Dental Provider Experiences with AI Radiograph Annotation: A Qualitative Case Study

INTRODUCTION: The use of artificial intelligence (AI) tools to aid in dental diagnosis, treatment planning, and education is rapidly growing in oral health care. One type of artificial intelligence (AI) tool is radiographic annotation software that identifies and highlights anomalies on dental radiographs that may be indicative of oral disease. OBJECTIVES: The aim of this study was to explore challenges and facilitators that contributed to oral health professionals accepting and using an AI radiograph annotation software in a large US oral health care organization. METHODS: A qualitative collective case study design was used to gain insight into dental providers' experiences using AI radiograph annotation software. Semi-structured interviews were conducted from November 8, 2024, to December 15, 2024, through an online platform. Study participants were from 5 Apple Tree Dental clinics located in Little Falls, Madelia, Mounds View, Rochester, and Fairmont, Minnesota. Abductive coding was conducted to create themes related to the interviewees' experiences with the AI software. RESULTS: = 3). The themes identified were providers' first impressions, current beliefs, utilization, diagnostic confidence, treatment plan alignment, person-centered care, unexpected benefits, and challenges related to the AI annotation software. Providers gained understanding over time that the AI software is a tool to assist with decision-making and is not capable of replacing critical thinking skills needed for patient-centered care. CONCLUSION: These study findings provide insights for oral health care delivery organizations on how best to support oral health professionals faced with implementing AI software protocols.Knowledge Transfer Statement:This study explored how dental AI radiograph annotation software could enhance diagnostic confidence, support treatment planning, and improve patient education. While adoption by the participants in this study varied, they found the tool valuable for engaging patients and identifying early signs of disease. This supports the need for structured onboarding, ongoing training, and peer support to optimize AI integration. Embracing such technologies could promote earlier intervention, more personalized care, and improved oral health outcomes across diverse populations.