BODY DYSMORPHIC DISORDER SCREENING IN AESTHETIC PRACTICE AND THE ROLE OF ARTIFICIAL INTELLIGENCE

Abstract

Background

Body dysmorphic disorder (BDD) is a psychiatric disorder characterized by a persistent preoccupation with perceived defects in physical appearance that are minimal or not observable to others. It is particularly relevant in aesthetic medicine, where prevalence appears higher than in the general population. Patients with BDD often seek cosmetic interventions; however, aesthetic treatment rarely addresses the underlying psychopathology and may worsen dissatisfaction, reinforce distorted self-perception, and increase requests for repeated procedures. Early recognition is therefore essential for patient safety and ethical practice.

Objective

To review the literature on the screening of BDD in aesthetic practice and to examine the emerging role of artificial intelligence (AI) as a supportive tool for early detection.

Methodology

A structured literature review was conducted using PubMed, Embase, Scopus, and Google Scholar. Studies published in English between January 2000 and March 2026 were considered. Search terms included body dysmorphic disorder, BDD, aesthetic medicine, cosmetic surgery, psychological screening, artificial intelligence, machine learning, and deep learning. A Best Evidence Topic (BestBETs) approach was used to evaluate the literature.

Results

The reviewed literature supports the use of validated screening tools, including the Body Dysmorphic Disorder Questionnaire (BDDQ), BDDQ-Dermatology Version (BDDQ-DV), Dysmorphic Concern Questionnaire (DCQ), and Cosmetic Procedure Screening Questionnaire (COPS), for identifying patients at risk of BDD in aesthetic settings. However, screening tools alone are insufficient for diagnosis, and a clinical interview by a mental health professional remains essential. Emerging AI-based approaches, including machine learning, natural language processing, digital phenotyping, and computer vision, show potential as adjunctive methods for identifying behavioral, linguistic, and visual patterns associated with dysmorphic concern. Current evidence is promising but limited by small sample sizes, heterogeneity of methods, and lack of large-scale clinical validation.

Conclusion

Conventional screening tools remain the cornerstone of BDD detection in aesthetic practice. AI may serve as a useful decision-support tool for early recognition, but it should complement rather than replace clinical judgment and psychiatric evaluation. Future