Artificial intelligence in psychological prevention and treatment: Empirical insights into blended care, adaptive interventions, and clinical impact

AI applications in mental health care are advancing quickly, although both research and clinical use remain in early stages. Before 2010, most digital interventions involved internet-based treatment programs and monitoring tools based on simple “if–then” rules. Because these systems depended on predefined decision structures, their ability to personalise feedback, process natural language, or adapt to individual users and changing situations was limited. From around 2010 onward, improvements in artificial intelligence and computer science led to more flexible and adaptive methods, which have since been applied across many sectors, including mental healthcare.Current developments primarily focus on conversational AI technologies such as chatbots, natural language processing (NLP), and large language models, as well as predictive machine learning (ML) models. These methods allow researchers and clinicians to forecast the progression of mental health conditions like depression, using both active and passive monitoring data, and to adjust interventions dynamically, for instance through Just-in-Time Adaptive Interventions (JITAIs). Furthermore, multimodal models that combine text, audio, and visual data are being developed. However, these approaches have not yet seen widespread adoption in routine clinical practice. Alongside these opportunities, significant challenges still exist. These include concerns about the limited transparency of AI algorithms, their “black-box” operation, and issues related to safety and user privacy.Despite the still limited body of research and the substantial challenges involved, it is expected that these emerging interventions will increasingly be applied in both research and clinical practice. Potential applications include unguided, guided, and blended treatment approaches, as well as decision support systems for healthcare professionals and tools for clinical education and training. For this Research Topic, we invite submissions based on empirical data that focus on mental health clinical practice. We welcome the following article types: Original Research, Reviews, Systematic Reviews, Clinical Trials, Case Reports, Community Case Studies, Curriculum, Instruction, and Pedagogy articles, Data Reports, FAIR² Data, and Brief Research Reports. Areas of particular interest include:• AI-supported blended psychological treatments (e.g., CBT) for depression and anxiety• AI-driven prevention and treatment interventions for mental health disorders• AI-supported clinical case studies in mental health• AI-supported third-generation CBT treatments, such as schema therapy for trauma based on imagery rescripting or EMDR• AI-supported Just-In-Time Adaptive Interventions for mental health disorders• Feasibility, acceptance, and effectiveness studies using pre-post, RCT, or meta-analytic designs• Implementation studiesStudies only testing an AI model without clinical implications are out of scope for this collection. In addition, bibliographic analytic papers are also out of scope. Topic editors: Heleen Riper, Tim Wind, Pepijn Van De Ven Source: https://www.frontiersin.org/research-topics/78743/artificial-intelligence-in-psychological-prevention-and-treatment-empirical-insights-into-blended-care-adaptive-interventions-and-clinical-impact