AI-DRIVEN DETECTION AND TREATMENT RESPONSE PREDICTION IN OBSESSIVE–COMPULSIVE DISORDER: A SYSTEMATIC REVIEW

Obsessive–compulsive disorder (OCD) is a chronic and disabling neuropsychiatric condition characterized by intrusive thoughts and repetitive behaviours that cause significant functional impairment. Despite its prevalence, diagnosis is often delayed by an average of 7.1 years, and in some cases up to 17 years, leading to poorer outcomes and increased socioeconomic burden. Recent advances in artificial intelligence (AI), including traditional machine learning (ML) and deep learning (DL), offer promising solutions for improving early diagnosis and predicting treatment response in OCD. Although findings demonstrate the significant potential of AI-driven methods in OCD research, substantial methodological heterogeneity remains across studies, emphasizing the need for standardized protocols, larger datasets, and clinically interpretable models.