ArticleBMC oral health2026
AI-based decision support in pediatric dentistry: a comparative study of ChatGPT-5 and gemini advanced.
Article in BMC oral health, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
1 citing paper in PubMed.
- Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
backgroundThe alignment of clinical decisions in pediatric dentistry with evidence-based guidelines is crucial for treatment success. The potential of artificial intelligence applications to provide decision support in accordance with the guidelines of the American Academy of Pediatric Dentistry (AAPD) is gaining increasing attention. This study aims to comprehensively compare the ability of OpenAI ChatGPT-5 and Google Gemini Advanced 2.0 Flash models to provide responses consistent with the 2020–2024 AAPD pulp treatment guidelines. MATERIALS AND
methodsAAPD’s Pulp Treatment in Primary and Immature Permanent Teeth (2020), Vital Pulp Therapy in Primary Teeth (2024), and Non-vital Pulp Therapy in Primary Teeth (2020) guidelines, a total of 27 questions were prepared, 9 of which are yes/no (dichotomous) and 18 are open-ended. The questions were posed by two different researchers over a period of 10 days, three times a day (morning, afternoon, evening), using both models (ChatGPT-5 and Gemini Advanced 2.0 Flash) in new chat sessions. A total of 1,620 responses were classified according to predefined, guideline-based criteria as ‘correct,’ ‘incorrect,’ or ‘consult an expert,’ with reference to the corresponding recommendations in the AAPD guidelines. The data were analysed using the Pearson Chi-Square test.
resultsThe ChatGPT-5 model provided accurate information consistent with guidelines in 72.8% of its responses, whereas this rate was 67.2% for Gemini Advanced. The difference in response distributions between the two models is statistically significant (Chi-Square test, p = 0.000). These results indicate that ChatGPT-5 provides more consistent and guideline-compliant responses to pediatric pulp therapy decision support questions compared to Gemini Advanced (2.0 Flash).
conclusionArtificial Intelligence-based chatbots have potential as clinical decision support tools in pediatric dentistry. ChatGPT-5 demonstrated higher accuracy than Gemini Advanced by providing responses that were largely consistent with the pulp treatment protocols outlined in the AAPD guidelines. However, both models can provide incorrect or insufficient guidance in some critical situations. Therefore, these tools should be viewed as auxiliary clinical decision support tools and should not replace the dentist’s expert knowledge and clinical judgment in final decisions. Developing artificial intelligence models that more comprehensively incorporate evidence-based guidelines in the field of pediatric dentistry will enhance their reliability in clinical practice.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.