Advancing precision psychiatry: Machine learning integration with neuroimaging for early detection and diagnosis of Obsessive-Compulsive Disorder.

Early detection of Obsessive-Compulsive Disorder (OCD), a chronic mental health condition characterized by intrusive thoughts and repetitive behaviors, is crucial for improving patient outcomes. Traditional diagnostic methods rely heavily on subjective assessments, which are often delayed or inaccurate. This review explores recent advancements in machine learning (ML) models - particularly hybrid and explainable AI (XAI) approaches - integrated with neuroimaging modalities such as structural (sMRI) and functional MRI (fMRI), as well as biochemical and clinical biomarkers. Studies demonstrate that ML techniques, including support vector machines (SVM), convolutional neural networks (CNN), and deep learning hybrids, can achieve diagnostic accuracies exceeding 90%. XAI methods like SHAP enhance interpretability and clinical trust. Despite promising results, challenges such as dataset variability, limited generalizability, and ethical concerns remain. The review highlights the need for multimodal data integration, scalable models, and privacy-preserving frameworks to support clinical adoption. By shifting from subjective assessments to ML-driven diagnostics, this paradigm promotes earlier detection, personalized treatment, and improved outcomes-advancing precision psychiatry in OCD care.