Human <i>vs</i> . artificial intelligence: Physicians outperform ChatGPT in real‐world pharmacotherapy counselling
ChatGPT's responses to real-world pharmacotherapeutic queries were substantially inferior compared to conventional physician-generated responses with regard to quality of information and factual correctness. Our study suggests that to date it must be strongly cautioned against the use of ChatGPT in pharmacotherapy counselling.
Authors
- Felix Koop (ORCID: https://orcid.org/0000-0001-7378-7877)
- Dirk O. Stichtenoth (ORCID: https://orcid.org/0000-0002-6526-0917)
- Benjamin Krichevsky (ORCID: https://orcid.org/0000-0001-5899-0113)
- Sebastian Schröder (ORCID: https://orcid.org/0000-0003-0905-274X)
- Stefanie M. Bode‐Böger (ORCID: https://orcid.org/0000-0002-5132-6591)
- Thorben Pape (ORCID: https://orcid.org/0000-0003-1031-1913)
- Carsten Schumacher (ORCID: https://orcid.org/0000-0002-3012-4245)
- Martin Schulze Westhoff (ORCID: https://orcid.org/0000-0003-3262-8137)
- Stefan Engeli (ORCID: https://orcid.org/0000-0002-3087-971X)
- Johannes Heck (ORCID: https://orcid.org/0000-0002-5382-3014)
Institutions
- Universitätsmedizin Greifswald (DE)
- Medizinische Hochschule Hannover (DE)
- University Hospital Schleswig-Holstein (DE)
- Technical University of Munich (DE)
- University of Lübeck (DE)
- Otto-von-Guericke-Universität Magdeburg (DE)
Publication Details
- Journal
- British Journal of Clinical Pharmacology
- Published
- 2025-10-25
- DOI
- https://doi.org/10.1002/bcp.70321
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Deutsche Forschungsgemeinschaft
- Medizinischen Hochschule Hannover