Back to Search
Start Over
Development and Testing of a System for Predicting the Risk of Developing Disorders of Occlusive Relationships as a Component of the Rehabilitation Program for Patients with Myofascial Pain Syndrome of the Masticatory Muscles.
- Source :
- Journal of International Dental & Medical Research; 2024, Vol. 17 Issue 3, p1138-1145, 8p
- Publication Year :
- 2024
-
Abstract
- In modern dentistry, the diagnosis and treatment of occlusal disharmony pose a significant challenge. About 80% of individuals over the age of 18 exhibit various occlusal disorders and maxillofacial pathologies, linked to anatomical peculiarities, systemic function, pathological conditions, and other factors. Therefore, accurately predicting disease progression and complications is crucial. This study conducted a randomized controlled trial involving 150 patients. All patients underwent comprehensive dental examinations, incorporating both primary and adjunctive assessment methods. A neural network was trained and integrated into an expert system, which included a computer algorithm for input, output, and patient data analysis. The system's outcome involved multidimensional computerized forecasting of the risk of occlusal imbalance, considering the identification of hidden neural connections, and recommending potential further patient examinations. The advantages of this method of developing prognostic models using artificial neural networks over classical methods such as discriminant analysis, logistic regression, and multiple regression lie in their ability to address tasks of data identification and interpretation involving categorical and quantitative predictor variables of varying data sizes. Moreover, they can classify hidden neural connections inaccessible to simplified non-digital analyses. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 1309100X
- Volume :
- 17
- Issue :
- 3
- Database :
- Supplemental Index
- Journal :
- Journal of International Dental & Medical Research
- Publication Type :
- Academic Journal
- Accession number :
- 180414584