EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

JADE: jawbone lesion diagnosis and decision supporting system

Soroush Baseri Saadi iD, Jonas Ver Berne iD, Rocharles Cavalcante Fontenele iD, Peter Claes iD, Reinhilde Jacobs iD

Dentomaxillofacial Radiology · 01.07.2026 · 55 (5) · 497-507

DOI: 10.1093/dmfr/twag017 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 23.03.2026. Verfasst von Soroush Baseri Saadi und 4 weiteren Autor:innen. Beteiligte Einrichtung: OMFS-IMPATH Research Group, Department of Imaging and Pathology, Catholic University Leuven, Leuven 3000, Belgium. Hauptthemen laut MEDLINE: Jaw Diseases, Decision Support Systems, Clinical. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To develop and evaluate JADE, a proof-of-concept retrieval-augmented generation (RAG) diagnostic assistive system, designed to enhance large language model (LLM) reasoning for jawbone lesion assessment. This study examined whether RAG improves diagnostic accuracy and stability compared with standalone LLMs and ORAD, a supervised learning-based system.

Methods

JADE was developed as a cloud-based RAG system integrating an expert-curated oral radiology database embedded using text-embedding-3-large and indexed in Qdrant Cloud. Structured clinical inputs were encoded as prioritized vector queries. Hybrid semantic and keyword-based retrieval appended relevant evidence to prompts for differential diagnosis generation across LLM backbones. Performance was evaluated in 25 validation cases and compared with GPT-5, Claude Sonnet 4.5, DeepSeek-R1, Gemini 2.5 Flash, their RAG configurations, and ORAD. Diagnostic accuracy was analyzed using Cochran’s Q test, with post-hoc McNemar’s tests and Bonferroni correction. Intra-model stability and response time were assessed.

Results

RAG-GPT-5 achieved the highest diagnostic accuracy (20/25), followed by RAG-Claude Sonnet 4.5 (18/25), RAG-DeepSeek R1 (17/25), and RAG-Gemini 2.5 Flash (15/25). Standalone models achieved 9–13/25 correct diagnoses, ORAD achieved 17/25. No significant differences were observed among standalone models or RAG-based models and ORAD. A significant improvement was observed for GPT-5 when integrated with RAG (P = .002). RAG configurations showed higher intra-model stability, with RAG-GPT-5 achieving mean stability of 0.90 ± 0.11. Mean response times ranged from 3 to 10 s.

Conclusions

JADE improved diagnostic accuracy and stability compared with standalone LLMs, underscoring value of RAG reasoning in jawbone lesion assessment and marking the first RAG application in dentomaxillofacial radiology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Jaw DiseasesDecision Support Systems, ClinicalHumansLarge Language ModelsDiagnosis, DifferentialGenerative Artificial Intelligence

Stichwörter der Autor:innen

cloud-based applicationsdifferential diagnosishybrid retrievaljawbone lesionslarge language modelsretrieval-augmented generation

Autor:innen und Institutionen

  • OMFS-IMPATH Research Group, Department of Imaging and Pathology, Catholic University Leuven, Leuven 3000, Belgium.
  • Department of Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven 3000, Belgium.
  • Department of Pathology, University Hospitals Leuven, Leuven 3000, Belgium.
  • Division of Oral Radiology, Department of Stomatology, Public Health, and Forensic Dentistry, School of Dentistry of Ribeirao Preto, University of Sao Paulo (USP), Ribeirao Preto, Sao Paulo 14040-904, Brazil.
  • Department of Human Genetics, KU Leuven, Leuven 3000, Belgium.
  • Medical Imaging Research Center, UZ Leuven, Leuven 3000,Belgium.

ORCID-Profile: Soroush Baseri Saadi, Jonas Ver Berne, Rocharles Cavalcante Fontenele, Peter Claes, Reinhilde Jacobs

Zitieren

APA

Baseri Saadi, S., Ver Berne, J., Cavalcante Fontenele, R., Claes, P., & Jacobs, R. (2026). JADE: jawbone lesion diagnosis and decision supporting system. Dentomaxillofacial Radiology, 55(5), 497-507. https://doi.org/10.1093/dmfr/twag017

Vancouver

Baseri Saadi S, Ver Berne J, Cavalcante Fontenele R, Claes P, Jacobs R. JADE: jawbone lesion diagnosis and decision supporting system. Dentomaxillofacial Radiology. 2026;55(5):497-507. doi:10.1093/dmfr/twag017

BibTeX
@article{BaseriSaadi2026,
  author = {Baseri Saadi, Soroush and Ver Berne, Jonas and Cavalcante Fontenele, Rocharles and Claes, Peter and Jacobs, Reinhilde},
  title = {JADE: jawbone lesion diagnosis and decision supporting system},
  journal = {Dentomaxillofacial Radiology},
  year = {2026},
  volume = {55},
  number = {5},
  pages = {497--507},
  doi = {10.1093/dmfr/twag017}
}
Kostenlos starten →