BackgroundIt is known that bone mineral density (BMD) predicts the fracture's risk only partially and the severity and number of vertebral fractures are predictive of subsequent osteoporotic fractures (OF). Spinal deformity index (SDI) integrates the severity and number of morphometric vertebral fractures. Nowadays, there is interest in developing algorithms that use traditional statistics for predicting OF. Some studies suggest their poor sensitivity. Artificial Neural Networks (ANNs) could represent an alternative. So far, no study investigated ANNs ability in predicting OF and SDI. The aim of the present study is to compare ANNs and Logistic Regression (LR) in recognising, on the basis of osteoporotic risk-factors and other clinical information, patients with SDI≥1 and SDI≥5 from those with SDI = 0.MethodologyWe compared ANNs prognostic performance with that of LR in identifying SDI≥1/SDI≥5 in 372 women with postmenopausal-osteoporosis (SDI≥1, n = 176; SDI = 0, n = 196; SDI≥5, n = 51), using 45 variables (44 clinical parameters plus BMD). ANNs were allowed to choose relevant input data automatically (TWIST-system-Semeion). Among 45 variables, 17 and 25 were selected by TWIST-system-Semeion, in SDI≥1 vs SDI = 0 (first) and SDI≥5 vs SDI = 0 (second) analysis. In the first analysis sensitivity of LR and ANNs was 35.8% and 72.5%, specificity 76.5% and 78.5% and accuracy 56.2% and 75.5%, respectively. In the second analysis, sensitivity of LR and ANNs was 37.3% and 74.8%, specificity 90.3% and 87.8%, and accuracy 63.8% and 81.3%, respectively.ConclusionsANNs showed a better performance in identifying both SDI≥1 and SDI≥5, with a higher sensitivity, suggesting its promising role in the development of algorithm for predicting OF.
Summary This study aimed to evaluate the prevalence of vertebral fractures in elderly women with a recent hip fracture. The burden of vertebral fractures expressed by the Spinal Deformity Index (SDI) is more strictly associated with the trochanteric than the cervical localization of hip fracture and may influence short-term functional outcomes. Introduction This study aimed to determine the prevalence and severity of vertebral fractures in elderly women with recent hip fracture and to assess whether the burden of vertebral fractures may be differently associated with trochanteric hip fractures with respect to cervical hip fractures. Methods We studied 689 Italian women aged 60 years or over with a recent low trauma hip fracture and for whom an adequate X-ray evaluation of spine was available. All radiographs were examined centrally for the presence of any vertebral deformities and radiological morphometry was performed. The SDI, which integrates both the number and the severity of fractures, was also calculated. Results Prevalent vertebral fractures were present in 55.7 % of subjects and 95 women (13.7 %) had at least one severe fracture. The women with trochanteric hip fracture showed higher SDI and higher prevalence of diabetes with respect to those with cervical hip fracture, p00.017 and p00.001, respectively. SDI, surgical menopause, family history of fragility fracture, and type2 diabetes mellitus were independently associated with the risk of trochanteric hip fracture. Moreover, a higher SDI was associated with a higher percentage of postsurgery complications (p00.05) and slower recovery (p<0.05). Conclusions Our study suggests that the burden of prevalent vertebral fractures is more strictly associated with the trochanteric than the cervical localisation of hip fracture and that elevated values of SDI negatively influence short term functional outcomes in women with hip fracture.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.