Democritus University of Thrace (DUTH)
Παράγοντες κινδύνου χαμηλής οστικής μάζας: η μελέτη των κλινικών εργαλείων (screening tools) και των υπολογιστικών τεχνικών
Abstract
dc:descriptionTo evaluate the power of six osteoporosis screening instruments. The Bayesian networks are becoming an increasingly important area in applications to medical diagnosis. ANN could have a good performance in identifying osteoporotic subjects in the elderly and it might serve as an alternative tool to screen the individual who should arrange further work-up like DXA.Data concerning several osteoporosis risk factors were prospectively collected from 1000 postmenopausal women aged 42-87 years who underwent dual-energy X-ray absorptiometry (DXA) screening. Six osteoporosis risk factor screening tools were applied to this sample to evaluate their performance and choose the most appropriate tool for the study population. Trying to measure the accuracy of t-score we had utilized Neural and Bayesian networks.The most important screening tool for osteoporosis status was the Simple Calculated Osteoporosis Risk Estimation, which had an area under the curve (AUC) of 0.678, a sensitivity of 72%, and a specificity of 72%, with a cut-off point of 20.75. The most important screening tool for osteoporosis risk was the Osteoporosis Self-assessment Tool, which had an AUC of 0.643, a sensitivity of 77%, and a specificity of 46%, with a cut-off point of -2.9. From artificial neural networks, multilayer perceptron (MLP) showed classification percent 71.33% and radial basis function (RBF) 75.52%.Some commonly used clinical risk instruments demonstrate high sensitivity for distinguishing individuals with DXA-ascertained osteoporosis or reduced bone mineral density. The development of Information Technology has generated large amount of databases and huge data in various areas. The research in databases and information technology has given rise to an approach to store and manipulate this data for further decision making. The evaluation of ANN in bone disease osteoporosis and the prediction of fracture risk and diagnosis of osteoporosis are the major concerns in orthopaedics. Evaluation of ANN is a great tool for prediction in different parts of medicine such as the prediction of diabetes. The future for this type of work can lie in either of two directions. The networks can be trained on a very large database and then used as a decision support tool.
Degree
thesis:*- Grantor dc:publisher
- Democritus University of Thrace (DUTH)
- Year dc:date
- 2017
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Christodoulou, Sotirios
- Χριστοδούλου, Σωτήριος
Subjects
dc:subject × 6Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/40502