Innovation and application of Large Language Models (LLMs) in dentistry - a scoping review

Abstract

Objective: Large Language Models (LLMs) have revolutionized healthcare, yet their integration in dentistry remains underexplored. Therefore, this scoping review aims to systematically evaluate current literature on LLMs in dentistry.

Data sources: The search covered PubMed, Scopus, IEEE Xplore, and Google Scholar, with studies selected based on predefined criteria. Data were extracted to identify applications, evaluation metrics, prompting strategies, and deployment levels of LLMs in dental practice.

Results: From 4079 records, 17 studies met the inclusion criteria. ChatGPT was the predominant model, mainly used for post-operative patient queries. Likert scale was the most reported evaluation metric, and only two studies employed advanced prompting strategies. Most studies were at level 3 of deployment, indicating practical application but requiring refinement.

Conclusion: LLMs showed extensive applicability in dental specialties; however, reliance on ChatGPT necessitates diversified assessments across multiple LLMs. Standardizing reporting practices and employing advanced prompting techniques are crucial for transparency and reproducibility, necessitating continuous efforts to optimize LLM utility and address existing challenges.

Fig. 1. PRISMA flowchart.

The figure illustrates the search and retrieval processes of studies via PubMed, Scopus, Google Scholar and IEEE Xplore. After comprehensive screening, 17 studies were found to be eligible and included in the analysis.

Fig. 2. Evaluation metrics utilized in the included studies.

The figure shows a brief description of the evaluation metrics used. The size of each colored box represents the number (weightage) of studies utilizing the individual metrics.

Fig. 3. Graphical representation of user experience.

The figure shows the positive, negative, neutral and mixed perspective of the human evaluators reported in the included studies.