Integrating AI and Into Dental Hygiene Documentation Education

Abstract

Comprehensive chart documentation is a key competency in dental hygiene education. Providers spend a significant portion of their day on record-keeping, over 12% in primary care settings [1]. Accurate charting supports decisions, billing, and legal protection, but excessive documentation reduces time for patient education. It also limits communication, leadership, and collaboration by restricting feedback and team interaction. At the same time, dental education must adapt to emerging artificial intelligence (AI) tools designed to improve efficiency and support learning. AI-assisted charting and automated note generation show promise in reducing documentation time [2, 3]. Despite the growing interest in AI, little is known about how such systems can be effectively integrated into dental hygiene training to enhance both perceived efficiency and patient communication [4]. Students continue to learn traditional, manual charting methods. AI-based documentation tools can help create record periodontal charts, clinical notes, analyze data, and improve record accuracy [5]. The lack of such training limits students’ and teachers’ awareness and readiness to use AI systems. To address these challenges, a dental hygiene program piloted DentalBee, an AI-powered tool that converts clinical speech into structured dental notes. The project aimed to determine whether AI-assisted documentation could improve workflow efficiency and patient engagement while integrating digital tools into dental hygiene education. The pilot involved 2nd-year students during clinical rotations and included faculty training, AI-assisted modules, and integration with the patient management system (PMS) (Table 1). Launched in Spring 2025, the initiative received administrative and IT support. Outcome measures focused on students’ perceived efficiency and patient interaction, assessed through a structured survey. Faculty also observed reduced documentation time, though exact times were not recorded because implementation occurred alongside student training, conditions that would have artificially inflated time data and misrepresented tool performance. This pilot established baseline perceptions of efficiency and engagement, providing a foundation for future studies to measure objective time savings once system use becomes routine. Institutional review board exemption was granted for this educational quality-improvement project. A quantitative survey assessed student perceptions of documentation efficiency and patient communication at three timepoints: pre-implementation (n = 23), mid-rotation (1 month; n = 23), and post-rotation (3 months; n = 20). At baseline, 74% of participants reported that documentation significantly impacted their perceived appointment efficiency (Figure 1). Following AI integration, 12.5% of students reported noticeable improvement at mid-rotation, increasing to 50% by post-rotation—suggesting a gradual adaptation and perceived benefit over time. In terms of patient communication, 50% of students initially indicated that note-taking limited their ability to connect with patients, while 27% reported a moderate burden and 23.5% a high burden (Figure 2). After using the AI system, 15.6% reported high improvement in patient connection at mid-rotation, increasing to 41.9% by post-rotation. Although self-reported, these findings suggest that with continued use, AI-assisted documentation may improve perceived workflow efficiency and facilitate more meaningful patient engagement. Future studies should include objective measurement of documentation time and direct assessment of patient outcomes to strengthen these preliminary results. The authors would like to acknowledge the support of Catherine Ford, Dean of Owens Community College School of Nursing and Health Professions. Acknowledgment to Kanza Javed for the logistic support.

Ähnliche Arbeiten