Symbiotic intelligence in dental trauma diagnostics—an exploratory case study

TL;DR

This study explores using AI, specifically OpenAI's o3, to help diagnose dental trauma in children, especially in remote areas, by combining AI with human expertise.

Contribution

The study introduces the use of o3's multimodal AI for dental trauma diagnostics with expert validation in a remote educational setting.

Findings

o3 correctly identified pulp necrosis and fractures in specific teeth consistent with IADT guidance.

Human expert validation was crucial for treatment decisions and ethical considerations.

Symbiotic intelligence improved learning outcomes in remote dental trauma simulations.

Abstract

Dental trauma in children is common and requires prompt diagnosis, which can be challenging in remote or isolated settings with limited access to emergency dental care. This exploratory case study investigates whether OpenAI's o3 can support dental trauma diagnostics in primary incisors, building on prior pretesting of GPT-4 on summative dental education exams (2023) and multimodal dental trauma analyses (2024), and focusing on o3's multimodal capability and reliability in 2025 with expert assessment (“human in the loop”) prior to a supervisor seminar with students and supervisors (N = 84). Preliminary findings indicate that GPT-4 performed well on sample exams (2023), and that 7/10 multimodal analyses of dental injuries were accurate (2024); in the 2025 case, o3 correctly identified pulp necrosis in tooth 51 and uncomplicated enamel/dentin fractures in teeth 51 and 61, consistent with IADT guidance. Human expert involvement contributed essential validation, particularly for treatment decisions and ethical considerations. Overall, the study illustrates how symbiotic intelligence—purposeful collaboration between human and AI—may enhance learning outcomes in scenario-based simulations in remote areas, while requiring active human involvement and multiple validation communities.

Figures