Pre-Diagnosis of Osteoartritis Before DEXA with the Help of Artificial Neural Networks

Year 2021, Volume: 1 Issue: 1, 76 - 82, 30.04.2021

Fadıma Gülsever Aksoy Volkan Akdoğan Murat Korkmaz

Abstract

Osteoarthritis (OA) is a degenerative joint disease that increases in frequency with age and can significantly impair an individual's quality of life by causing pain and disability [1]. OA is the most common type of arthritis. In this study, due to the unnecessary exposure to radiation disadvantage of X-ray absorptiometry (DEXA) test used in the diagnosis of osteoarthritis, it was aimed to create an alternative and artificial intelligence-based decision support system with high accuracy. The system will be used as a pre-diagnosis method and decision support system. For this
application, probabilistic artificial neural network designed with the help of a data set consisting of certain parameters taken from 200 patients. With its success rate, it has been observed that artificial neural networks can be used as a decision support system in the diagnosis of osteoarthritis. Thanks to this study, the possibility of applying the DEXA test to all patients who will come to the orthopedic and traumatology department with the suspicion of this disease will be minimized [2]

Keywords

osteoarthritis, artificial inteligence, decision support system, lubricin

References

• 1. Koca NT, Sepici V, Tosun AK, Koca G. Diz Osteoartritli Hastalarımızda Risk Faktörleri ve OsteoartritOsteoporoz İlişkisi. Turk J Osteoporos 2011;17.
• 2. Alakoç, Y., Akdoğan, V., Korkmaz, M., & Orhan, E. R. (2018). Osteoporoz Ön Tanısının Olasılıksal Sinir Ağları (OSA) Yardımıyla Gerçekleştirilmesi. Sakarya University Journal of Computer and Information Sciences, 1(3), 1-6.
• 3. Hedbom, E., & Häuselmann, H. J. (2002). Molecular aspects of pathogenesis in osteoarthritis: the role of inflammation. Cellular and Molecular Life Sciences CMLS, 59(1), 45-53.
• 4. Cesare Paul, E., & Abramson, S. B. (2006). Osteoartrit Patogenezi; İç: Dinçer F, editör. Kelley Romatoloji. Ankara: Güneş Kitapevi, 1493-1513.
• 5. Choi, Y. J. (2016). Dual-energy X-ray absorptiometry: beyond bone mineral density determination. Endocrinology and Metabolism, 31(1), 25.
• 6. Wang, Y., Gludish, D.W., Hayashi, K. et al. Synovial fluid lubricin increases in spontaneous canine cruciate ligament rupture. Sci Rep 10, 16725 (2020). https://doi.org/10.1038/s41598-020-73270-2
• 7. Wang, S., Dong, X., & Sun, R. (2010). Predicting saturates of sour vacuum gas oil using artificial neural networks and genetic algorithms. Expert Systems with Applications, 37(7), 4768-4771.
• 8. Takefuji, Y., & Wang, J. (Eds.). (1993). Neural networks in design and manufacturing. World Scientific.
• 9. Efendigil, T., Önüt, S., & Kahraman, C. (2009). A decision support system for demand forecasting with artificial neural networks and neuro-fuzzy models: A comparative analysis. Expert Systems with Applications, 36(3), 6697-6707.
• 10. Koskivaara, E. (2000). Artificial neural network models for predicting patterns in auditing monthly balances. Journal of the operational research society, 51(9), 1060-1069.
• 11. Egrioglu, E., Aladag, C. H., Yolcu, U., Uslu, V. R., & Basaran, M. A. (2009). A new approach based on artificial neural networks for high order multivariate fuzzy time series. Expert Systems with Applications, 36(7), 10589- 10594