Computational Strategies for Depression Detection and Treatment: The Role of Behavioral Activation and Neurobiological Insights - A Systematic Review

ObjectiveDepression is a multifaceted disorder with neurobiological, behavioral, and environmental components. This review aims to explore how artificial intelligence (AI) and computational methods are advancing the understanding and treatment of depression, focusing on neurobiological mechanisms, early detection, and behavioral activation (BA) interventions. MethodsA comprehensive literature review was conducted searching PubMed, Scopus, ACM, and Web of Science databases. From 77654 articles identified, 48 studies were selected based on relevance and methodological rigor. These include meta-analyses, randomized controlled trials, or observational studies, focusing on the integration of AI and computational tools in depression research and treatment. ResultsAdvances in AI-driven neuroimaging and machine learning have enhanced the identification of neurobiological changes associated with depression, such as hippocampal atrophy, prefrontal cortex dysfunction, and HPA axis dysregulation. AI models have also facilitated early detection of subtle biomarkers linked to neuroinflammation and reduced BDNF levels. Furthermore, AI-powered digital platforms have optimized BA interventions, personalized treatment and improving access through virtual coaching and mobile applications. AI-enhanced interventions incorporating physical activity monitoring have shown neuroprotective effects, promoting neurogenesis, reducing inflammation, and increasing BDNF levels. ConclusionThe integration of AI and computational approaches into traditional depression therapies holds significant promise. AI-driven tools, when combined with BA interventions, provide scalable, personalized solutions, particularly for individuals with limited access to conventional treatments. The future of depression care can strongly profit from the convergence of AI, neurobiology, and behavioral science, which will enhance diagnostic accuracy, treatment effectiveness, and accessibility.