EUVIMEDEUVIMED entdecken
Systematische ÜbersichtMetaanalyseOpen Access · CC BY 4.0

Transforming evidence synthesis: A systematic review of the evolution of automated meta-analysis in the age of AI

Lingbo Li iD, Anuradha Mathrani iD, Teo Susnjak iD

Research Synthesis Methods · 2026-05 · 17 (3) · 403-450

DOI: 10.1017/rsm.2025.10065 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Research Synthesis Methods, online erschienen am 09.01.2026. Verfasst von Lingbo Li und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematical and Computational Sciences, https://ror.org/052czxv31Massey University, New Zealand. Hauptthemen laut MEDLINE: Artificial Intelligence, Meta-Analysis as Topic. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 113 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Exponential growth in scientific literature has heightened the demand for efficient evidence-based synthesis, driving the rise of the field of automated meta-analysis (AMA) powered by natural language processing and machine learning. This PRISMA systematic review introduces a structured framework for assessing the current state of AMA, based on screening 13,216 papers (2006–2024) and analyzing 61 studies across diverse domains. Findings reveal a predominant focus on automating data processing (52.5%), such as extraction and statistical modeling, while only 16.4% address advanced synthesis stages. Just one study (approximately 2%) explored preliminary full-process automation, highlighting a critical gap that limits AMA’s capacity for comprehensive synthesis. Despite recent breakthroughs in large language models and advanced AI, their integration into statistical modeling and higher-order synthesis, such as heterogeneity assessment and bias evaluation, remains underdeveloped. This has constrained AMA’s potential for fully autonomous meta-analysis (MA). From our dataset spanning medical (67.2%) and non-medical (32.8%) applications, we found that AMA has exhibited distinct implementation patterns and varying degrees of effectiveness in actually improving efficiency, scalability, and reproducibility. While automation has enhanced specific meta-analytic tasks, achieving seamless, end-to-end automation remains an open challenge. As AI systems advance in reasoning and contextual understanding, addressing these gaps is now imperative. Future efforts must focus on bridging automation across all MA stages, refining interpretability, and ensuring methodological robustness to fully realize AMA’s potential for scalable, domain-agnostic synthesis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceMeta-Analysis as TopicHumansAlgorithmsAutomationIntelligent SystemsLarge Language ModelsMachine LearningModels, StatisticalNatural Language ProcessingReproducibility of Results

Stichwörter der Autor:innen

AI-driven meta-analysisautomated evidence synthesisautomated meta-analysis (AMA)large language models for meta-analysisscalable meta-analysissystematic reviews

Autor:innen und Institutionen

  • School of Mathematical and Computational Sciences, https://ror.org/052czxv31Massey University, New Zealand.

ORCID-Profile: Lingbo Li, Anuradha Mathrani, Teo Susnjak

Zitieren

APA

Li, L., Mathrani, A., & Susnjak, T. (2026). Transforming evidence synthesis: A systematic review of the evolution of automated meta-analysis in the age of AI. Research Synthesis Methods, 17(3), 403-450. https://doi.org/10.1017/rsm.2025.10065

Vancouver

Li L, Mathrani A, Susnjak T. Transforming evidence synthesis: A systematic review of the evolution of automated meta-analysis in the age of AI. Research Synthesis Methods. 2026;17(3):403-450. doi:10.1017/rsm.2025.10065

BibTeX
@article{Li2026,
  author = {Li, Lingbo and Mathrani, Anuradha and Susnjak, Teo},
  title = {Transforming evidence synthesis: A systematic review of the evolution of automated meta-analysis in the age of AI},
  journal = {Research Synthesis Methods},
  year = {2026},
  volume = {17},
  number = {3},
  pages = {403--450},
  doi = {10.1017/rsm.2025.10065}
}
Kostenlos starten →