EUVIMEDEUVIMED entdecken
Open Access

Leveraging Large Language Models for Simulated Psychotherapy Client Interactions: Development and Usability Study of Client101

Daniel Cabrera Lozoya iD, Mike Conway iD, Edoardo Sebastiano De Duro iD, Simon D'Alfonso iD

JMIR Medical Education · 31.07.2025 · 11 · e68056-e68056

DOI: 10.2196/68056 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Medical Education, online erschienen am 31.07.2025. Verfasst von Daniel Cabrera Lozoya und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing and Information Systems, The University of Melbourne, Gratham St, Parkville VIC, Melbourne, 3010, Australia, 61 90355511. Hauptthemen laut MEDLINE: Psychotherapy, Language, Patient Simulation. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

In recent years, large language models (LLMs) have shown a remarkable ability to generate human-like text. One potential application of this capability is using LLMs to simulate clients in a mental health context. This research presents the development and evaluation of Client101, a web conversational platform featuring LLM-driven chatbots designed to simulate mental health clients.

Objective

We aim to develop and test a web-based conversational psychotherapy training tool designed to closely resemble clients with mental health issues.

Methods

We used GPT-4 and prompt engineering techniques to develop chatbots that simulate realistic client conversations. Two chatbots were created based on clinical vignette cases: one representing a person with depression and the other, a person with generalized anxiety disorder. A total of 16 mental health professionals were instructed to conduct single sessions with the chatbots using a cognitive behavioral therapy framework; a total of 15 sessions with the anxiety chatbot and 14 with the depression chatbot were completed. After each session, participants completed a 19-question survey assessing the chatbot’s ability to simulate the mental health condition and its potential as a training tool. Additionally, we used the LIWC (Linguistic Inquiry and Word Count) tool to analyze the psycholinguistic features of the chatbot conversations related to anxiety and depression. These features were compared to those in a set of webchat psychotherapy sessions with human clients—42 sessions related to anxiety and 47 related to depression—using an independent samples t test.

Results

Participants’ survey responses were predominantly positive regarding the chatbots’ realism and portrayal of mental health conditions. For instance, 93% (14/15) considered that the chatbot provided a coherent and convincing narrative typical of someone with an anxiety condition. The statistical analysis of LIWC psycholinguistic features revealed significant differences between chatbot and human therapy transcripts for 3 of 8 anxiety-related features: negations ( t 56 =4.03, P =.001), family ( t 56 =–8.62, P =.001), and negative emotions ( t 56 =–3.91, P =.002). The remaining 5 features—sadness, personal pronouns, present focus, social, and anger—did not show significant differences. For depression-related features, 4 of 9 showed significant differences: negative emotions ( t 60 =–3.84, P =.003), feeling ( t 60 =–6.40, P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PsychotherapyLanguagePatient SimulationHumansFemaleMaleAdultCommunicationCognitive Behavioral TherapyLarge Language Models

Stichwörter der Autor:innen

chatbotsmedical educationmental healthpsychotherapy trainingvirtual client

Autor:innen und Institutionen

  • School of Computing and Information Systems, The University of Melbourne, Gratham St, Parkville VIC, Melbourne, 3010, Australia, 61 90355511.
  • Department of Psychology and Cognitive Science, University of Trento, Trento, Italy.

ORCID-Profile: Daniel Cabrera Lozoya, Mike Conway, Edoardo Sebastiano De Duro, Simon D'Alfonso

Zitieren

APA

Cabrera Lozoya, D., Conway, M., Sebastiano De Duro, E., & D'Alfonso, S. (2025). Leveraging Large Language Models for Simulated Psychotherapy Client Interactions: Development and Usability Study of Client101. JMIR Medical Education, 11, e68056-e68056. https://doi.org/10.2196/68056

Vancouver

Cabrera Lozoya D, Conway M, Sebastiano De Duro E, D'Alfonso S. Leveraging Large Language Models for Simulated Psychotherapy Client Interactions: Development and Usability Study of Client101. JMIR Medical Education. 2025;11:e68056-e68056. doi:10.2196/68056

BibTeX
@article{CabreraLozoya2025,
  author = {Cabrera Lozoya, Daniel and Conway, Mike and Sebastiano De Duro, Edoardo and D'Alfonso, Simon},
  title = {Leveraging Large Language Models for Simulated Psychotherapy Client Interactions: Development and Usability Study of Client101},
  journal = {JMIR Medical Education},
  year = {2025},
  volume = {11},
  pages = {e68056--e68056},
  doi = {10.2196/68056}
}
Kostenlos starten →