EUVIMEDEUVIMED entdecken
FallberichtOpen Access · CC BY 4.0

Artificial intelligence-assisted visual elicitation in anorexia nervosa

Dimitri Chubinidze, Catherine Perry, Kate Tchanturia

neuropsychiatrie · 2025

DOI: 10.1007/s40211-025-00538-2 ↗

Kurz gefasst

Fallbericht in der Zeitschrift neuropsychiatrie, 2025. Verfasst von Dimitri Chubinidze und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Psychiatry, Psychology and Neuroscience, Department of Psychological Medicine, King's College London, London, UK. Dimitri.Chubinidze@kcl…. Hauptthemen laut MEDLINE: Anorexia Nervosa, Artificial Intelligence. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council (EPSRC), Impact Acceleration Account (IAA), MRF_, Medical Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

This study explored the feasibility and therapeutic potential of combining artificial intelligence (AI)-assisted visual elicitation with sensory-attuned guided reflection to support emotional expression and engagement in individuals with anorexia nervosa (AN).

Methods

We conducted a two-session, therapist-led intervention with two adults with restrictive AN. In session 1, we guided participants to reflect on emotionally challenging experiences using metaphor and sensory language cues. We translated these narratives into prompts for DALL·E (v3; OpenAI, San Francisco, CA, USA), an AI image-generation tool. In session 2, participants selected from curated images to reflect on and deepen their exploration of emotional experiences. We analysed the data using reflexive thematic analysis and performed a cross-case synthesis.

Results

Visual metaphors helped to externalise and communicate emotions, evoke embodied responses and refine affective descriptions. The co-creative process fostered therapeutic engagement and a greater sense of agency in both participants.

Conclusion

AI-assisted visual elicitation, integrated into a structured therapeutic process, may offer an additional benefit to talking therapy for individuals with AN. By enabling visual expression, this approach could support emotional insight and communication in populations with emotion labelling and regulation differences.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Anorexia NervosaArtificial IntelligenceHumansFemaleAdultQualitative ResearchMetaphorEmotionsYoung AdultFeasibility StudiesCues

Stichwörter der Autor:innen

Artificial intelligence-generated imagesEating disordersEmotion regulationGuided reflectionPhoto elicitationVisual metaphor

Autor:innen und Institutionen

  • Institute of Psychiatry, Psychology and Neuroscience, Department of Psychological Medicine, King's College London, London, UK. Dimitri.Chubinidze@kcl.ac.uk.
  • Department of Eating Disorders, South London and Maudsley NHS Foundation Trust, London, UK.
  • Institute of Psychiatry, Psychology and Neuroscience, Department of Psychological Medicine, King's College London, London, UK.
  • Department of Psychology, Illia State University, Tbilisi, Georgia.

Förderung

  • Engineering and Physical Sciences Research Council (EPSRC), Impact Acceleration Account (IAA)
  • MRF_
  • Medical Research Foundation
  • NIHR BRC for Mental Health, SLaM, and Institute of Psychiatry, Psychology and Neuroscience, KCL
  • Maudsley Charity

Zitieren

APA

Chubinidze, D., Perry, C., & Tchanturia, K. (2025). Artificial intelligence-assisted visual elicitation in anorexia nervosa. neuropsychiatrie. https://doi.org/10.1007/s40211-025-00538-2

Vancouver

Chubinidze D, Perry C, Tchanturia K. Artificial intelligence-assisted visual elicitation in anorexia nervosa. neuropsychiatrie. 2025. doi:10.1007/s40211-025-00538-2

BibTeX
@article{Chubinidze2025,
  author = {Chubinidze, Dimitri and Perry, Catherine and Tchanturia, Kate},
  title = {Artificial intelligence-assisted visual elicitation in anorexia nervosa},
  journal = {neuropsychiatrie},
  year = {2025},
  doi = {10.1007/s40211-025-00538-2}
}
Kostenlos starten →