首页|Baskent University Reports Findings in Machine Learning (Evaluation of different machine learning algorithms for extraction decision in orthodontic treatment)
Baskent University Reports Findings in Machine Learning (Evaluation of different machine learning algorithms for extraction decision in orthodontic treatment)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Machine Learning is the subject o f a report. According to news reporting out of Ankara, Turkey, by NewsRx editors , research stated, "The extraction decision significantly affects the treatment process and outcome. Therefore, it is crucial to make this decision with a more objective and standardized method." Financial support for this research came from Baskent Universitesi. Our news journalists obtained a quote from the research from Baskent University, "The objectives of this study were (1) to identify the best-performing model am ong seven machine learning (ML) models, which will standardize the extraction de cision and serve as a guide for inexperienced clinicians, and (2) to determine t he important variables for the extraction decision. This study included 1000 pat ients who received orthodontic treatment with or without extraction (500 extract ion and 500 non-extraction). The success criteria of the study were the decision s made by the four experienced orthodontists. Seven ML models were trained using 36 variables; including demographic information, cephalometric and model measur ements. First, the extraction decision was performed, and then the extraction ty pe was identified. Accuracy and area under the curve (AUC) of the receiver opera ting characteristics (ROC) curve were used to measure the success of ML models. The Stacking Classifier model, which consists of Gradient Boosted Trees, Support Vector Machine, and Random Forest models, showed the highest performance in ext raction decision with 91.2% AUC. The most important features deter mining extraction decision were maxillary and mandibular arch length discrepancy , Wits Appraisal, and ANS-Me length. Likewise, the Stacking Classifier showed th e highest performance with 76.3% accuracy in extraction type decis ions. The most important variables for the extraction type decision were mandibu lar arch length discrepancy, Class I molar relationship, cephalometric overbite, Wits Appraisal, and L1-NB distance. The Stacking Classifier model exhibited the best performance for the extraction decision."
AnkaraTurkeyEurasiaAlgorithmsCyb orgsEmerging TechnologiesHealth and MedicineMachine LearningOrthodontics