CoChat
Sign Up
Cited by 5Artificial Intelligence in Healthcare and EducationEthics and Social Impacts of AIInformation Retrieval and Search Behavior

Artificial intelligence reliability in implant dentistry: A comparative analysis of clinical accuracy and hallucination patterns across multiple language models

Hooshiar, Mohammad Hosseini·2026·The Journal of Prosthetic Dentistry
DOI 10.1016/j.prosdent.2025.11.005
Open this paper in CoChat — free account

Abstract

Statement of problem Artificial intelligence (AI) language models have been increasingly used for clinical decision-making in implant dentistry and for scholarly writing. Yet, their reliability, fabrication rates, and comparative performance across different architectures and generations remain unestablished, potentially compromising evidence-based practice. Purpose The purpose of this cross-sectional comparative study was to evaluate the accuracy of different AI models in implant dentistry. How often they produced false information under evidence-based prompting was also examined. Material and methods The clinical accuracy and hallucination patterns of multiple AI language models, including both conventional large language models (represented by ChatGPT) and retrieval-augmented generation (RAG) systems (represented by ScholarQA and OpenEvidence), were examined with regard to their response to evidence-based clinical questions in implant dentistry and to whether evidence-based prompting strategies reduced fabrication rates across these different AI architectures. Five AI models (GPT-4o, Model 4.1, Model 4.5, ScholarQA, and OpenEvidence) were tested with 15 clinical questions in implant dentistry under both unprompted and evidence-based prompting conditions. Results ScholarQA and OpenEvidence both achieved high accuracy (80.0%) with 0% fabrication, while GPT-4o showed high rates of reference (82%) and statistical (85.7%) fabrication. More recently released models demonstrated increased fabrication rates compared with earlier versions. Notably, 89.1% of fabricated citations were dated 2023 to 2025. Evidence-based prompting increased GPT-4o's accuracy from 33.3% to 66.7% but did not reduce fabrication rates. Both RAG systems showed minimal response to prompting, with OpenEvidence improving marginally to 86.6% and ScholarQA decreasing to 73.3%. Conclusions Conventional generative models frequently produced hallucinations, including fabricated citations and data, whereas retrieval-augmented systems such as ScholarQA and OpenEvidence avoided fabricated references but still generated incorrect interpretations. ChatGPT-4.5, ScholarQA, and OpenEvidence demonstrated comparable accuracy, yet hallucination in these forms remains the principal barrier to reliable clinical and scholarly use. Prompting improved performance mainly in earlier generations of AI models, while more recently released versions and RAG systems showed only limited benefit or were unaffected.

Integrity signals

Registry

Crossref · 10.1016/j.prosdent.2025.11.005

Cites

22 of 22 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Cites

Flagged first, then by citations

Cited by

Still being checked.

Related

Authors
Hooshiar, M. H.
Affiliations
Tehran University of Medical Sciences (IR)
Corresponding author
Hooshiar, Mohammad Hosseini
ORCID
Hooshiar, Mohammad Hosseini
Venue
The Journal of Prosthetic Dentistry
Publisher
Elsevier BV
Published
2026-05
Volume
135
Issue
5
Pages
e155-e161
ISSN
0022-3913 (ISSN-L)
DOI
10.1016/j.prosdent.2025.11.005
OpenAlex
W4416425441
Cited by
5
References
22
Citations by year
2026: 5
FWCI
1.21
Type
journal article
Language
en
Open access
closed
Licence
Locations
  • Journal of Prosthetic Dentistry (publishedVersion)
  • PubMed (publishedVersion)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
  • Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
Keywords
implant dentistry, large language models, hallucinations, retrieval-augmented generation, ChatGPT, OpenEvidence, clinical accuracy, dental implants
MeSH terms
Clinical Decision-Making, Artificial Intelligence, Cross-Sectional Studies, Dental Implantation, Humans, Language, Reproducibility of Results, Evidence-Based Dentistry

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review