Procedure to Improve the Accuracy of Dental Implant Failures by Data Science Techniques
Nowadays, the prediction about dental implant failure is determined through clinical and radiological evaluation. For this reason, predictions are highly dependent on the Implantologists’ experience. In addition, it is extremely crucial to detect in time if a dental implant is going to fail, due to...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Articulo |
| Lenguaje: | Inglés |
| Publicado: |
2021
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/128264 |
| Aporte de: |
| Sumario: | Nowadays, the prediction about dental implant failure is determined through clinical and radiological evaluation. For this reason, predictions are highly dependent on the Implantologists’ experience. In addition, it is extremely crucial to detect in time if a dental implant is going to fail, due to time, cost, trauma to the patient, postoperative problems, among others. This paper proposes a procedure using multiple feature selection methods and classification algorithms to improve the accuracy of dental implant failures in the province of Misiones, Argentina, validated by human experts. The experimentation is performed with two data sets, a set of dental implants made for the case study and an artificially generated set. The proposed approach allows to know the most relevant features and improve the accuracy in the classification of the target class (dental implant failure), to avoid biasing the decision making based on the application and results of individual methods. The proposed approach achieves an accuracy of 79% of failures, while individual classifiers achieve a maximum of 72%. |
|---|