SmartEBM AI Agent: A Web-Based Platform for Streamlining Network Meta-Analysis via Human-AI Collaboration
Complementary Medicine Research · 28.05.2026 · 1-14
DOI: 10.1159/000552717 ↗Kurz gefasst
Netzwerk-Metaanalyse in der Zeitschrift Complementary Medicine Research, online erschienen am 28.05.2026. Verfasst von Jiayi Liu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Health Policy and Health Management, School of Public Health, Lanzhou University, Lanzhou, China. Hauptthemen laut MEDLINE: Internet, Artificial Intelligence, Network Meta-Analysis as Topic. Die Arbeit nennt 20 Literaturangaben.
Abstract (Originalsprache)
Introduction
Network meta-analysis (NMA) plays an important role in comparative effectiveness research, particularly in fields such as traditional and complementary medicine, where multiple interventions often need to be assessed within a single evidence framework. However, conducting NMA remains labor-intensive, methodologically demanding, and difficult to complete efficiently using conventional workflows. Although recent advances in large language models have created new opportunities for supporting evidence synthesis, their routine use in NMA is still constrained by limited transparency, prompt dependency, and difficulty integrating with structured analytical procedures.
Methods
We developed SmartEBM, a web-based human-AI collaborative platform designed to support the full workflow of NMA. The platform is organized around a human-in-the-loop model, in which AI-assisted functions support repeated and labor-intensive tasks while researchers retain oversight of methodological judgment, verification, and final decision-making. SmartEBM integrates six functional modules: title and abstract screening, full-text screening, data extraction, risk of bias assessment, statistical analysis, and certainty of evidence assessment.
Results
SmartEBM provides low-code interfaces, structured outputs, and verification-oriented workspaces that connect the major steps of evidence synthesis within a single platform. The six modules collectively address the core analytical stages of NMA, enabling researchers to conduct screening, extraction, assessment, and analysis in an integrated environment rather than across disparate tools.
Conclusion
Rather than functioning as a stand-alone automation tool, SmartEBM is intended as a practical platform for end-to-end NMA support. This platform-oriented approach may help make evidence synthesis more manageable, traceable, and accessible in routine research practice, especially in complex review settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Health Policy and Health Management, School of Public Health, Lanzhou University, Lanzhou, China.
- Evidence-Based Medicine Center, School of Basic Medical Sciences, Lanzhou University, Lanzhou, China.
- State Key Laboratory of Dampness Syndrome of Chinese Medicine, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China, darongwu@gzucm.edu.cn.
- Department of Health Policy and Health Management, School of Public Health, Lanzhou University, Lanzhou, China, gelong2009@163.com.
- WHO Collaborating Center for Guideline Implementation and Knowledge Translation, Lanzhou, China, gelong2009@163.com.
Zitieren
APA
Liu, J., Lai, H., Zhao, W., Tong, B., Ma, N., Pan, B., Wu, D., & Ge, L. (2026). SmartEBM AI Agent: A Web-Based Platform for Streamlining Network Meta-Analysis via Human-AI Collaboration. Complementary Medicine Research, 1-14. https://doi.org/10.1159/000552717
Vancouver
Liu J, Lai H, Zhao W, Tong B, Ma N, Pan B, et al. SmartEBM AI Agent: A Web-Based Platform for Streamlining Network Meta-Analysis via Human-AI Collaboration. Complementary Medicine Research. 2026:1-14. doi:10.1159/000552717
BibTeX
@article{Liu2026,
author = {Liu, Jiayi and Lai, Honghao and Zhao, Weilong and Tong, Bo and Ma, Ning and Pan, Bei and Wu, Darong and Ge, Long},
title = {SmartEBM AI Agent: A Web-Based Platform for Streamlining Network Meta-Analysis via Human-AI Collaboration},
journal = {Complementary Medicine Research},
year = {2026},
pages = {1--14},
doi = {10.1159/000552717}
}
EUVIMED