Artificial intelligence in allergology: A Position Paper of the German Society of Allergology and Clinical Immunology (DGAKI), German Academy of Allergy, Clinical Immunology and Environmental Medicine (AeDA) and German Society of Pediatric Allergology and Environmental Medicine (GPA): Part 1.
22 affiliations
- 1Department of Otorhinolaryngology, Head and Neck Surgery, Section of Rhinology and Allergy, University Hospital Marburg, Philipps-Universität Marburg, Marburg.
- 2Contributed equally as first authors.
- 3Department of Dermatology and Allergy, Medizinische Hochschule Hannover, Hanover.
- 4Center for Rhinology and Allergology, Wiesbaden.
- 5Department of Otorhinolaryngology, Head and Neck Surgery, University of Tübingen.
- 6Hals-Nasen-Ohrenheilkunde, interdisziplinäre Facharztklinik, Düsseldorf.
- 7Center of Allergy & Environment (ZAUM), Member of the German Center for Lung Research (DZL), Technical University and Helmholtz Center, Munich.
- 8Department of Pediatric Respiratory Care, Immunology and Intensive Care Medicine, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin.
- 9Allergology and Immunology, Department of Dermatology, Venereology and Allergology, Charité-Universitätsmedizin, Berlin.
- 10Pediatric Pulmonology and Allergology, University Hospital Augsburg, Augsburg.
- 11Children's Center Bethel, University Hospital OWL, University Bielefeld, Bielefeld.
- 12Institute of Biometry and Clinical Epidemiology, Charité - Universitätsmedizin Berlin, Berlin.
- 13Department of Pediatrics, GFO-Kliniken Bonn, St. Marien-Hospital, Bonn.
- 14Institute of Allergology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin.
- 15Fraunhofer Institute for Translational Medicine and Pharmacology ITMP, Allergology and Immunology, Berlin.
- 16Pediatric Dermatology and Allergology, Kinder- und Jugendkrankenhaus AUF DER BULT, Hannover.
- 17Kinderarztpraxis Hirschberg, Hirschberg.
- 18Department of Otorhinolaryngology, Düsseldorf University Hospital, Düsseldorf.
- 19Kinderarztpraxis Dr. med. Mehrak Yoosefi, Berlin.
- 20Department of Dermatology and Allergology, TUM Clinic Rechts der Isar, School of Medicine and Health, Technical University of Munich, Munich, and.
- 21Contributed equally as last authors.
- 22Department of Respiratory Medicine, Allergology and Sleep Medicine, General Hospital Nuremberg, Campus North, Paracelsus Medical University, Nuremberg, Germany.
Abstract
Background
Artificial intelligence (AI) is rapidly advancing in medicine, yet its translation into clinical and research practice in allergology remains limited. Given the heterogeneity of allergic diseases and the complexity of integrating clinical, environmental, and molecular data, a structured assessment is required. This first part of a joint position paper, developed by German allergology societies and associations under the leadership of the DGAKI, aims to establish a conceptual and clinical foundation for AI in allergology.Materials and methods
The Position Paper is based on a targeted narrative literature review and structured expert consensus. Development was informed by AGREE II principles. Part I comprises Chapters 1 - 4, covering introduction, methodology, AI taxonomy, and selected early application domains.Results
AI is conceptualized as an augmentative tool supporting clinical reasoning and individualized decision-making. The paper distinguishes classical statistical approaches from machine learning, deep learning, vision models, and large language models, emphasizing their complementary roles. Key applications include environmental analytics (e.g., automated pollen monitoring and forecasting), image-based classification systems, clinical decision support for diagnostics and therapy, and emerging patient-facing tools. Across these domains, AI may improve diagnostic precision and enable integration of heterogeneous data. Limitations include restricted generalizability, bias, limited explainability, and regulatory and data protection challenges.Conclusion
The role of AI in allergology is defined, its methodological basis is outlined, and initial application domains are highlighted. Together, these elements provide a framework for evidence-based and patient-oriented integration, requiring human oversight, robust scientific validation, and regulatory alignment.
Related
- Editorial: Revolutionizing obstetric and pediatric pharmacology through artificial intelligence and digital health innovations
- Artificial intelligence in pediatric head and neck tumor imaging: a mini review of current applications and future directions
- Unique Opportunities and Challenges of Artificial Intelligence in Pediatric Imaging.
- Artificial intelligence–enabled nursing surveillance for pediatric cancer immunotherapy: integrating biomarkers, patient-reported outcomes, and long-term toxicity management
- Artificial Intelligence in Pediatric Cardiovascular Genetics: From Multimodal Diagnosis to Risk Prediction and Precision Therapeutics
BibTeX
@article{pfaar2026artificial,
title = {{Artificial intelligence in allergology: A Position Paper of the German Society of Allergology and Clinical Immunology (DGAKI), German Academy of Allergy, Clinical Immunology and Environmental Medicine (AeDA) and German Society of Pediatric Allergology and Environmental Medicine (GPA): Part 1.}},
author = {Oliver Pfaar and Stephan Traidl and Friederike Bärhold and Sven Becker and Christoph Bergmann and Jeroen Buters and Stephanie Dramburg and Wojciech Francuzik and Michael Gerstlauer and Eckard Hamelmann and Camilo José Hernandez Toro and Ludger Klimek and Lars Lange and Paolo M Matricardi and Laura Pfeffer and Mariel Suarez-Suarez and Philipp Utz and Martin Wagenmann and Margitta Worm and Mehrak Yoosefi and Sonja Mathes and Sebastian Seurig},
journal = {Allergologie select},
year = {2026},
month = oct,
doi = {10.5414/alx02643e},
url = {https://europepmc.org/article/MED/43011820},
note = {CC BY},
}
RIS
TY - JOUR
TI - Artificial intelligence in allergology: A Position Paper of the German Society of Allergology and Clinical Immunology (DGAKI), German Academy of Allergy, Clinical Immunology and Environmental Medicine (AeDA) and German Society of Pediatric Allergology and Environmental Medicine (GPA): Part 1.
AU - Oliver Pfaar
AU - Stephan Traidl
AU - Friederike Bärhold
AU - Sven Becker
AU - Christoph Bergmann
AU - Jeroen Buters
AU - Stephanie Dramburg
AU - Wojciech Francuzik
AU - Michael Gerstlauer
AU - Eckard Hamelmann
AU - Camilo José Hernandez Toro
AU - Ludger Klimek
AU - Lars Lange
AU - Paolo M Matricardi
AU - Laura Pfeffer
AU - Mariel Suarez-Suarez
AU - Philipp Utz
AU - Martin Wagenmann
AU - Margitta Worm
AU - Mehrak Yoosefi
AU - Sonja Mathes
AU - Sebastian Seurig
PY - 2026
DA - 2026/10/12
JO - Allergologie select
DO - 10.5414/alx02643e
UR - https://europepmc.org/article/MED/43011820
AB - Background Artificial intelligence (AI) is rapidly advancing in medicine, yet its translation into clinical and research practice in allergology remains limited. Given the heterogeneity of allergic diseases and the complexity of integrating clinical, environmental, and molecular data, a structured assessment is required. This first part of a joint position paper, developed by German allergology societies and associations under the leadership of the DGAKI, aims to establish a conceptual and clinical foundation for AI in allergology.Materials and methods The Position Paper is based on a targeted narrative literature review and structured expert consensus. Development was informed by AGREE II principles. Part I comprises Chapters 1 - 4, covering introduction, methodology, AI taxonomy, and selected early application domains.Results AI is conceptualized as an augmentative tool supporting clinical reasoning and individualized decision-making. The paper distinguishes classical statistical approaches from machine learning, deep learning, vision models, and large language models, emphasizing their complementary roles. Key applications include environmental analytics (e.g., automated pollen monitoring and forecasting), image-based classification systems, clinical decision support for diagnostics and therapy, and emerging patient-facing tools. Across these domains, AI may improve diagnostic precision and enable integration of heterogeneous data. Limitations include restricted generalizability, bias, limited explainability, and regulatory and data protection challenges.Conclusion The role of AI in allergology is defined, its methodological basis is outlined, and initial application domains are highlighted. Together, these elements provide a framework for evidence-based and patient-oriented integration, requiring human oversight, robust scientific validation, and regulatory alignment.
SN - 2512-8957
ER -