EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Retrieval-Augmented Language Models for Clinical Decision Support in the Classification of Inborn Errors of Immunity

Afrooz Arzehgar, Saeed Varasteh Yazdi, Hamid Ahanchian, Saeid Eslami

Journal of Clinical Immunology · 05.06.2026 · 46 (1)

DOI: 10.1007/s10875-026-02035-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Clinical Immunology, online erschienen am 05.06.2026. Verfasst von Afrooz Arzehgar und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Informatics, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran. Hauptthemen laut MEDLINE: Decision Support Systems, Clinical. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Mashhad University of Medical Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early diagnosis of inborn errors of immunity (IEIs) can make a difference in patient outcomes and even cut healthcare costs. However, there are some challenges to overcome, such as clinical complexity, low awareness, and limited resources. Generative artificial intelligence has attracted considerable global attention in medical domains, particularly when integrated into clinical decision support systems (CDSS), as it has the potential to facilitate data interpretation, clinical reasoning, and the optimal use of knowledge resources. Preliminary studies have explored the potential of large language models (LLMs) in various information retrieval tasks, but a systematic evaluation of LLMs with and without retrieval mechanisms for IEI classification is still unexplored. We evaluated and compared the validity and reliability of the responses generated by four open-source and closed-source LLMs, in their baseline form and with augmented data, across 169 IEI patient records, using two input scenarios and four prompt templates. Our primary finding was that the models varied in terms of reliability and performance. The most reliable models were Gemini-1.5-Pro and Llama-3.1-8B-Instruct ( $$\kappa =0.98$$ ) and the best-performing model without data augmentation was Gemini with an F1 score of $$43.39\, \% \pm 0.10$$ . The results also showed that retrieval strategies improved the average classification performance, increasing the F1 score from $$34\, \%$$ to $$53\, \%$$ across all models. DeepSeek-R1, which reasoned over retrieved information through the integration of quality refinement and structured retrieval, achieved the best weighted F1 score of $$66.94\, \% \pm 1.19$$ . The study highlights the effective use of generative AI and retrieval-augmented models as a decision support tool for IEI classification. However, incorporating retrieval systems into clinical decision-making processes requires adequate input, effective prompt engineering, and the adoption of retrieval strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Decision Support Systems, ClinicalHumansLarge Language ModelsGenerative Artificial IntelligenceReproducibility of Results

Stichwörter der Autor:innen

Clinical decision supportInborn errors of immunityLarge language modelsPrimary immunodeficiencyRetrieval-augmented generation

Autor:innen und Institutionen

  • Department of Medical Informatics, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran.
  • Department of Operations, Data and Artificial Intelligence, emlyon business school, Lyon, France.
  • Allergy Research Center, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran. ahanchianh@mums.ac.ir.
  • Department of Medical Informatics, UMC-Location AMC, University of Amsterdam, Amsterdam, Netherlands.

Förderung

  • Mashhad University of Medical Sciences

Zitieren

APA

Arzehgar, A., Varasteh Yazdi, S., Ahanchian, H., & Eslami, S. (2026). Retrieval-Augmented Language Models for Clinical Decision Support in the Classification of Inborn Errors of Immunity. Journal of Clinical Immunology, 46(1). https://doi.org/10.1007/s10875-026-02035-9

Vancouver

Arzehgar A, Varasteh Yazdi S, Ahanchian H, Eslami S. Retrieval-Augmented Language Models for Clinical Decision Support in the Classification of Inborn Errors of Immunity. Journal of Clinical Immunology. 2026;46(1). doi:10.1007/s10875-026-02035-9

BibTeX
@article{Arzehgar2026,
  author = {Arzehgar, Afrooz and Varasteh Yazdi, Saeed and Ahanchian, Hamid and Eslami, Saeid},
  title = {Retrieval-Augmented Language Models for Clinical Decision Support in the Classification of Inborn Errors of Immunity},
  journal = {Journal of Clinical Immunology},
  year = {2026},
  volume = {46},
  number = {1},
  doi = {10.1007/s10875-026-02035-9}
}
Kostenlos starten →