ChatGPT Performance on 120 Interdisciplinary Allergology Questions—Systematic Evaluation With Clinical Error Impact Assessment for Critical Erroneous AI-Guided Chatbot Advice
ChatGPT's imperfect reliability in allergology highlights the need for expert counseling in specialized fields. Tailoring these tools to allergy use cases could improve utility of models like ChatGPT for clinical applications, such as answering questions from allergological routine care.
Authors
- Kirsten M. M. Beyer (ORCID: https://orcid.org/0000-0002-7513-8528)
- Sebastian Seurig (ORCID: https://orcid.org/0000-0001-6511-0102)
- Sonja Mathes (ORCID: https://orcid.org/0000-0001-5770-762X)
- Tilo Biedermann (ORCID: https://orcid.org/0000-0002-5352-5105)
- Manfred Wagner (ORCID: https://orcid.org/0000-0001-7583-1667)
- Friederike Bluhme
- Ulf Darsow
- Fabian Heizmann
- Ina Neugärtner
Institutions
- Humboldt-Universität zu Berlin (DE)
- Nuremberg Hospital (DE)
- Technical University of Munich (DE)
Publication Details
- Journal
- The Journal of Allergy and Clinical Immunology In Practice
- Published
- 2025-03-27
- DOI
- https://doi.org/10.1016/j.jaip.2025.03.030
- Citations
- 3
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.96