Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4948436 | Neurocomputing | 2016 | 6 Pages |
Abstract
In order to achieve a diagnosis system of osteoporosis with the assistance of a network, an artificial neural network model is established and applied. We extract features through the observation of X-ray images and clinical main symptoms from patients with osteoporosis by three experienced orthopedists and three experienced radiologists and score the features related to osteoporosis according to the quantified standard. Then parts of patients are selected randomly as the training set and the rest is regarded as the prediction set. Input score results and biochemical parameters are related to osteoporosis. The prediction results of all samples are compared with the predicted results of logistic regression. Diagnostic results of the artificial neural network model are compared with the results of logistic regression. The sensitivities are 94.5% and 63.6%, respectively. The specificities are 96.9% and 87.5%, respectively. The area under the receiver operating characteristic curve of the artificial neural network (0.950) is larger than that of logistic regression (0.870), P=0.034. The results of this study show that the artificial neural network is effective in the diagnostic system of osteoporosis.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Xinghu Yu, Chao Ye, Liangbi Xiang,