EUVIMEDEUVIMED entdecken
Crossref

Retrieval-augmented generative AI enhances clinical reasoning in odontogenic sinusitis versus maxillary sinus mucositis

Sholem Hack, John R Craig, Chih-Feng Lin, Chia-Hsiang Fu, Marta Aleksandra Kwiatkowska, Petr Kocum, Fabiana Allevi, Alberto Maria Saibene

European Archives of Oto-Rhino-Laryngology · 2026

DOI: 10.1007/s00405-026-10040-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Archives of Oto-Rhino-Laryngology, 2026. Verfasst von Sholem Hack und 7 weiteren Autor:innen. Beteiligte Einrichtung: City St. George's University of London, School of Medicine, Program delivered by University of Nicosia at the Chaim Sheba Medical Center, Ramat Gan, …. Hauptthemen laut MEDLINE: Maxillary Sinusitis, Mucositis, Clinical Reasoning, Maxillary Sinus. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 43 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: This exploratory pilot study evaluated whether combining structured clinical information, medical imaging, and literature-derived knowledge could enhance the diagnostic reasoning and output quality of a large language model in distinguishing odontogenic sinusitis from maxillary sinus mucositis. METHODS: Six complex clinical cases were constructed with nasal endoscopy, computed tomography findings, and clinical vignettes. ChatGPT-4.0 was prompted using four strategies: (1) clinical text only, (2) text with medical imaging, (3) text with structured literature excerpts, and (4) text with both imaging and literature input. Seven blinded expert reviewers rated 168 responses across diagnostic accuracy, clinical reasoning, safety, and overall usefulness using a five-point scale. Statistical comparisons and inter-rater reliability were assessed. RESULTS: All prompting strategies produced clinically safe outputs with minimal hallucinations or unsafe recommendations. Combining structured literature and imaging with clinical text significantly improved clinical reasoning scores (F(3,123) = 4.32, p = 0.0058), ranking first or second in six of seven evaluation domains. No significant differences were observed in diagnostic accuracy or safety across strategies. Inter-rater reliability was substantial (kappa = 0.7). CONCLUSION: Providing structured evidence and imaging appeared to enhance the clinical reasoning quality of large language models in this small, simulated dataset, without compromising diagnostic accuracy or safety. These preliminary findings suggest that structured multimodal prompting may help improve the interpretability and reliability of artificial intelligence tools for supporting diagnostic reasoning in sinus-related diseases, though larger prospective validation studies are needed before clinical implementation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Maxillary SinusitisMucositisClinical ReasoningMaxillary SinusRhinosinusitisHumansGenerative Artificial IntelligencePilot ProjectsLarge Language ModelsTomography, X-Ray ComputedFemaleMaleDiagnosis, DifferentialEndoscopyReproducibility of ResultsMiddle AgedAdult

Stichwörter der Autor:innen

Clinical reasoningComputed tomographyDiagnostic reasoningLarge language modelsMaxillary sinus mucositisMultimodal promptingNasal endoscopyOdontogenic sinusitisOtolaryngologyRetrieval-augmented generation

Autor:innen und Institutionen

  • City St. George's University of London, School of Medicine, Program delivered by University of Nicosia at the Chaim Sheba Medical Center, Ramat Gan, Israel. sholemhack1@gmail.com.
  • Department of Otolaryngology - Head and Neck Surgery, Henry Ford Health , Detroit, MI, USA.
  • Department of Otolaryngology - Head and Neck Surgery, National Taiwan University Hospital, Taipei, Taiwan.
  • College of Medicine, Graduate Institute of Clinical Medical Sciences, Chang Gung University, Taoyuan, Taiwan.
  • Department of Otolaryngology and Laryngological Oncology, Military Institute of Medicine-National Research Institute, Warsaw, Poland.
  • Department of ENT - Head and Neck Surgery, Na Homolce Hospital, Prague, Czech Republic.

Zitieren

APA

Hack, S., Craig, J. R., Lin, C. F., Fu, C. H., Kwiatkowska, M. A., Kocum, P., Allevi, F., & Saibene, A. M. (2026). Retrieval-augmented generative AI enhances clinical reasoning in odontogenic sinusitis versus maxillary sinus mucositis. European Archives of Oto-Rhino-Laryngology. https://doi.org/10.1007/s00405-026-10040-2

Vancouver

Hack S, Craig JR, Lin CF, Fu CH, Kwiatkowska MA, Kocum P, et al. Retrieval-augmented generative AI enhances clinical reasoning in odontogenic sinusitis versus maxillary sinus mucositis. European Archives of Oto-Rhino-Laryngology. 2026. doi:10.1007/s00405-026-10040-2

BibTeX
@article{Hack2026,
  author = {Hack, Sholem and Craig, John R and Lin, Chih-Feng and Fu, Chia-Hsiang and Kwiatkowska, Marta Aleksandra and Kocum, Petr and Allevi, Fabiana and Saibene, Alberto Maria},
  title = {Retrieval-augmented generative AI enhances clinical reasoning in odontogenic sinusitis versus maxillary sinus mucositis},
  journal = {European Archives of Oto-Rhino-Laryngology},
  year = {2026},
  doi = {10.1007/s00405-026-10040-2}
}
Kostenlos starten →