential for these methods to be used for subject-specific assessment of fracture risk.
Introduction
Areal bone mineral density (aBMD) is the current clinical diagnostic standard for assessing fracture risk; however, many fractures occur in people not defined as osteoporotic by aBMD. Finite element (FE) analysis based on quantitative computed tomography (QCT) images takes into account both bone material and structural properties to provide subject-specific estimates of bone strength. Thus, our objective was to determine if FE estimates of bone strength could classify women with and without hip fracture.
Methods
Twenty women with femoral neck fracture and 15 women with trochanteric fractures along with 35 age-matched controls were scanned with QCT at the hip. Since it is unknown how a specific subject will fall, FE analysis was used to estimate bone stiffness and bone failure load under loading configurations with femoral neck internal rotation angles ranging from −30° to 45° with 15° intervals. Support vector machine (SVM) models and a tenfold cross-validation scheme were used to classify the subjects with and without fracture.
Results
High accuracy was achieved when using only FE analysis for classifying the women with and without fracture both when the fracture types were pooled (82.9 %) and when analyzed separately by femoral neck fracture (87.5 %) and trochanteric fracture (80.0 %). The accuracy was further increased when FE analysis was combined with volumetric BMD (pooled fractures accuracy, 91.4 %)
Conclusions
While larger prospective studies are needed, these results demonstrate that FE analysis using multiple loading configurations together with SVM models can accurately classify individuals with previous hip fracture.
Similar content being viewed by others
References
Amin S, Kopperdhal DL, Melton LJ, Achenbach SJ, Therneau TM, Riggs BL, Keaveny TM, Khosla S (2011) Association of hip strength estimates by finite element analysis with fractures in women and men. J Bone Miner Res 26:1593–1600
Bessho M, Ohnishi I, Matsuyama J, Matsumoto T, Imai K, Nakamura K (2007) Prediction of strength and strain of the proximal femur by a CT-based finite element method. J Biomech 40:1745–1753
Bessho M, Ohnishi I, Matsumoto T, Ohashi S, Matsuyama J, Tobita K, Kaneko M, Nakamura K (2009) Prediction of proximal femur strength using a CT-based nonlinear finite element method: differences in predicted fracture load and site with changing load and boundary conditions. Bone 45:226–231
Cody DD, Gross GJ, Hou FJ, Spencer HJ, Goldstein SA, Fyhrie DP (1999) Femoral strength is better predicted by finite element models than QCT and DXA. J Biomech 32:1013–1020
Dragomir-Daescu D, Op Den Buijs J, McEligot S, Dai Y, Entwistle RC, Salas C, Melton LJ, Bennet KE, Khosla S, Amin S (2011) Robust QCT/FEA models of proximal femur stiffness and fracture load during a sideways fall on the hip. Ann Biomed Eng 39:742–755
Duchemin L, Mitton D, Jolivet E, Bousson V, Laredo JD, Skalli W (2008) An anatomical subject-specific FE-model for hip fracture load prediction. Comput Method Biomech 11:105–111
Grassi L, Schileo E, Taddei F, Zani L, Juszczyk M, Cristofolini L, Viceconti M (2012) Accuracy of finite element predictions in sideways load configurations for the proximal human femur. J Biomech 45:394–399
Keaveny TM, Kopperdahl DL, Melton LJ, Hoffmann PF, Amin S, Riggs BL, Khosla S (2010) Age-dependence of femoral strength in white women and men. J Bone Miner Res 25:994–1001
Keyak JH, Rossi SA, Jones KA, Skinner HB (1998) Prediction of femoral fracture load using automated finite element modeling. J Biomech 31:125–133
Keyak JH (2001) Improved prediction of proximal femoral fracture load using nonlinear finite element models. Med Eng Phys 23:165–173
Keyak JH, Sigurdsson S, Karlsdottir G, Oskarsdottir D, Sigmarsdottir A, Zhao S, Kornak J, Harris TB, Sigurdsson G, Jonsson BY, Siggeirsdottir K, Eiriksdottir G, Gudnason V, Lang TF (2011) Male–female differences in the association between incident hip fracture and proximal femoral strength: a finite element analysis study. Bone 48:1239–1245
Koivumäki JE, Thevenot J, Pulkkinen P, Kuhn V, Link TM, Eckstein F, Jämsä T (2012) Ct-based finite element models can be used to estimate experimentally measured failure loads in the proximal femur. Bone 50:824–829
Orwoll ES, Marshall LM, Nielson CM, Cummings SR, Lapidus J, Cauley JA, Ensrud K, Lane N, Hoffmann PR, Kopperdahl DL, Keaveny TM (2009) Finite element analysis of the proximal femur and hip fracture risk in older men. J Bone Miner Res 24:475–483
Viceconti M, Davinelli M, Taddei F, Cappello A (2004) Automatic generation of accurate subject-specific bone finite element models to be used in clinical studies. J Biomech 37:1597–1605
Wakao N, Harada A, Matsui Y, Takemura M, Shimokata H, Mizuno M, Ito M, Matsuyama Y, Ishiguro N (2009) The effect of impact direction on the fracture load of osteoporotic proximal femurs. Med Eng Phys 31:1134–1139
Cummings SR, Melton LJ (2002) Epidemiology and outcomes of osteoporotic fractures. Lancet 359:1761–1767
Melton LJ III (2003) Adverse outcomes of osteoporotic fractures in the general population. J Bone Miner Res 18:1139–1141
Nishiyama KK, Gilchrist S, Guy P, Cripton P, Boyd SK (2013) Proximal femur bone strength estimated by a computationally fast finite element analysis in a sideways fall configuration. J Biomech 46:1231–1236
Lang TF, Sigurdsson S, Karlsdottir G, Oskarsdottir D, Sigmarsdottir A, Chengshi J, Kornak J, Harris TB, Sigurdsson G, Jonsson BY, Siggeirsdottir K, Eiriksdottir G, Gudnason V, Keyak JH (2012) Age-related loss of proximal femoral strength in elderly men and women: the Age Gene/Environment Susceptibility Study–Reykjavik. Bone 50:743–748
Keaveny TM, McClung MR, Wan X, Kopperdahl DL, Mitlak BH, Krohn K (2012) Femoral strength in osteoporotic women treated with teriparatide or alendronate. Bone 50:165–170
Grisso JA, Kelsey JL, Strom BL, Ghiu GY, Maislin G, O'Brien LA, Hoffman S, Kaplan F (1991) Risk factors for falls as a cause of hip fracture in women. N Engl J Med 324:1326–1331
Nevitt MC, Cummings SR, Kidd S, Black D (1989) Risk factors for nonsyncopal falls - a prospective study. JAMA 261:2663–2668
Vapnik V (1982) Estimation of dependences based on empirical data: Springer Series in Statistics. Springer, New York
Valyon J, Horváth G (2003) A weighted generalized LS-SVM. Period Polytech Electr Eng 47:229–251
Kavitha MS, Asano A, Taguchi A, Kurita T, Sanada M (2012) Diagnosis of osteoporosis from dental panoramic radiographs using the support vector machine method in a computer-aided system. BMC Med Imaging 12:1
Lee S, Lee JW, Jeong JW, Yoo DS, Kim S (2008) A preliminary study on discrimination of osteoporotic fractured group from nonfractured group using support vector machine. Conf Proc IEEE Eng Med Biol Soc 2008:474–477
Nishiyama K, Macdonald M, Hanley A, Boyd K (2013) Women with previous fragility fractures can be classified based on bone microarchitecture and finite element analysis measured with HR- pQCT. Osteoporos Int 24:1733–1740
Ito M, Wakao N, Hida T, Matsui Y, Abe Y, Aoyagi K, Uetani M, Harada A (2010) Analysis of hip geometry by clinical CT for the assessment of hip fracture risk in elderly Japanese women. Bone 46:453–457
Treece GM, Gee AH, Mayhew PM, Poole KE (2010) High resolution cortical bone thickness measurement from clinical CT data. Med Image Anal 14:276–290
McErlain DD, Nishiyama KK, Sandino C, Boyd SK (2012) Evaluation of the effect of CT image resolution on voxel-based, subject specific FEA models. J Biomech 45(S1):S545
Keller TS (1994) Predicting the compressive mechanical behavior of bone. J Biomech 27:1159–1168
Varghese B, Short D, Penmetsa R, Goswami T, Hangartner T (2011) Computed-tomography-based finite-element models of long bones can accurately capture strain response to bending and torsion. J Biomech 44:1374–1379
Pistoia W, van Rietbergen B, Lochmüller EM, Lill CA, Eckstein F, Rüegsegger P (2002) Estimation of distal radius failure load with micro-finite element analysis models based on three-dimensional peripheral quantitative computed tomography images. Bone 30:842–848
McLachlan GJ, Do KA, Ambroise C (2004) Analyzing microarray gene expression data. Wiley, New Jersey
Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. SIGKDD Explor 11(1):10–18
Feng Z (2010) Classification versus association models: should the same methods apply? Scand J Clin Lab Invest Suppl 242:53–58
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297
Pinilla TP, Boardman KC, Bouxsein ML, Myers ER, Hayes WC (1996) Impact direction from a fall influences the failure load of the proximal femur as much as age-related bone loss. Calcif Tissue Int 58:231–235
Keyak JH, Skinner HB, Fleming JA (2001) Effect of force direction on femoral fracture load for two types of loading conditions. J Orthop Res 19:539–544
Ross PD, Norimatsu H, Davis JW, Yano K, Wasnich RD, Fujiwara S, Hosoda Y, Melton LJ (1991) A comparison of hip fracture incidence among native Japanese, Japanese Americans, and American Caucasians. Am J Epidemiol 133:801–809
Acknowledgments
We wish to thank all of the participants in this study as well as all of the technicians who performed the scans. We would also like to thank Meaghan Nolan for the preparation of the figure. We would like to acknowledge the Canadian Institutes of Health Research (CIHR), the Natural Sciences and Engineering Research Council of Canada (NSERC), and the Vanier Canada Graduate Scholarships.
Conflicts of interest
MI has received research grants from Chugai and consulting fees from Asahi. Kasei, Chugai, Ono, Astellas, and Daiichi Sankyo. KKN, AH, and SKB have no disclosures.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nishiyama, K.K., Ito, M., Harada, A. et al. Classification of women with and without hip fracture based on quantitative computed tomography and finite element analysis. Osteoporos Int 25, 619–626 (2014). https://doi.org/10.1007/s00198-013-2459-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00198-013-2459-6