Archive | 2019
Neural network analysis of bone vibration signals to assesses bone density
Abstract
Osteoporosis is a systemic disease, characterised by low bone \nmineral density (BMD) with a consequent increase in bone fragility. The most \ncommonly used method to examine BMD is dual energy X-ray absorptiometry \n(DXA). However DXA cannot be used reliably in children less than 5 years old \nbecause of the limitations in the availability of required normative data. \nVibration analysis is a well-established technique for analysing physical \nproperties of materials and so it has the potential for assessing BMD. The \noverall purpose of this study was development and evaluation of low frequency \nvibration analysis as a tool to assess BMD in children. A novel portable \ncomputer-controlled system that suitably vibrated the bone, acquired, stored, \ndisplayed and analysed the resulting bone vibration responses was developed \nand its performance was investigated by comparing it with DXA-derived BMD \nvalues in children. 41 children aged between 7 and 15 years suspected of having \nabnormal BMD were enrolled. The ulna was chosen for all tests due to the ease \nwith which it can be vibrated and responses measured. Frequency spectra of \nbone vibration responses were obtained using both impulse and continuous \nmethods and these plus the participants clinical data were processed by a \nmultilayer perceptron (MLP) artificial neural network. The correlation \ncoefficient values between MLP outputs and DXA-derived BMD values were \n0.79 and 0.86 for impulse and continuous vibration methods respectively. It was \ndemonstrated that vibration analysis has potential for assessing fracture risk.