EUVIMEDEUVIMED entdecken
Open Access

AI-Generated Exposure Hierarchies for Body Dysmorphic Disorder: Proof-of-Concept Study

Geneva K Jonathan, Adam C Jaroszewski, Heyli T Arcese, Natasha H Bailen, Ivar Snorrason, Anne Chosak, Jennifer Ragan, Susan Sprich, Jessica Rasmussen, Emily E Bernstein, Sabine Wilhelm

JMIR Formative Research · 03.11.2026 · 10 · e98393-e98393

DOI: 10.2196/98393 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Formative Research, online erschienen am 03.11.2026. Verfasst von Geneva K Jonathan und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry, Massachusetts General Hospital, 185 Cambridge Street, Suite 2000, Boston, MA, 02114, United States, 1 6177246146. Hauptthemen laut MEDLINE: Body Dysmorphic Disorders, Cognitive Behavioral Therapy. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Body dysmorphic disorder (BDD) is a chronic, impairing condition for which cognitive behavioral therapy, including exposure and response prevention (ERP), is the first-line treatment, but few clinicians are trained in BDD-specific ERP. Constructing personalized exposure hierarchies is time-intensive and requires clinical expertise, particularly for patients with absent insight who may hold appearance beliefs with delusional conviction. Generative AI (GenAI)–powered chatbots, such as ChatGPT, have shown utility for clinical content, but their capacity to produce safe, appropriate ERP hierarchies for BDD has not been examined.

Objective

This study evaluated the feasibility of using ChatGPT (GPT-5) to generate ERP hierarchies for BDD, assessed the influence of clinical and demographic characteristics on output quality, benchmarked AI-generated hierarchies against those created by doctoral-level BDD specialists, and tested whether blinded experts could distinguish AI-generated from expert-generated hierarchies.

Methods

GPT-5 generated 10-item graded exposure hierarchies for 72 simulated vignettes that varied by body area, insight level (good, limited, or absent), symptom specificity, age, and gender. Expert clinicians independently generated hierarchies for a subset of 18 vignettes. Two researchers rated all GPT-5 hierarchies for task completion and information integration. Three BDD expert clinicians, blinded to the hierarchy source (expert vs GPT-5), rated all 90 hierarchies for relevance, specificity, variability, safety, and overall quality. After unblinding, raters attempted to identify the AI-generated hierarchy in the 18 matched pairs.

Results

GPT-5 generated complete hierarchies for 69 of 72 (95.8%) vignettes. Blinded experts rated GPT-5 hierarchies highly across all dimensions (mean scores ranging from 4.39, SD 0.26 to 4.90, SD 0.16 out of 5), with no significant differences from expert-generated hierarchies except for variability, where experts scored modestly higher ( P =.02; r =0.24). After unblinding, raters correctly identified AI-generated hierarchies only 31.5% (17/54) of the time, significantly below chance ( P =.009); this below-chance result was mostly due to one rater, and no rater performed above chance. Insight level was the most consistent predictor of quality: absent-insight hierarchies received significantly lower safety ( P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Body Dysmorphic DisordersCognitive Behavioral TherapyHumansGenerative Artificial IntelligenceFemaleMaleAdultProof of Concept StudyMiddle Aged

Stichwörter der Autor:innen

AIbody dysmorphic disorderclinical decision supportcognitive behavioral therapydigital healthexposure therapyinsightlarge language modelsmental healthtreatment planning

Autor:innen und Institutionen

  • Department of Psychiatry, Massachusetts General Hospital, 185 Cambridge Street, Suite 2000, Boston, MA, 02114, United States, 1 6177246146.
  • Department of Psychiatry, Harvard Medical School, Boston, MA, United States.
  • iris labs, Cambridge, MA, United States.

Zitieren

APA

Jonathan, G. K., Jaroszewski, A. C., Arcese, H. T., Bailen, N. H., Snorrason, I., Chosak, A., Ragan, J., Sprich, S., Rasmussen, J., Bernstein, E. E., & Wilhelm, S. (2026). AI-Generated Exposure Hierarchies for Body Dysmorphic Disorder: Proof-of-Concept Study. JMIR Formative Research, 10, e98393-e98393. https://doi.org/10.2196/98393

Vancouver

Jonathan GK, Jaroszewski AC, Arcese HT, Bailen NH, Snorrason I, Chosak A, et al. AI-Generated Exposure Hierarchies for Body Dysmorphic Disorder: Proof-of-Concept Study. JMIR Formative Research. 2026;10:e98393-e98393. doi:10.2196/98393

BibTeX
@article{Jonathan2026,
  author = {Jonathan, Geneva K and Jaroszewski, Adam C and Arcese, Heyli T and Bailen, Natasha H and Snorrason, Ivar and Chosak, Anne and Ragan, Jennifer and Sprich, Susan and Rasmussen, Jessica and Bernstein, Emily E and Wilhelm, Sabine},
  title = {AI-Generated Exposure Hierarchies for Body Dysmorphic Disorder: Proof-of-Concept Study},
  journal = {JMIR Formative Research},
  year = {2026},
  volume = {10},
  pages = {e98393--e98393},
  doi = {10.2196/98393}
}
Kostenlos starten →