EUVIMEDEUVIMED entdecken
LeitlinieOpen Access · CC BY 4.0

GIN‐McMaster Guideline Development Checklist Extension for Integrating Artificial Intelligence in the Health Guideline Enterprise

GIN-McMaster Guideline Development Checklist Extension zur Integration von künstlicher Intelligenz in das Leitlinienwesen im Gesundheitsbereich

Manuel Marques-Cruz, Bernardo Sousa-Pinto iD, Ignacio Neumann, Yuan Chi, Monika Nothacker, Artur Nowak iD, Marge Reinap, Mariette Awad, Pablo Alonso-Coello, Amir Qaseem, Elie A Akl, Wojtek Wiercioch iD und 3 weitere

Clinical and Public Health Guidelines · 2026-07 · 3 (3)

DOI: 10.1002/gin2.70073 ↗

Auf einen Blick

Beschrieben wird die Entwicklung einer Erweiterung der GIN-McMaster Guideline Development Checklist für den Einsatz von KI im Leitlinienprozess. Die Endfassung umfasst 49 Items.

Fragestellung

Wie kann künstliche Intelligenz in die Entwicklung von Gesundheitsleitlinien in die GIN-McMaster Guideline Development Checklist integriert werden?

Methode

Entwicklungsarbeit der GIN-AI Working Group mit LLM-Prompting, iterativen Diskussionen und retrospektiver Anwendung auf ARIA 2024-2025.

Ergebnisse

LLM-Prompting erzeugte 149 Items; 117 wurden entfernt, 19 geändert und 17 neu ergänzt. Nach retrospektiver Anwendung wurden vier Items sprachlich angepasst; die Endfassung enthält 49 Items.

Schlussfolgerung der Autor:innen

Die Autor:innen berichten, dass eine Erweiterung der GIN-McMaster GDC entwickelt wurde, die Standards zur umfassenden und transparenten Integration von KI im Leitlinienwesen umfasst.

Kernaussagen

  • 149 Items aus LLM-Prompting erzeugt
  • 49 Items in der finalen Checklisten-Erweiterung
  • Retrospektive Anwendung führte zu Änderungen an vier Items

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Leitlinie in der Zeitschrift Clinical and Public Health Guidelines, online erschienen am 30.05.2026. Verfasst von Manuel Marques-Cruz und 14 weiteren Autor:innen. Beteiligte Einrichtung: MEDCIDS - Department of Community Medicine, Information and Health Decision Sciences; Faculty of Medicine University of Porto Porto Portugal. Die Arbeit nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Artificial intelligence (AI) may support several processes of the health guideline enterprise. This article describes the development of an extension of the Guidelines International Journal (GIN)‐McMaster Guideline Development Checklist (GDC) for integrating AI in the guideline enterprise. This development has been led by the GIN‐AI Working Group.

Methods

We started by prompting a large language model (LLM) for items related to the use of AI in each of the steps of the original GDC. Subsequently, the members of the working group engaged in a set of iterative discussions, resulting in item refinement and in a consensus first version of the extension. We retrospectively applied this first version to a case use of guidelines incorporating AI in their development (Allergic Rhinitis and its Impact on Asthma [ARIA] 2024‐2025 guidelines), leading to further refinement and to the approval of the final extension tool.

Results

Prompting LLMs resulted in the generation of 149 items. Of those, 117 were removed and 19 were modified by members of the working group. On the other hand, 17 new items were added during the iterative discussion process. The retrospective application of the extension led to changes in the wording of four items. The final version of the checklist extension has been approved with 49 items modifying or adding to the original GDC.

Discussion

We have developed an extension of the GIN‐McMaster GDC that encompasses a set of conduct standards that are intended to facilitate the comprehensive and transparent integration of AI in the health guideline enterprise. Clinical Trial Registration Not applicable. This study is not a clinical trial.

Autor:innen und Institutionen

  • MEDCIDS - Department of Community Medicine, Information and Health Decision Sciences; Faculty of Medicine University of Porto Porto Portugal.
  • CINTESIS@RISE - Health Research Network, MEDCIDS, Faculty of Medicine University of Porto Porto Portugal.
  • School of Medicine Universidad San Sebastián Santiago Chile.
  • Clinical Epidemiology and Research Center (CERC) Humanitas University Milan Italy.
  • Yealth Network, Beijing Yealth Technology Co., Ltd Beijing China.
  • AWMF (Association of the Scientific Medical Societies in Germany) Institute for Medical Knowledge Management, c/o University of Marburg, Marburg Germany.

ORCID-Profile: Bernardo Sousa-Pinto, Artur Nowak, Wojtek Wiercioch, Holger J Schünemann

Zitieren

APA

Marques-Cruz, M., Sousa-Pinto, B., Neumann, I., Chi, Y., Nothacker, M., Nowak, A., Reinap, M., Awad, M., Alonso-Coello, P., Qaseem, A., Akl, E. A., Wiercioch, W., Brozek, J., Schünemann, H. J., & GIN AI working group (2026). GIN‐McMaster Guideline Development Checklist Extension for Integrating Artificial Intelligence in the Health Guideline Enterprise. Clinical and Public Health Guidelines, 3(3). https://doi.org/10.1002/gin2.70073

Vancouver

Marques-Cruz M, Sousa-Pinto B, Neumann I, Chi Y, Nothacker M, Nowak A, et al. GIN‐McMaster Guideline Development Checklist Extension for Integrating Artificial Intelligence in the Health Guideline Enterprise. Clinical and Public Health Guidelines. 2026;3(3). doi:10.1002/gin2.70073

BibTeX
@article{MarquesCruz2026,
  author = {Marques-Cruz, Manuel and Sousa-Pinto, Bernardo and Neumann, Ignacio and Chi, Yuan and Nothacker, Monika and Nowak, Artur and Reinap, Marge and Awad, Mariette and Alonso-Coello, Pablo and Qaseem, Amir and Akl, Elie A and Wiercioch, Wojtek and Brozek, Jan and Schünemann, Holger J and GIN AI working group, GIN AI working group},
  title = {GIN‐McMaster Guideline Development Checklist Extension for Integrating Artificial Intelligence in the Health Guideline Enterprise},
  journal = {Clinical and Public Health Guidelines},
  year = {2026},
  volume = {3},
  number = {3},
  doi = {10.1002/gin2.70073}
}
Kostenlos starten →