Artificial intelligence (AI), specifically machine learning (ML), is increasingly applied in decision-making for dental diagnosis, prognosis, and treatment. However, the methodological completeness of published models has not been rigorously assessed. We performed a scoping review of PubMed-indexed articles (English, 1 January 2018‒31 December 2023) that used ML in any dental specialty. Each study was evaluated with the TRIPOD + AI rubric for key reporting elements such as data preprocessing, model validation, and clinical performance. Out of 1,506 identified studies, 280 met the inclusion criteria. Oral and maxillofacial radiology (27.5%), oral and maxillofacial surgery (15.0%), and general dentistry (14.3%) were the most represented specialties. Sixty-four studies (22.9%) lacked comparison with a clinical reference standard or existing model performing the same task. Most models focused on classification (59.6%), whereas generative applications were relatively rare (1.4%). Key gaps included limited assessment of model bias, poor outlier reporting, scarce calibration evaluation, low reproducibility, and restricted data access. ML could transform dental care, but robust calibration assessment and equity evaluation are critical for real-world adoption. Future research should prioritize error explainability, outlier reporting, reproducibility, fairness, and prospective validation.
Lakhotia et al. (Wed,) studied this question.