Automated Meta-Analysis of Transcranial Magnetic Stimulation Based on GraphRAG: A Methodology Study
Abstract
Abstract Background The therapeutic efficacy of transcranial magnetic stimulation (TMS) is highly dependent on the selection of stimulation parameters. Different parameter combinations for the same disease may lead to heterogeneous clinical outcomes, necessitating quantitative evidence synthesis via meta-analysis to optimize stimulation protocols. However, manual meta-analysis is time-consuming and prone to human error, making automated meta-analysis a worthwhile area of investigation. Large language models (LLMs) are capable of extracting information from unstructured text, offering potential for automated data extraction. Nevertheless, conducting a full meta-analysis requires systematic retrieval and synthesis of all relevant literature, rather than processing individual papers or isolated sections. Conventional retrieval-augmented generation (RAG), which uses text chunks as retrieval units, cannot satisfy this requirement. Therefore, this paper proposes a literature extraction and retrieval method based on the GraphRAG paradigm. Methods The methodological workflow comprises three parts: parameter extraction, knowledge graph construction, and query-based retrieval. In the parameter extraction phase, we design a long-text processing strategy based on title-based chunking and sliding windows, along with prompt templates combining semantic blocks for basic information, outcome measures, TMS parameters, and risk of bias. In the knowledge graph construction phase, we use papers…
How strong is the evidence?
Evidence Hub reads this as a meta-analysis. 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.