Academic Journal
Unmasking bias in the evidence ecosystem: a panoramic analysis of 311,751 meta-analyses using an artificial intelligence agent-based approach.
| Title: | Unmasking bias in the evidence ecosystem: a panoramic analysis of 311,751 meta-analyses using an artificial intelligence agent-based approach. |
|---|---|
| Authors: | Chen X; Department of Adult Joint Reconstructive Surgery, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China., She Z; Department of Adult Joint Reconstructive Surgery, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China., Yang S; Changping Laboratory, Beijing, China., Chu M; Department of Immunology, School of Basic Medical Sciences, Peking University, Beijing, China., Zhou Y; Department of Adult Joint Reconstructive Surgery, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China. |
| Source: | Journal of global health [J Glob Health] 2026 Sep 04; Vol. 16, pp. 03029. Date of Electronic Publication: 2026 Sep 04. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: International Society of Global Health Country of Publication: Scotland NLM ID: 101578780 Publication Model: Electronic Cited Medium: Internet ISSN: 2047-2986 (Electronic) Linking ISSN: 20472978 NLM ISO Abbreviation: J Glob Health Subsets: MEDLINE |
| Imprint Name(s): | Publication: <2019>-: Edinburgh : International Society of Global Health Original Publication: Edinburgh : Edinburgh University Global Health Society, 2011- |
| MeSH Terms: | Artificial Intelligence* , Meta-Analysis as Topic*, Bias ; Large Language Models ; Humans ; Workflow |
| Abstract: | Traditional secondary meta-analysis workflows are highly labour-intensive, time-consuming, and difficult to update in real time. Currently, there is a lack of comprehensive artificial intelligence frameworks capable of automating the entire meta-analysis workflow, including literature screening, data extraction, and quality assessment. Furthermore, a large-scale structured database for systematically analysing the global landscape of published meta-analyses remains unavailable. In this viewpoint, we aimed to evaluate the feasibility of large language models in automating meta-analysis workflows and develop the Meta-Analysis Screening, Transformation and Evaluation Review Agent (MASTER) agent; establish a large-scale Unified Meta-Analysis Repository (UMAR) and perform an exploratory panoramic analysis of the current evidence ecosystem; and develop an Agent-based Secondary Meta-analysis Platform (ASAP), integrating these capabilities. We subsequently applied the agent to process 311,751 meta-analysis records to establish the UMAR database. Building upon these resources, we developed the ASAP platform to support multimodal, automated meta-analysis workflows. In benchmark evaluations, the MASTER agent demonstrated high accuracy and stability in performing core automated meta-analysis tasks. The ASAP platform enabled automated literature retrieval, quality assessment, data extraction, and visualisation generation through predefined workflows. Here, we provide an initial exploration of the technical feasibility and scalability of artificial intelligence-driven automated meta-analysis. (© 2026 The Authors.) |
| Competing Interests: | Disclosure of interest: The authors completed the ICMJE Disclosure of Interest Form (available upon request from the corresponding author) and disclose no relevant interests. |
| References: | Nature. 2025 Jun;642(8067):451-457. (PMID: 40205049) Annu Rev Psychol. 2019 Jan 4;70:747-770. (PMID: 30089228) Chest. 2020 Jul;158(1S):S97-S102. (PMID: 32658658) JAMA. 2025 Jan 28;333(4):319-328. (PMID: 39405325) Nat Med. 2025 Aug;31(8):2546-2549. (PMID: 40267970) Cell. 2025 Apr 17;188(8):2235-2248.e10. (PMID: 40147442) |
| Contributed Indexing: | Keywords: evidence synthesis; global health; large language models; meta-analysis; reporting bias; research integrity |
| Entry Date(s): | Date Created: 20260904 Date Completed: 20260904 Latest Revision: 20260914 |
| Update Code: | 20260915 |
| PubMed Central ID: | PMC13542800 |
| DOI: | 10.7189/jogh.16.03029 |
| PMID: | 42693920 |
| Database: | MEDLINE |
| ISSN: | 2047-2986 |
|---|---|
| DOI: | 10.7189/jogh.16.03029 |