Retrieval-Augmented Generation in Mental Health: A Systematic Review
Abstract
Abstract Background: Retrieval-augmented generation (RAG) grounds large language model outputs in external knowledge. Systematic reviews have examined RAG in healthcare and generative AI in mental health as separate topics.
Objective:: To systematically identify and synthesize empirical studies applying RAG to mental health, stress, anxiety, depression, psychological assessment, and digital therapeutics.
Methods:: Searches followed PRISMA 2020 reporting guidelines.20 PubMed was searched on 4 July 2026 (56 records). Additional records were identified through IEEE Xplore, ACM Digital Library, Scopus, Web of Science, and forward/backward citation tracking. One reviewer (E.F.) screened records, extracted data, and assessed study quality using a structured LLM-RAG framework adapted from prior reviews, with verification steps described in Methods. Outcomes were too heterogeneous for valid quantitative pooling; synthesis was qualitative.
Results:: Fifteen studies met inclusion criteria (2022–2026). Naïve RAG was reported in 5 studies, advanced RAG in 7, and modular RAG in 3. Depression and general psychological distress were the most common conditions. Six studies reported direct RAG-versus-baseline comparisons with published metrics; in each, RAG or knowledge-augmented configurations outperformed the stated comparator on the study's primary reported outcome. Crisis-management documentation appeared in 2 studies. No included study indexed multimodal behavioral, VR, or wearable…
How strong is the evidence?
Evidence Hub reads this as a systematic review. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.