AI-Generated Exposure Hierarchies for Body Dysmorphic Disorder: Proof-of-Concept Study
- 1Department of Psychiatry, Massachusetts General Hospital, 185 Cambridge Street, Suite 2000, Boston, MA, 02114, United States, 1 6177246146
- 2Department of Psychiatry, Harvard Medical School, Boston, MA, United States
- 3iris labs, Cambridge, MA, United States
Abstract
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<.001; r=0.73) and overall quality ratings (P=.01; r=0.43). This pattern was not unique to GPT-5; safety ratings for expert-generated hierarchies also declined significantly by insight level (P=.03). Miscalibration of exposure difficulty, particularly for low- and absent-insight cases, was the most common rater concern (30/43, 69.8% comments), disproportionately directed at GPT-5 hierarchies.
Conclusions: GPT-5 generated ERP hierarchies for BDD that blinded experts rated as comparable to clinician-created hierarchies and could not reliably distinguish them from clinician-created hierarchies. However, hierarchies for patients with absent insight received lower safety and quality ratings from both AI and expert sources, and qualitative comments suggested AI-generated hierarchies were less well calibrated to delusional-level presentations. GenAI thus shows promise as a clinician-facing aid for ERP hierarchy generation, but these findings underscore the need for clinician oversight, especially for patients with delusional conviction.
Related
- Effects of theta burst stimulation on neural connectivity and visual perception following attention modification of own-face viewing in body dysmorphic disorder
- LLM-Generated Well-being Intervention Recommendations Are Sensitive to Psychological Profiles: A Proof-of-Concept Expert-Rating Study
- Proof‐of‐concept trial of PP‐01 for mitigating cannabis withdrawal syndrome in participants with cannabis use disorder
- Letter: Reconsidering Scopolamine as a Psychedelic Adjunct in Exposure-Based Therapy: Cholinergic Modulation and Fear Extinction in Social Anxiety Disorder
- An Evaluation of Neuro-Physiological Psychotherapy for Adopted Children and Young People with Neurodevelopmental Trauma and Prenatal Alcohol Exposure Who May Meet Criteria for Foetal Alcohol Syndrome Disorder
BibTeX
@article{jonathan2026aigenerated,
title = {{AI-Generated Exposure Hierarchies for Body Dysmorphic Disorder: Proof-of-Concept Study}},
author = {Geneva K Jonathan and Adam C Jaroszewski and Heyli T Arcese and Natasha H Bailen and Ivar Snorrason and Anne Chosak and Jennifer Ragan and Susan Sprich and Jessica Rasmussen and Emily E Bernstein and Sabine Wilhelm},
journal = {JMIR Formative Research},
year = {2026},
month = nov,
doi = {10.2196/98393},
url = {https://doi.org/10.2196/98393},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - AI-Generated Exposure Hierarchies for Body Dysmorphic Disorder: Proof-of-Concept Study
AU - Geneva K Jonathan
AU - Adam C Jaroszewski
AU - Heyli T Arcese
AU - Natasha H Bailen
AU - Ivar Snorrason
AU - Anne Chosak
AU - Jennifer Ragan
AU - Susan Sprich
AU - Jessica Rasmussen
AU - Emily E Bernstein
AU - Sabine Wilhelm
PY - 2026
DA - 2026/11/03
JO - JMIR Formative Research
DO - 10.2196/98393
UR - https://doi.org/10.2196/98393
AB - 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<.001; r=0.73) and overall quality ratings (P=.01; r=0.43). This pattern was not unique to GPT-5; safety ratings for expert-generated hierarchies also declined significantly by insight level (P=.03). Miscalibration of exposure difficulty, particularly for low- and absent-insight cases, was the most common rater concern (30/43, 69.8% comments), disproportionately directed at GPT-5 hierarchies. Conclusions: GPT-5 generated ERP hierarchies for BDD that blinded experts rated as comparable to clinician-created hierarchies and could not reliably distinguish them from clinician-created hierarchies. However, hierarchies for patients with absent insight received lower safety and quality ratings from both AI and expert sources, and qualitative comments suggested AI-generated hierarchies were less well calibrated to delusional-level presentations. GenAI thus shows promise as a clinician-facing aid for ERP hierarchy generation, but these findings underscore the need for clinician oversight, especially for patients with delusional conviction.
SN - 2561-326X
ER -