Evaluation of some statistical methods for referring women for bone densitometry

• Autorzy: Enăchescu C.
• Języki publikacji: EN

Abstrakty

EN

The aim of our study is to design and compare some predictive models for estimating the Bone Mineral Density score (BMD) t-score. The data were collected, except the t-score, by self-report from 356 women recruited from the Cantacuzino Hospital, Bucharest, Romania, during the period 1998-2003. The following methods are tuned and compared on this data: the General Regression Model (GRM), the Classification Trees (CT) and the Multilayer Perceptrons Network (MLP). Comparatively with a number of different bone densitometry criteria, currently used in clinical practice, we show that each of the above investigated models have a better sensitivity and specificity.

Słowa kluczowe

EN

bone mineral density score; osteoporosis risk factors; general regression model; classification trees; multilayer perceptrons network

PL

gęstość kości; osteoporoza; drzewo klasyfikacyjne

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2007
• Tom: Vol. 27, no. 3
• Strony: 43--58
• Opis fizyczny: Bibliogr. 14 poz., rys., tab., wykr.

Twórcy

autor

Enăchescu C.

• Romanian Academy, Institute of Mathematical Statistics and Applied Mathematics, Calea 13 Septembrie No. 13, Bucharest 50711, Romania,

Bibliografia

• 1.Kanis J. A., Delmas P., Burckhardt P., et al.: Guide lines for diagnosis and management of osteoporosis: the European Foundation for Osteoporosis and Bone Disease. Osteoporos Int. 1997, 7, 390-406.
• 2. Melton L.J. III.: How many women have osteoporosis now? J. Bone Miner. Res. 1995, 10, 175-177.
• 3. Marshall D.A., Sheldon T.A., Jonsson E.: Recommendations for the application of bone density measurement. What can you believe? Int. J. Technol. Assess. Health Care, 1997, 13, 411-419.
• 4. Slemenda C.W., Hui S.L., Longcope C., et al.: Predictors of bone mass in perimenopausal women. Ann Intern. Med. 1990, 112, 96-100.
• 5. Ribot C., Pouilles J.M., Bonneau M., et al.: Assessment of the risk of post-menopausal osteoporosis using clinical factors. Clin. Endocrinol., 1992, 36, 225-228.
• 6. Bauer D.C., Browner W.S., Cauley J.A., et al.: Factors associated with appendicular bone mass in older women. Ann. Intern. Med., 1993, 118, 657-665.
• 7. Lydick E., Cook K., Turpin J., et al.: Development and validation of a simple questionnaire to facilitate identification of women likely to have low bone mass. Am. J. Ma Care, 1998, 4, 37-48.
• 8. Cadarette S.M., Jaglal S.B., Kreiger N., et al.: Development and validation of the osteoporosis risk assessment instrument to facilitate selection of women for bone densitometry. Can. Med. Assoc. J., 2000, 162, 1289-94.
• 9. Black D.M., Palermo L., Abbott T., et al.: SOFSURF: a simple useful risk factory system can identify the large majority of women with osteoporosis. Bone, 1998, 23, S605.
• 10. Martin A.: Risk Factors and the Diagnosis of Osteoporosis for Women. PhD Thesis, University "Carol Davilla": Bucharest 2004.
• 11. Hastie T., Tibshirani R., Friedman J.: The Elements of Statistical Learning. Data Mining, Inference, and Prediction. Springer-Verlag: New York 2002.
• 12. Ripley B.D.: Pattern Recognition and Neural Networks, Cambridge Univ. Press 1996.
• 13. Demuth H., Beale M.: Neural Network Toolbox. User's Guide, The Mathworks Inc.: Natick 2000.
• 14. Geusens P., Hochberg M.C., van der Voort D.J.M., et al.: Performance of Risk Indices for identifying Low Bone density in Postmenopausal Women. Mayo Clin Proc. 2002, 77, 629-637.