Artificial intelligence approaches, including machine learning and digital phenotyping, offer new opportunities for identifying, predicting, and treating obesity-related depression.
Abstract Depression and obesity are among the most prevalent and disabling health conditions worldwide, imposing a substantial burden on healthcare systems and society. Increasing evidence suggests a bidirectional relationship between these disorders, supported by common biological, genetic, metabolic, inflammatory, and psychosocial mechanisms. Obesity contributes significantly to the development of numerous chronic diseases, including cardiovascular disease, type 2 diabetes mellitus, metabolic syndrome, non-alcoholic fatty liver disease, sleep disorders, and neurodegenerative conditions, all of which may further exacerbate depressive symptomatology. Recent advances in artificial intelligence (AI) have created new opportunities for identifying, predicting, and treating obesity-related depression through machine learning, deep learning, digital phenotyping, and precision medicine approaches. This narrative review examines the complex relationship between depression and obesity, discusses the major diseases associated with obesity, and explores the current and future role of AI in clinical decision-making, risk prediction, genetic profiling, and personalized therapeutic interventions.
Ana-Maria et al. (2026) conducted a review in Depression and obesity. Artificial intelligence was evaluated. Artificial intelligence approaches, including machine learning and digital phenotyping, offer new opportunities for identifying, predicting, and treating obesity-related depression.