[Paper Review] Generative artificial intelligence in dentistry: Current approaches and future challenges

Fabián Villena, Claudia Véliz+2 more|arXiv (Cornell University)|Jul 24, 2024

Artificial Intelligence in Healthcare and EducationMedicine3 citations

TL;DR

This review explores the current applications and future challenges of generative artificial intelligence (GenAI) in dentistry, focusing on its roles in dental education, clinical decision support, patient communication, and research. It highlights GenAI's potential to enhance learning, diagnosis, and research efficiency while addressing critical issues like data privacy, ethical use, bias, and over-reliance on technology.

ABSTRACT

Artificial intelligence (AI) has become a commodity for people because of the advent of generative AI (GenAI) models that bridge the usability gap of AI by providing a natural language interface to interact with complex models. These GenAI models range from text generation - such as two-way chat systems - to the generation of image or video from textual descriptions input by a user. These advancements in AI have impacted Dentistry in multiple aspects. In dental education, the student now has the opportunity to solve a plethora of questions by only prompting a GenAI model and have the answer in a matter of seconds. GenAI models can help us deliver better patient healthcare by helping practitioners gather knowledge quickly and efficiently. Finally, GenAI can also be used in dental research, where the applications range from new drug discovery to assistance in academic writing. In this review, we first define GenAI models and describe their multiple generation modalities; then, we explain and discuss their current and potential applications in Dentistry; and finally, we describe the challenges these new technologies impose in our area.

Motivation & Objective

• To analyze the current and emerging applications of generative AI (GenAI) across dental education, clinical practice, patient communication, and research.
• To identify and discuss the major ethical, privacy, and technical challenges associated with integrating GenAI into dental workflows.
• To examine the risks of over-reliance on GenAI, including diminished critical thinking and clinical judgment among students and practitioners.
• To assess the role of AI literacy and institutional guidelines in ensuring responsible and effective use of GenAI in dentistry.
• To provide a framework for the ethical and secure deployment of GenAI models in dental research and patient care.

Proposed method

• Systematic review of existing literature and applications of GenAI in dentistry, focusing on text, image, and multimodal generation capabilities.
• Analysis of GenAI models such as Llama 3 and ChatGPT in the context of academic writing and language refinement, with human oversight.
• Evaluation of GenAI's role in dental education through prompt-based learning and real-time response generation for clinical questions.
• Examination of GenAI applications in diagnostic support, including image generation from textual descriptions and treatment planning assistance.
• Review of ethical frameworks and policy guidelines for data privacy, bias mitigation, and transparency in AI-generated outputs.
• Assessment of AI literacy initiatives and training models to promote responsible use and critical evaluation of GenAI outputs.

Experimental results

Research questions

• RQ1 How is generative AI currently being applied in dental education to support student learning and clinical reasoning?
• RQ2 What are the key clinical and administrative applications of GenAI in patient diagnosis, treatment planning, and communication?
• RQ3 What ethical and privacy challenges arise from using patient data to train GenAI models in dentistry?
• RQ4 How can over-reliance on GenAI compromise clinical decision-making and critical thinking in dental practice?
• RQ5 What institutional and educational strategies are needed to promote AI literacy and responsible use of GenAI in dentistry?

Key findings

• GenAI models such as Llama 3 and ChatGPT are being used to improve the language and readability of academic writing, with authors retaining full responsibility for content.
• GenAI enables rapid access to knowledge in dental education, allowing students to receive instant, natural language-based responses to complex clinical questions.
• In clinical settings, GenAI supports diagnosis and treatment planning by generating image and text outputs from textual inputs, improving efficiency and decision support.
• Ethical risks include data privacy breaches, algorithmic bias, and lack of transparency, particularly when training models on sensitive patient data.
• Over-reliance on GenAI may erode critical thinking and clinical judgment, especially if users fail to verify or contextualize AI-generated outputs.
• AI literacy programs and clear institutional guidelines are essential to ensure responsible use, mitigate bias, and maintain clinical and academic integrity.