Aim: To evaluate the effects of an at-home artificial intelligence (AI)-assisted dental monitoring application on treatment outcomes in patients with periodontitis.
Materials and methods: Participants with periodontitis were recruited and randomly assigned to an AI (n = 16), AI and human counselling (AIHC; n = 17), or control (CG; n = 20) group. All participants received non-surgical periodontal treatment. We employed an AI-assisted tool called DENTAL MONITORING® (DM) intervention, a new technological AI monitoring product that utilizes smartphone cameras for intra-oral scanning and assessment. Patients in the AI and AIHC groups received additional (a) DM or (b) DM, respectively, with real-person counselling over 3 months. Periodontal parameters were collected at baseline and follow-ups. A mixed-design model analysed the follow-up effects over time.
Results: The AI and AIHC groups, respectively, exhibited greater improvement in probing pocket depth (PPD) (mean diff = -0.9 ± 0.4 and -1.4 ± 0.3, effect size [ES] = 0.76 and 1.98), clinical attachment level (mean diff = -0.8 ± 0.3 and -1.4 ± 0.3, ES = 0.84 and 1.77), and plaque index (mean diff = -0.5 ± 0.2 and - 0.7 ± 0.2, ES = 0.93 and 1.81) at 3-month follow-up than the CG did. The AIHC group had a greater reduction in PPD (ES = 0.46) and clinical attachment level (ES = 0.64) at the 3-month follow-up compared with the AI group.
Conclusions: Using AI monitoring at home had a positive effect on treatment outcomes for patients with periodontitis. Patients who received AI-assisted health counselling exhibited better treatment outcomes than did patients who received AI monitoring alone.
Trial registration: ClinicalTrials.gov NCT04567030.
Keywords: artificial intelligence; counselling; periodontitis.
© 2022 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.