Exploring the potential of ChatGPT as a digital advisor in acute psychiatric crises: a feasibility study
Der Nervenarzt · 2026
DOI: 10.1007/s00115-025-01837-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Der Nervenarzt, 2026. Verfasst von Lubomir Barabas und 4 weiteren Autor:innen. Beteiligte Einrichtung: Private Clinic for Psychiatry and Psychotherapy Meiringen, Meiringen, Switzerland. Hauptthemen laut MEDLINE: Mental Disorders, Crisis Intervention. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universitäre Psychiatrische Dienste Bern.
Abstract (Originalsprache)
Background
This exploratory study tested ChatGPT as a digital advisor chatbot for German-speaking individuals in acute psychiatric crises. Additionally, the attitudes of young physicians and psychologists towards the use of large language models (LLMs) in healthcare were investigated.
Methods
In total, 20 resident physicians and psychologists simulated patients in three clinical scenarios (depression, psychosis, adjustment disorder) and interacted with ChatGPT. They evaluated the chatbot’s performance regarding overall experience, pleasantness, appropriateness of the responses, realism, and helpfulness. Before and after the intervention, their attitudes towards such a chatbot were assessed. Finally, they assessed 12 statements about the future of LLMs in healthcare and provided open feedback on the chat experience.
Results
ChatGPT received predominantly positive ratings (over 8/10 points) for overall experience, helpfulness, pleasantness, and appropriateness, while realism was rated slightly lower at 7/10 points. The appropriateness of the responses varied significantly between the scenarios, with lower ratings for the psychosis scenario. Open feedback confirmed the limited suitability of ChatGPT for psychosis patients. Overall, 70% or more of the participants agreed that LLMs will become increasingly important in everyday life and healthcare, and that an LLM-based chatbot would be a modern tool for low-threshold access to initial psychiatric aid. However, the high number of neutral responses across all 12 items (20–45%) indicates uncertainty regarding the actual benefits and risks.
Conclusion
The performance of ChatGPT was rated positively overall by the participants. Significant practical and methodological limitations remain, however, highlighting the need for further research including real patients for a gradual, carefully monitored integration of LLMs into mental healthcare.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Private Clinic for Psychiatry and Psychotherapy Meiringen, Meiringen, Switzerland.
- conceito GmbH, Leutzenheldstraße 4, 76327, Pfinztal, Germany.
- Translational Research Center, University Hospital of Psychiatry and Psychotherapy, University of Bern, Bern, Switzerland.
- Translational Research Center, University Hospital of Psychiatry and Psychotherapy, University of Bern, Bern, Switzerland. Nicolas.Mertse@upd.ch.
- University Hospital of Old Age Psychiatry and Psychotherapy, University of Bern, Murtenstrasse 21, 3008, Bern, Switzerland. Nicolas.Mertse@upd.ch.
Förderung
- Universitäre Psychiatrische Dienste Bern
Zitieren
APA
Barabas, L., Novotny, M., Jung, D., Müller, T., & Mertse, N. N. (2026). Exploring the potential of ChatGPT as a digital advisor in acute psychiatric crises: a feasibility study. Der Nervenarzt. https://doi.org/10.1007/s00115-025-01837-3
Vancouver
Barabas L, Novotny M, Jung D, Müller T, Mertse NN. Exploring the potential of ChatGPT as a digital advisor in acute psychiatric crises: a feasibility study. Der Nervenarzt. 2026. doi:10.1007/s00115-025-01837-3
BibTeX
@article{Barabas2026,
author = {Barabas, Lubomir and Novotny, Michal and Jung, Dennis and Müller, Thomas and Mertse, Nicolas Nagysomkuti},
title = {Exploring the potential of ChatGPT as a digital advisor in acute psychiatric crises: a feasibility study},
journal = {Der Nervenarzt},
year = {2026},
doi = {10.1007/s00115-025-01837-3}
}
EUVIMED