What question did this study set out to answer?

This research aims to evaluate the performance of various large language models in providing evidence-based responses to dental implantology questions.

July 26, 2026BMC Oral Health0 citationsOpen Access

Evaluating different large language model performances in evidence-based dental implantology: a blinded controlled experimental evaluation using expert panel assessment

VAVasilios AlevizakosDanube Private University RGRobert GaudinSwiss Epilepsy Center IGIman GhanadCharité - Universitätsmedizin Berlin

Key Points

This research aims to evaluate the performance of various large language models in providing evidence-based responses to dental implantology questions.
Controlled experimental design with four large language models (LLMs) assessed on 16 clinical questions.
Responses evaluated by three dental implantology specialists on specificity, accuracy, and clinical utility using a 0-10 scale.
Data analyzed using Kruskal-Wallis tests, with inter-rater reliability assessed through Fleiss’ kappa.
LLM4 achieved the highest median scores in specificity (9.0), accuracy (9.5), and clinical utility (10.0), significantly outperforming other models (all p < 0.001).
Cohen’s d indicated large to very large effect sizes favoring LLM4, especially against LLM2 and LLM3.
Inter-rater reliability was slight, indicating moderate evaluator disagreement (κ = 0.078–0.180).

Abstract

Artificial intelligence (AI) and large language models (LLMs) are increasingly being explored for clinical decision-making and evidence-based information retrieval in dental implantology. However, concerns remain regarding the accuracy, reliability, and clinical applicability of different AI approaches, including general-purpose, fine-tuned, and retrieval-augmented generation (RAG) models. This study aimed to compare their ability to provide accurate, evidence-based, and clinically relevant responses to implantology-related questions. Sixteen master’s-level clinical questions were presented to all four LLMs under controlled conditions. Their anonymized responses were independently evaluated by three dental implantology specialists based on three core criteria: specificity, accuracy, and clinical utility, using a 0–10 scale. Descriptive statistics were reported as medians and interquartile ranges. Differences among models were assessed primarily using Kruskal–Wallis tests, and inter-rater reliability was evaluated using Fleiss’ kappa. LLM4 consistently achieved the highest median scores across all criteria (Specificity: median 9.0, IQR 9.0–10.0; Accuracy: median 9.5, IQR 9.0–10.0; Clinical Utility: median 10.0, IQR 9.0–10.0), significantly outperforming the other models (all p < 0.001). Cohen’s d revealed large to very large effect sizes in comparisons involving LLM4, particularly against LLM2 and LLM3. LLM2 scored lowest and showed the highest variability. Inter-rater reliability was slight across all metrics (κ = 0.078–0.180), indicating moderate evaluator disagreement. Among the models tested, LLaMA 3.2 + RAG demonstrated superior and more consistent clinical performance in dental implantology. While fine-tuning provided moderate benefits, real-time access to structured guidelines significantly enhanced response quality. Despite low inter-rater agreement, these findings highlight the promise of RAG models in supporting high-complexity, evidence-based clinical domains, while emphasizing the need for standardization in AI evaluation protocols.

问 AI

Bookmark

View Full Paper