Prediction of hip fracture in post-menopausal women using artificial neural network approach

Abstract

Hip fracture is one of the most serious health problems among post-menopausal women with osteoporosis. It is very difficult to predict hip fracture, because it is affected by multiple risk factors. Existing statistical models for predicting hip fracture risk yield area under the receiver operating characteristic curve (AUC) ~0.7-0.85. In this study, we trained an artificial neural network (ANN) to predict hip fracture in one cohort, and validated its predictive performance in another cohort. The data for training and validation included age, bone mineral density (BMD), clinical factors, and lifestyle factors which had been obtained from a longitudinal study that involved 1167 women aged 60 years and above. The women had been followed up for up to 10 years, and during the period, the incidence of new hip fractures was ascertained. We applied feed-forward neural networks to learn from the data, and then used the learning for predicting hip fracture. Results of prediction showed that the accuracy of model I (which included only lumbar spine and femoral neck BMD) and model II (which included non-BMD factors) was 82% and 84%, respectively. When both BMD and non-BMD factors were combined (Model III), the accuracy increased to 87%. The AUC for model III was 0.94. These findings indicate that ANNs are able to predict hip fracture more accurately than any existing statistical models, and that ANNs can help stratify individuals for clinical management.

Overview of artificial neural network models in the biomedical domain

“…Due to their ability to analyse the data with nonlinear relationship, ANN models are being extensively used in the area of diagnosis (9, 10, 11): prognosis (12): classifi cation (13): prediction (14,15,16,17): and survival analysis (18).…”

Individualized fracture risk assessment: State-of-the-art and room for improvement

“…Recent studies have demonstrated that ANN performed better than traditional statistical models in terms of predicting vertebral fracture among postmenopausal women [ 86 ], and mortality following a hip fracture [ 87 ]. We and others [ 88 , 89 ] have also shown that for hip fracture prediction, ANN yielded a more accurate prediction than traditional statistical methods such as the logistic regression model.…”

“…Association analysis striving for elegance and parsimony are unlikely inadequate to delineate their separate contributions or to capture their interactional effects. Prediction analysis using machine learning approach (e.g., ANN and deep learning) may be statistically less elegant but it could help identify potential highly predictive factors that are ignored by traditional association analysis [ 88 , 89 ].…”

FRAX: re-adjust or re-think

“…Several studies have been published with the aim of either to predict an indicator of osteoporosis, such as BMD or fractures, or as a tool for automatic segmentation of the images of patients with or at risk of osteoporosis. Examples are those tools which used the supervised category of models to predict categorical outcomes, specifically the fractures/no-fracture classes [69][70][71] and osteonecrosis [72], whereas others predict quantitatively the BMD value [73,74].…”