ArticleBMC oral health2025
Comparative analysis of AI chatbot (ChatGPT-4.0 and Microsoft Copilot) and expert responses to common orthodontic questions: patient and orthodontist evaluations.
Article in BMC oral health, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 12 papers.
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
12 citing papers in PubMed.
- Artificial intelligence in orthodontics: clinical maturity, evidence gaps, and emerging applications-a narrative review.The Saudi dental journal · 2026Review
- Assessing the Diagnostic Performance of ChatGPT-5.0 versus Machine Learning in Orthodontics: A Comparative Analysis for Extraction Treatment Planning.Turkish journal of orthodontics · 2026Article
- Patient Facing AI Chatbots in Digital Orthodontic Education: A Comparative Evaluation of Understandability, Actionability, Quality, and Safety of Dietary Advice.Healthcare (Basel, Switzerland) · 2026Article
- Article
- Prompt sensitivity of large language models in orthodontic patient counseling: a scenario-based experimental study.BMC oral health · 2026Article
- Performance of AI chatbots in answering questions on tooth bleaching: a multilingual comparative study.BMC oral health · 2026Article
- Generative Artificial Intelligence-driven orthodontic education practices.BMC medical education · 2026Review
- Exploring LLM-based chatbot effectiveness in answering questions related to the risks and benefits of orthognathic treatment: a cross-sectional study.European journal of orthodontics · 2026Article
- Assessing AI-Based Large Language Models (ChatGPT, Google Gemini, and DeepSeek) for Common Parent Questions about Autism: Acceptability, Readability, and Accuracy.The Psychiatric quarterly · 2025Article
- Performance of ChatGPT-4 as an Auxiliary Tool: Evaluation of Accuracy and Repeatability on Orthodontic Radiology Questions.Bioengineering (Basel, Switzerland) · 2025Article
- Reliability of Large Language Model-Based Chatbots Versus Clinicians as Sources of Information on Orthodontics: A Comparative Analysis.Dentistry journal · 2025Article
- Conversational artificial intelligence compared with orthodontic reference standards for orthodontic information: A systematic review of accuracy, readability, safety, and certainty of evidence.Journal of oral biology and craniofacial researchReview
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
objectiveThe aim of this study was to evaluate the adequacy of responses provided by experts and artificial intelligence-based chatbots (ChatGPT-4.0 and Microsoft Copilot) to frequently asked orthodontic questions, utilizing scores assigned by patients and orthodontists.
methodsFifteen questions were randomly selected from the FAQ section of the American Association of Orthodontists (AAO) website, addressing common concerns related to orthodontic treatments, patient care, and post-treatment guidelines. Expert responses, along with those from ChatGPT-4.0 and Microsoft Copilot, were presented in a survey format via Google Forms. Fifty-two orthodontists and 102 patients rated the three responses for each question on a scale from 1 (least adequate) to 10 (most adequate). The findings were analyzed comparatively within and between groups.
resultsExpert responses consistently received the highest scores from both patients and orthodontists, particularly in critical areas such as Questions 1, 2, 4, 9, and 11, where they significantly outperformed chatbots (P < 0.05). Patients generally rated expert responses higher than those of chatbots, underscoring the reliability of clinical expertise. However, ChatGPT-4.0 showed competitive performance in some questions, achieving its highest score in Question 14 (8.16 ± 1.24), but scored significantly lower than experts in several key areas (P < 0.05). Microsoft Copilot generally received the lowest scores, although it demonstrated statistically comparable performance to other groups in certain questions, such as Questions 3 and 12 (P > 0.05).
conclusionsOverall, the scores for ChatGPT-4.0 and Microsoft Copilot were deemed acceptable (6.0 and above). However, both patients and orthodontists generally rated the expert responses as more adequate. This suggests that current current chatbots does not yet match the theoretical adequacy of expert opinions.
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.