Enhanced control of periodontitis by an artificial intelligence-enabled multimodal-sensing toothbrush and targeted mHealth micromessages: A randomized trial

Abstract

Aim: Treatment of periodontitis, a chronic inflammatory disease driven by biofilm dysbiosis, remains challenging due to patients' poor performance and adherence to the necessary oral hygiene procedures. Novel, artificial intelligence-enabled multimodal-sensing toothbrushes (AI-MST) can guide patients' oral hygiene practices in real-time and transmit valuable data to clinicians, thus enabling effective remote monitoring and guidance. The aim of this trial was to assess the effect of such a system as an adjunct to clinical practice guideline-conform treatment.

Materials and methods: This was a single-centre, double-blind, standard-of-care controlled, randomized, parallel-group, superiority trial. Male and female adults with generalized Stage II/III periodontitis were recruited at the Shanghai Ninth People's Hospital, China. Subjects received a standard-of-care oral hygiene regimen or a technology-enabled, theory-based digital intervention consisting of an AI-MST and targeted doctor's guidance by remote micromessaging. Additionally, both groups received guideline-conform periodontal treatment. The primary outcome was the resolution of inflamed periodontal pockets (≥4 mm with bleeding on probing) at 6 months. The intention-to-treat (ITT) analysis included all subjects who received the allocated treatment and at least one follow-up.

Results: One hundred patients were randomized and treated (50 tests/controls) between 1 February and 30 November 2022. Forty-eight tests (19 females) and 47 controls (16 females) were analysed in the ITT population. At 6 months, the proportion of inflamed periodontal pockets decreased from 80.7% (95% confidence interval [CI] 76.5-84.8) to 52.3% (47.7-57.0) in the control group, and from 81.4% (77.1-85.6) to 44.4% (39.9-48.9) in the test group. The inter-group difference was 7.9% (1.6-14.6, p < .05). Test subjects achieved better levels of oral hygiene (p < .001). No significant adverse events were observed.

Conclusions: The tested digital health intervention significantly improved the outcome of periodontal therapy by enhancing the adherence and performance of self-performed oral hygiene. The model breaks the traditional model of oral health care and has the potential to improve efficiency and reduce costs (NCT05137392).

Keywords: artificial intelligence; digital health intervention; mHealth; periodontitis; power toothbrush; randomized controlled trial.

FIGURE 1

Architecture of the test intervention. The illustration shows the overall components and structure of the tested digital intervention. (a) Multimodal‐sensing power toothbrush. It provides multiple real‐time feedback to the user: the light display (1) shows the correct range of pressure in response to data obtained by a bi‐modal pressure sensor (2). Motion and gyroscope sensors (3) with proprietary AI processing determine the 3D position of the toothbrush in the mouth. Real‐time data transfer to the user's smartphone is achieved by Bluetooth connectivity (4). (b) The App running on the smartphone provides real‐time feedback and personal instructions to the users. It paces the time spent in each of 16 zones of the dentition to ensure adequate cleaning of all the dentition and graphically displays areas that have received inadequate brushing time so that the user can insist in those areas. It also provides the users with a timer showing progress towards the objective of 3 min per session. The patient is encouraged to stay on the specific area and avoid constantly changing location to enable a systematic approach. At the end of the brushing session, the App provides feedback based on percentage of coverage of the dentition, using the correct pressure range, and avoiding constantly changing the brushing area (c). It also asks about completion of the prescribed inter‐dental cleaning. The brushing data are anonymously transferred to a cloud server (d). From there data are downloaded to a desktop located in the hospital (e) and are analysed in batch using an SAS macro procedure that provides elaborated brushing data in terms of time, duration, coverage of the 16 zones, duration of brushing in each one of the 16 zones, times of brushing with the desired pressure and the use of inter‐dental cleaning devices. The study therapist reviewed daily the data for each individual subject and used them for remote monitoring and to select appropriate mHealth messages from a purpose‐built library (f). The targeted micromessages were sent to the participant via SMS messaging (g).

FIGURE 2

Example of the actionable data for remote monitoring. The figure illustrates the key parameters of brushing adherence and effectiveness of a representative subject. Each toothbrushing episode over the 6‐month study period is represented by a circle. The brushing duration in seconds is shown in (a). After an initial period requiring longer duration, this participant brushed slightly over 3 min per session, thus complying with the recommendation. Panel (b) illustrates the time of brushing in the 24‐h clock illustrating compliance with the prescribed three times/day regimen and occurrence after breakfast, lunch and dinner. (c) shows that after a brief learning curve at the beginning, the subject was able to obtain high brushing coverage scores, indicating that his brushing achieved the isochronicity (equal time of brushing in the various zones of the dentition) objective.

FIGURE 3

CONSORT diagram.