Development and Reliability Assessment of an Artificial Intelligence-Driven Urticaria Support (AIDUS) Chatbot
The Journal of Allergy and Clinical Immunology: In Practice · 2025
DOI: 10.1016/j.jaip.2025.07.047 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Allergy and Clinical Immunology: In Practice, 2025. Verfasst von Felix Aulenbacher und 12 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Allergology, Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin…. Hauptthemen laut MEDLINE: Artificial Intelligence, Urticaria, Chronic Urticaria. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Charité - Universitätsmedizin Berlin.
Abstract (Originalsprache)
BACKGROUND: Chronic urticaria (CU) severely impairs patients' quality of life. Correctly diagnosing and treating CU can take years, so patients seek answers from the Internet to manage the condition. OBJECTIVE: We aimed to build a chatbot, Artificial Intelligence-Driven Urticaria Support (AIDUS) for patients with CU and treating physicians and to evaluate its reliability in providing high-quality CU-specific information compared with Chat Generative Pre-Trained Transformer (ChatGPT)-3.5 and ChatGPT-4o. METHODS: AIDUS was developed by an expert committee of urticaria and artificial intelligence specialists using JavaScript and OpenAI's (https://www.clay.com/dossier/openai-headquarters-office-locations) ChatGPT large language model. PubMed was systematically reviewed to ensure AIDUS contained high-quality information. The chatbot was populated exclusively with selected peer-reviewed CU publications authored by the Charité University, Berlin research group, published after 2014. A total of 254 publications were integrated using ChatGPT-3.5 as the underlying algorithm. We developed A set of 100 validated questions based on current CU knowledge to evaluate the performance of AIDUS. The program was run on the same questions several times and compared for consistency. We tested performance with different chunk- and overlap-size settings to optimize AIDUS's efficiency and accuracy. RESULTS: AIDUS outperformed general ChatGPT models in terms of accuracy, consistency, and stability in answering CU-specific questions. AIDUS demonstrated higher average accuracy (94.6%) across multiple test runs compared with ChatGPT-3.5 (42.6%) and ChatGPT-4o (85.7%). CONCLUSIONS: AIDUS provides reliable, high-quality information about CU, addressing patients' and physicians' needs for accurate, relevant answers based on peer-reviewed medical literature. AIDUS remains a means of assistance and does not replace consultation with a physician.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Allergology, Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany; Immunology and Allergology, Fraunhofer Institute for Transl…
- Institute of Allergology, Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.
Förderung
- Charité - Universitätsmedizin Berlin
Zitieren
APA
Aulenbacher, F., Gutsche, A., Bihlmaier, B., Bonnekoh, H., Cherrez-Ojeda, I., Fluhr, J. W., Kolkhir, P., Magerl, M., Metz, M., Pyatilova, P., Siebenhaar, F., Zuberbier, T., & Neisinger, S. (2025). Development and Reliability Assessment of an Artificial Intelligence-Driven Urticaria Support (AIDUS) Chatbot. The Journal of Allergy and Clinical Immunology: In Practice. https://doi.org/10.1016/j.jaip.2025.07.047
Vancouver
Aulenbacher F, Gutsche A, Bihlmaier B, Bonnekoh H, Cherrez-Ojeda I, Fluhr JW, et al. Development and Reliability Assessment of an Artificial Intelligence-Driven Urticaria Support (AIDUS) Chatbot. The Journal of Allergy and Clinical Immunology: In Practice. 2025. doi:10.1016/j.jaip.2025.07.047
BibTeX
@article{Aulenbacher2025,
author = {Aulenbacher, Felix and Gutsche, Annika and Bihlmaier, Benedict and Bonnekoh, Hanna and Cherrez-Ojeda, Ivan and Fluhr, Joachim W and Kolkhir, Pavel and Magerl, Markus and Metz, Martin and Pyatilova, Polina and Siebenhaar, Frank and Zuberbier, Torsten and Neisinger, Sophia},
title = {Development and Reliability Assessment of an Artificial Intelligence-Driven Urticaria Support (AIDUS) Chatbot},
journal = {The Journal of Allergy and Clinical Immunology: In Practice},
year = {2025},
doi = {10.1016/j.jaip.2025.07.047}
}
EUVIMED