Premium
Application of machine learning for diagnostic prediction of root caries
Author(s) -
Hung Man,
Voss Maren W.,
Rosales Megan N.,
Li Wei,
Su Weicong,
Xu Julie,
Bounsanga Jerry,
RuizNegrón Bianca,
Lauren Evelyn,
Licari Frank W.
Publication year - 2019
Publication title -
gerodontology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.7
H-Index - 54
eISSN - 1741-2358
pISSN - 0734-0664
DOI - 10.1111/ger.12432
Subject(s) - root caries , medicine , machine learning , artificial intelligence , receiver operating characteristic , population , root (linguistics) , decision tree , dentistry , computer science , environmental health , linguistics , philosophy
Objective This study sought to utilise machine learning methods in artificial intelligence to select the most relevant variables in classifying the presence and absence of root caries and to evaluate the model performance. Background Dental caries is one of the most prevalent oral health problems. Artificial intelligence can be used to develop models for identification of root caries risk and to gain valuable insights, but it has not been applied in dentistry. Accurately identifying root caries may guide treatment decisions, leading to better oral health outcomes. Methods Data were obtained from the 2015‐2016 National Health and Nutrition Examination Survey and were randomly divided into training and test sets. Several supervised machine learning methods were applied to construct a tool that was capable of classifying variables into the presence and absence of root caries. Accuracy, sensitivity, specificity and area under the receiver operating curve were computed. Results Of the machine learning algorithms developed, support vector machine demonstrated the best performance with an accuracy of 97.1%, precision of 95.1%, sensitivity of 99.6% and specificity of 94.3% for identifying root caries. The area under the curve was 0.997. Age was the feature most strongly associated with root caries. Conclusion The machine learning algorithms developed in this study perform well and allow for clinical implementation and utilisation by dental and nondental professionals. Clinicians are encouraged to adopt the algorithms from this study for early intervention and treatment of root caries for the ageing population of the United States, and for attaining precision dental medicine.