Package: metaextractoR Type: Package Title: Data Extraction for Meta-Analysis with Large Language Models Version: 0.1.0 Authors@R: c( person( given = "Danyang", family = "Dai", email = "danyan.dai01@gmail.com", role = c("aut", "cre", "cph"), comment = c(ORCID = "0009-0006-3984-291X") ), person( given = "Emi", family = "Tanaka", email = "dr.emi.tanaka@gmail.com", role = c("aut"), comment = c(ORCID = "0000-0002-1455-259X") ), person( given = "Jason", family = "Pole", email = "j.pole@uq.edu.au", role = c("ths"), comment = c(ORCID = "0000-0002-0413-5434") ) ) Description: Use Large Language Models (LLMs) to assist with data extraction for meta-analysis. This package incorporates three modular Shiny apps to implement a human-in-the-loop framework. (1) a manual extraction interface for abstracts, (2) refining prompt engineering and model selection, and (3) validation of LLM-generated outputs. These apps enable researchers to iteratively collaborate with LLMs, with each abstract undergoing double data extraction—once manually by a human researcher and once independently by an LLM-assisted process—to emulate the double extraction process recommended by international standards. Notably, the package runs fully on local machines, with no need for API setup or external data transfer, maximising data privacy and accessibility. Robust logging features further enhance transparency and reproducibility by recording all prompt iterations and outputs. License: MIT + file LICENSE Encoding: UTF-8 LazyData: true RoxygenNote: 7.3.2 Depends: R (>= 3.5) Imports: ellmer, shiny, tidyr, shinyFiles, cli, dplyr, fs, methods, DT, bslib, shinyjs Suggests: testthat (>= 3.0.0) Config/testthat/edition: 3 URL: https://danyangdai.github.io/metaextractoR/ BugReports: https://github.com/DanyangDai/metaextractoR/issues Config/pak/sysreqs: cmake make libicu-dev libuv1-dev libssl-dev zlib1g-dev Repository: https://emitanaka.r-universe.dev Date/Publication: 2026-04-07 22:22:39 UTC RemoteUrl: https://github.com/DanyangDai/metaextractoR RemoteRef: HEAD RemoteSha: 229c8547ffc83f73d418a860254f066023d9ec0d NeedsCompilation: no Packaged: 2026-07-05 08:34:35 UTC; root Author: Danyang Dai [aut, cre, cph] (ORCID: ), Emi Tanaka [aut] (ORCID: ), Jason Pole [ths] (ORCID: ) Maintainer: Danyang Dai