Ronnie Sebro1,2, Cynthia De la Garza-Ramos3. 1. Department of Radiology, Mayo Clinic, Jacksonville, FL, 32224, USA. Sebro.ronnie@mayo.edu. 2. Center for Augmented Intelligence, Mayo Clinic, Jacksonville, FL, 32224, USA. Sebro.ronnie@mayo.edu. 3. Department of Radiology, Mayo Clinic, Jacksonville, FL, 32224, USA.
Abstract
OBJECTIVES: To use multivariable machine learning using the computed tomography (CT) attenuation of each of the bones in the lumbar spine, pelvis, and sacrum, to predict osteoporosis/osteopenia. METHODS: This was a retrospective study of 394 patients aged 50 years or older with CT scans of the abdomen and pelvis and dual-energy x-ray absorptiometry (DXA) scans obtained within 6 months of each other. Volumetric segmentations were performed for each of the bones from L1-L4 vertebrae, pelvis, and sacrum to obtain the mean CT attenuation of each bone. The data was randomly split into training/validation (n = 274, 70%) and test (n = 120, 30%) datasets. The CT attenuation of the L1 vertebrae, univariate logistic regression, least absolute shrinkage and selection operator (LASSO), and support vector machines (SVM) with radial basis function (RBF) were used to predict osteoporosis/osteopenia. The performance of using the CT attenuation at L1 to the univariate logistic regression, LASSO, and SVM models were compared using DeLong's test in the test dataset. RESULTS: All CT attenuation measurements were predictive of osteoporosis/osteopenia (p < 0.001 for all). The SVM model (accuracy = 0.892, AUC = 0.886) outperformed the models using the CT attenuation of threshold of 173.9 Hounsfield units (HU) at L1 (accuracy = 0.725, AUC = 0.739, p = 0.010), the univariate logistic regression model (accuracy = 0.767, AUC = 0.533, p < 0.001) and the LASSO model (accuracy = 0.817, AUC = 0.711, p = 0.007) to predict osteoporosis/osteopenia. CONCLUSION: A SVM model using the CT attenuations of multiple bones within the lumbar spine and pelvis and clinical data has a better ability to predict osteoporosis/osteopenia than using the CT attenuation of L1 or a LASSO model. KEY POINTS: • Multivariable SVM model using the CT attenuation of multiple bones and clinical/demographic data was more predictive than using the CT attenuation at L1 only.
OBJECTIVES: To use multivariable machine learning using the computed tomography (CT) attenuation of each of the bones in the lumbar spine, pelvis, and sacrum, to predict osteoporosis/osteopenia. METHODS: This was a retrospective study of 394 patients aged 50 years or older with CT scans of the abdomen and pelvis and dual-energy x-ray absorptiometry (DXA) scans obtained within 6 months of each other. Volumetric segmentations were performed for each of the bones from L1-L4 vertebrae, pelvis, and sacrum to obtain the mean CT attenuation of each bone. The data was randomly split into training/validation (n = 274, 70%) and test (n = 120, 30%) datasets. The CT attenuation of the L1 vertebrae, univariate logistic regression, least absolute shrinkage and selection operator (LASSO), and support vector machines (SVM) with radial basis function (RBF) were used to predict osteoporosis/osteopenia. The performance of using the CT attenuation at L1 to the univariate logistic regression, LASSO, and SVM models were compared using DeLong's test in the test dataset. RESULTS: All CT attenuation measurements were predictive of osteoporosis/osteopenia (p < 0.001 for all). The SVM model (accuracy = 0.892, AUC = 0.886) outperformed the models using the CT attenuation of threshold of 173.9 Hounsfield units (HU) at L1 (accuracy = 0.725, AUC = 0.739, p = 0.010), the univariate logistic regression model (accuracy = 0.767, AUC = 0.533, p < 0.001) and the LASSO model (accuracy = 0.817, AUC = 0.711, p = 0.007) to predict osteoporosis/osteopenia. CONCLUSION: A SVM model using the CT attenuations of multiple bones within the lumbar spine and pelvis and clinical data has a better ability to predict osteoporosis/osteopenia than using the CT attenuation of L1 or a LASSO model. KEY POINTS: • Multivariable SVM model using the CT attenuation of multiple bones and clinical/demographic data was more predictive than using the CT attenuation at L1 only.
Authors: Peiqi Chen; John H Krege; Jonathan D Adachi; Jerilynn C Prior; Alan Tenenhouse; Jacques P Brown; Emmanuel Papadimitropoulos; Nancy Kreiger; Wojciech P Olszynski; Robert G Josse; David Goltzman Journal: J Bone Miner Res Date: 2009-03 Impact factor: 6.741
Authors: S R Cummings; M C Nevitt; W S Browner; K Stone; K M Fox; K E Ensrud; J Cauley; D Black; T M Vogt Journal: N Engl J Med Date: 1995-03-23 Impact factor: 91.245
Authors: Jorma Panula; Harri Pihlajamäki; Ville M Mattila; Pekka Jaatinen; Tero Vahlberg; Pertti Aarnio; Sirkka-Liisa Kivelä Journal: BMC Musculoskelet Disord Date: 2011-05-20 Impact factor: 2.362