ArticleCureus2025
Comparative Evaluation of Accuracy, Completeness and Readability of Common Patient Queries Related to Prosthodontic Treatment by Two Artificial Intelligence Models (ChatGPT-4o and Gemini).
Article in Cureus, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 2 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
2 citing papers in PubMed.
- Generative artificial intelligence to augment ethical problem solving in ophthalmology: GPT-5.1 versus a human ethicist.International ophthalmology · 2026Article
- Preliminary Evaluation of Large Language Models in Kennedy Classification and Removable Partial Denture Planning: An In Silico Study.Medical science monitor : international medical journal of experimental and clinical research · 2026Article
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
introductionArtificial intelligence (AI) is fundamentally characterized by the capacity of computer systems to execute tasks that traditionally require human intelligence through the application of sophisticated algorithms. The coming years are bound to witness an increase in the number of people relying on the AI language models for initial health-related queries. The reasons may include increased credibility of AI models, convenience and privacy, initial knowledge acquisition before their visit to a doctor and guidance regarding treatment options.
aimThe aim of the study was to compare the performance of two commonly used AI models, Chat Generative Pretrained Transformer (ChatGPT-4o, OpenAI, San Francisco, United States) and Google Gemini Flash 2.5 (Google Bard, Google DeepMind, Mountain View, California, United States), in responding to common patient queries related to prosthodontic treatments and evaluate their responses in terms of accuracy, completeness, generation time, length and readability. MATERIALS AND
methodsIn this study, 30 open-ended questions that are frequently asked by patients visiting prosthodontists were collected. Ten questions each from the domains (removable (partial and complete), fixed partial dentures and dental implantology) were submitted to both AI models: ChatGPT 4o and Google Gemini Flash 2.5. Four experts in the field of Prosthodontics with a minimum of 20 years' experience, who were blinded to the study, evaluated the accuracy and completeness of the responses from the models. Accuracy, completeness, generation time, length and readability of the responses generated by the two AI models were compared using the Likert scale and Simple Measure of Gobbledygook (SMOG) Index.
resultsThe comparison of outputs from two AI systems evaluated illustrated that Model B (Gemini) achieved 0.25 higher completeness and accuracy scores compared to Model A (ChatGPT). In terms of readability, Gemini generated outputs with a median SMOG index 1.46 points higher than ChatGPT (p = 0.004), suggesting a more advanced reading level.
conclusionGemini demonstrated superior performance compared to ChatGPT, delivering more professional and technical content, while ChatGPT was more accessible and comprehensible for non-professionals and the general public.
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.