Artificial intelligence and its impact on oral health care education. A randomized study

Abstract

BACKGROUND:

Artificial intelligence (AI)-generated educational materials demonstrate superior effectiveness in improving patient comprehension and reducing anxiety compared to traditional methods. Their integration into dental practice could enhance patient satisfaction and streamline the educational process, particularly for complex or anxiety-inducing procedures. The present study aimed to evaluate the act of AI applications on oral healthcare, focusing on clinical outcomes.

MATERIALS AND METHODS:

A cluster-randomized controlled trial with 1000 participants from 20 villages (10 interventions, 10 controls) was conducted. The intervention group received 4 weeks of chatbot-guided oral health education via WhatsApp/IVR, while controls received standard health talks and leaflets. Knowledge, oral hygiene practices, and OHI-S scores were measured pre- and post-intervention.

RESULTS:

The intervention group showed a marked rise in mean knowledge scores (9.8 to 15.2) compared to controls (10.1 to 11.3; P < 0.001). Twice-daily brushing improved from 28% to 64% (vs. 30% to 37% in controls). OHI-S scores improved significantly more in the chatbot group (reduction = 1.2) than in controls (0.3; P < 0.001). Engagement with the chatbot correlated positively with outcome improvements.

CONCLUSION:

AI-based chatbots significantly enhance oral health awareness, hygiene practices, and clinical outcomes in rural settings, highlighting their potential for scalable public health interventions and integration into primary health programs.

Introduction

Oral health is an essential component of overall well-being, yet it remains to be a neglected aspect of general health, particularly in rural populations.[1] Limited accessibility to dental professionals, financial constraints, and poor awareness contribute to a higher burden of oral diseases such as dental caries and periodontal conditions.[2,3] Preventive oral health education using conventional strategies such as pamphlets, community talks, and postershasbeen shown to significantly reduce disease incidence but often fails to achieve sustained behavioral changes.[4]

With the advancement of digital health technologies, Artificial Intelligence (AI) has emerged as a novel tool for delivering personalized health interventions.[5] AI-driven chatbotssimulate human conversation to provide accessible, interactive, and user-friendly health information.[6]Chatbots offer real-time engagement, reminders, and tailored responses, making them highly effective in promoting behavioral modifications in targeted individuals.[7]

Scientific evidence has suggested that digital interventions can improve oral hygiene practices, especially among the rural population, whogenerally have less awareness about dental and oral health.[8,9,10] However, there is limited empirical research evaluating the effectiveness of chatbot-based oral health education in improving awareness and clinical outcomes.[11]

Thus, this study was designed to assess the impact of an AI-based chatbot intervention on oral health knowledge, practices, and oral hygiene status among rural adults using a cluster-randomized controlled trial design. The theoretical framework is shown in Figure 1.

Figure 1.

Theoretical framework

Materials and Methods

Study design and settings

This cluster-randomized controlled trial was conducted from January 2025 to June 2025 in rural villages of Odisha state, India, after obtaining approval from the Institutional Ethics Committee (IEC/MM2409) and permission from Village Panchayats. The study purpose was explained to all participants of this study in the local language and informed consent was taken.

Study participants and sampling

A total of1500 participants from 20 villages (10 intervention and 10 control) were included in the study using randomization sampling technique. After initial screening, 500 subjects were excluded based on theinclusion and exclusion criteria for subject selection. Subjects were divided into two groups:(a) Group I (intervention group) and (b) Group II (Control group). Each of the studied groups was constituted by 500 study participants.

Inclusion criteria

These were: (a) Age ≥18 years, (b) resident of the studied village for more than 6 months, (c) access to a smartphone, and (d) provided consent. Exclusion criteria were: (a) Severe cognitive or psychiatric condition and (b) edentulous subjects.

Data collection tool and technique

Intervention used: The intervention arm received 4 weeks of AI chatbot-delivered oral health education via WhatsApp text/audio through their smartphones. Oral health module included—toothbrushing techniques, benefits of fluoride use, prevention of gum diseases, dietary advice, and risks associated with tobacco/alcohol use. The features included reminders, quizzes, and clinic locator information. The control arm received a one-time health talk and a printed leaflet.

Procedure

The baseline oral health knowledge was assessed for both groups using a pre-validated questionnaire[Table 1]. The intervention group interacted with the chatbot for 4 weeks, and the participants were encouraged to use it at least three times per week. On the other hand, the control group received printed materials at the beginning of the study. Assessment of knowledge was done by comparing the results at the baseline and after a 4-week period by analyzing OHI-S scores from the questionnaire.

Table 1.

Survey questionnaire

Section		No. of items		Example question		Response type
Demographics		6		Age, gender, education, occupation		Categorical/numeric
Phone anddigital access		4		Type of phone owned		Multiple choice
Oral health knowledge		20		“Fluoride toothpaste prevents tooth decay.”		True/false
Oral hygiene practices		8		Frequency of toothbrushing		Multiple choice
Tobacco/alcohol use		2		Tobacco use in the last 30 days		yes/no
self-efficacy		5		Confidence to brush twice-daily		5-point Likert
OHIP-14 short form		14		“Have you had painful aching in your mouth?”		5-point Likert
Usability (intervention only)		10		“I found the chatbot easy to use.”		5-point Likert

OHIP- 14=Oral Health Impact Profile-14

Results

1. Demographic characteristics: On comparing the mean ± standard deviation (SD) age (in years) in intervention (Group A) and control groups (Group B), it was found to be 39.2 ± 12.1 and 38.5 ± 11.7 years, respectively, which was found to have no statistically significant difference (P = 0.42). On analyzing the gender distribution, ^there were 52.4% females in Group A and 51.0% in Group B, which had no statisticallysignificant difference (P = 0.65). On comparing education level, subjects of both groups were observed to have attained secondary level or higher education level, ^that is, 38.0% in Group Aand 39.2% in Group B, which had no statistical significance (P = 0.74). A 68.2% study participants in theintervention arm (Group A) and 66.4% participants in thecontrol arm owned a smartphone. This was found to have no statistical significance (P = 0.54) [Table 2 and Graph 1].

2. Assessment of oral health indicators: On observing baseline knowledge scores, Group A was found to have 9.8 ± 3.1, and Group B wasobserved as having 10.1 ± 3.0, which had no statistically significant difference (P = 0.21). On comparing brushing habits, twice a day toothbrushing habit was observed in 28.0% study participants of Group A and 30.0% subjects belonging to Group B. This was found to have no statistically significant difference (P = 0.51). On comparing post-intervention outcomes after 4 weeks, Group A (intervention using an AI-based chatbot) demonstrated significantly better improvement when compared withthe control group. Mean ± SD knowledge score was found to increase by +5.4 ± 2.0 in the intervention group; however, in Group B, an increase of +1.2 ± 1.8was obtained, which was less in comparison with Group A. This was found to have an extremely significant statistical difference (P < 0.001). Positive changes in behavioral modifications were observed, with 36% more participants adopting twice-daily brushing in the intervention group compared to 7% in controls (P < 0.001). Similarly, use of fluoridated toothpaste was found toincrease substantially by 42% in the intervention group compared to an 8%increase in the control group. It was found to have extreme significance (P < 0.001). Oral hygiene outcomes demonstrated statistically significant (P < 0.001) clinical improvement with a reduction of − 1.2 ± 0.5 in mean ± SD OHI-S scores of Group Ain comparison with − 0.3 ± 0.4 reduction in the control group (Group B)[Table 3 and Graph 2].

Table 2.

Demographic characteristics of study participants

Studied variables		Group A (intervention; n=500)		Group B (control; n=500)		P
Mean±SD age (years)		39.2±12.1		38.5±11.7		0.42
Female gender (%)		52.4		51.0		0.65
Education ≥ secondary (%)		38.0		39.2		0.74
Use of smartphone (%)		68.2		66.4		0.54
Baseline knowledge score (0 to 20)		9.8±3.1		10.1±3.0		0.21
Twice-daily brushing (%)		28.0		30.0		0.51
Mean OHI-S score		3.1±0.9		3.0±0.9		0.33

OHI-S=The Oral Hygiene Index Simplified, SD=Standard deviation

Graph 1.

Graph demonstrating P values of studied demographic features

Table 3.

Table showing changes in outcomes after 4 weeks

Outcome		Group A		Group B		P
Knowledge score		+5.4±2.0		+1.2±1.8		<0.001
Twice-daily brushing (%)		+36.0		+7.0		<0.001
Fluoride toothpaste use (%)		+42.0		+8.0		<0.001
OHI-S scores		−1.2±0.5		−0.3±0.4		<0.001
Professional dental visits (%)		+18.0		+4.0		<0.001

Graph 2.

Outcomes after 4 weeks in intervention and control groups

Also, professional dental visits were found to increaseby 18% among the intervention group when compared to a 4% increase in the control group. This was demonstrated to have statistical significance (P < 0.001). Therefore, improvements inthe level of knowledge and positive oral health practices were noted in the studied rural populations using AI-based chatbots.

Discussion

AI is gradually getting integratedwith healthcare at an accelerated rateduring the last decade, with continued advancements in processing of data, machine learningalgorithms, and imaging techniques.[12] Dentistry is emerging as an area forthe incorporation of AI in diagnostic imaging, identification of visual patterns, and structured planning of treatment.[13]AI provides assistancefor streamliningroutine administrative tasks, scheduling appointments, and improving theallocation of resources. AI can help in designing personalized healthcare by integrating multi-modal patient data that ranges from clinical records to information pertaining to lifestyle for prevention as well as treatment strategies.[14]

The baseline comparability of the intervention and control groups strengthens the internal validity of this cluster-randomized trial, as no significant demographic or oral health differences were observed between the study groups. This balance ensures that subsequent changes in knowledge, practices, or oral hygiene indices can be confidently attributed to the chatbot-based intervention rather than baseline disparities. The role of AI in dentistry has been expanding, with advances in deep learning contributing to diagnostic, preventive, and behavioral health strategies.[10] Previously, AI chatbot responses have been compared with those of healthcare professionals, whichhave demonstrated comparable accuracy and acceptability.[11] However, evidence specific to oral health, particularly in rural and underserved communities, remains scarce. Recent explorations into AI applications in oral and maxillofacial surgery and dental education highlight their potential for knowledge transfer and patient engagement.[15,16] Furthermore, systematic reviews confirm that AI chatbots are effective in promoting health-related behavioral changes, particularly through personalized, interactive communication.[17] However, oral health literacy gaps persist in low-resource settings, where mobile health (mHealth) and eHealth interventions could serve as vital tools to bridge inequities.[15] Within this context, the current study addresses a critical literature gap by testing AI-driven chatbot interventions specifically tailored for oral health awareness in rural populations, thereby contributing novel evidence to a growing field of AI-supported community health promotion.

The present study findings demonstrate that chatbot-driven interventions can substantially enhance both knowledge and behavior in underserved rural populations. The observed rise in knowledge scores aligns with previous evidence where AI chatbots improved oral health literacy and awareness in similar populations.[1] Likewise, increased adoption of twice-daily brushing and fluoride toothpaste use reflects the effectiveness of digital health interventions in reinforcing preventive practices.[2,3]

These behavioral gains parallel broader applications of conversational AI in promoting health-related behavior changes, including vaccination and chronic disease prevention.[7,9] The meaningful clinical improvement in OHI-S underscores the potential for AI-enabled strategies to bridge oral health inequities by providing consistent, scalable education.[5,6,10] Furthermore, the rise in preventive dental visits in the intervention group reflects greater health-seeking behavior, consistent with earlier studies showing AI chatbot acceptability and willingness to engage with digital health solutions.[4,11]

Importantly, these results highlight not only the effectiveness but also the scalability of chatbot interventions for low-resource rural settings. This reinforces the potential integration of AI tools into primary oral health programs, complementing traditional education approaches and overcoming barriers of literacy, cost and access.[16,17] Naik et al. (2025) surmised that professional dentists must assist in providing informative videos on social media platforms such as YouTube.[18] Collectively, the evidence supports AI chatbots as a transformative tool in dentistry and public health, offering sustainable pathways to improve awareness, practices, and clinical outcomes in oral health care.

Limitation

The study was limited to short-term outcomes, without assessment of long-term behavioral adherence. Larger multi-center trials with extended follow-up are needed to evaluate the sustainability and broader applicability of chatbot-based interventions.

Conclusion

AI-based chatbots proved highly effective in improving oral health awareness, practices, and clinical outcomes among underserved rural populations. Their scalability and accessibility make them a valuable adjunct to traditional health education methods. Integrating such digital interventions into community programs can significantly bridge oral health disparities, as evident from the current study findings, which underlined increased responsiveness after training using a chatbot application. Future studies must focus on the application of AIto increase awareness regarding oral health practices by targeting a larger population size.

AI policy statement

No artificial intelligence (AI) tools were used in the writing, data collection, analysis, or preparation of this manuscript.

Ethical approval

The study was conducted after obtaining approval from the Institutional Ethics Committee (IEC/MM2409).

Author’s contributions

KD, AS and RN conceptualized and designed the study. MM, MSMM and SJA performed validation, analysis, and investigation. MNM managed resources, data curation, and visualization. MM drafted the manuscript, and DA reviewed and edited it.

Data availability statement

The data information can be obtained from the corresponding author on request.

Conflicts of interest

There are no conflicts of interest.

Funding Statement

Nil.