Diagnosis of Tooth Prognosis Using Artificial Intelligence

Abstract

The accurate diagnosis of individual tooth prognosis has to be determined comprehensively in consideration of the broader treatment plan. The objective of this study was to establish an effective artificial intelligence (AI)-based module for an accurate tooth prognosis decision based on the Harvard School of Dental Medicine (HSDM) comprehensive treatment planning curriculum (CTPC). The tooth prognosis of 2359 teeth from 94 cases was evaluated with 1 to 5 levels (1—Hopeless, 5—Good condition for long term) by two groups (Model-A with 16, and Model-B with 13 examiners) based on 17 clinical determining factors selected from the HSDM-CTPC. Three AI machine-learning methods including gradient boosting classifier, decision tree classifier, and random forest classifier were used to create an algorithm. These three methods were evaluated against the gold standard data determined by consensus of three experienced prosthodontists, and their accuracy was analyzed. The decision tree classifier indicated the highest accuracy at 0.8413 (Model-A) and 0.7523 (Model-B). Accuracy with the gradient boosting classifier and the random forest classifier was 0.6896, 0.6687, and 0.8413, 0.7523, respectively. Overall, the decision tree classifier had the best accuracy among the three methods. The study contributes to the implementation of AI in the decision-making process of tooth prognosis in consideration of the treatment plan.

Artificial Intelligence in Dentistry: Past, Present, and Future

“…Lin et al suggested two models, first for identifying alveolar bone loss [ 22 ] and second for quantifying the extent of the bone loss [ 23 ]. Lee et al [ 24 ], based on the level of alveolar bone loss, developed a model formulated on a deep learning network of neurons to identify periodontally challenged molars and premolars and predict hopeless molars and premolars. Mol et al [ 25 ] and Carmody et al [ 26 ] presented models to categorize the severity of periapical lesions with regard to the diagnosis of periapical pathology.…”

“…A useful tool for determining dental prognosis in light of the treatment strategy is an AI-based machine learning system. To determine a tooth's prognosis for long-term oral health and function, a thorough treatment strategy must be carefully reviewed [ 24 ].…”

Machine Learning in Predicting Tooth Loss: A Systematic Review and Risk of Bias Assessment

“…Both the excluded studies made predictions without boosting the algorithm. Finally, five studies formed the basis of this study [ 17 , 18 , 19 , 20 , 21 ].…”

“…Four of the five included studies were development/validation studies [ 17 , 18 , 19 , 20 ]. Another study was a development study [ 21 ]. The included studies were published between 2019 and 2022.…”

“…Furthermore, two studies used socioeconomic variables [ 19 , 20 ]. Three out of the five studies included predictions made at the tooth level [ 17 , 18 , 21 ], and the two other studies with socioeconomic variables made predictions at the patient level [ 19 , 20 ]. All five included studies employed XGB as the model algorithm, and four employed random forest optimization (RFO) [ 17 , 19 , 20 , 21 ].…”