ArticleCochrane evidence synthesis and methods2025
Using Artificial Intelligence Tools as Second Reviewers for Data Extraction in Systematic Reviews: A Performance Comparison of Two AI Tools Against Human Reviewers.
Article in Cochrane evidence synthesis and methods, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 14 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
14 citing papers in PubMed.
- Impact of maxillomandibular atresia on the response to mandibular advancement devices in obstructive sleep apnea: a scoping review.Sleep & breathing = Schlaf & Atmung · 2026Article
- Automated data extraction for systematic reviews using GPT-5.2 and Google Gemini Pro 3: A dual-large language model approach in orthopaedic research.Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA · 2026Article
- From API to Action: A Multi-Model Comparison of OpenAI, Anthropic, Google, and Meta LLMs for Clinical Trial Data Extraction.Bioengineering (Basel, Switzerland) · 2026Article
- From review to synthesis: A step-by-step methodological guide to systematic reviews and multilevel meta-analyses.Behavior research methods · 2026Article
- Using Generative AI to Appraise the Quality of Medical Education Research Studies: Agreement Between AI-Generated and Human MERSQI Scores.AEM education and training · 2026Article
- Artificial intelligence in rheumatology and paediatric rheumatology: insights from an international survey by EMEUNET.EULAR rheumatology open · 2026Article
- Methodological Quality of Umbrella Reviews in Paediatric Dentistry: A Cross-Sectional Study.International dental journal · 2026Article
- AI-accelerated meta-analysis in psychology: Large language models code study properties with high accuracy.Behavior research methods · 2026Article
- How large language models can help us write a systematic review.Intensive care medicine · 2026Article
- Core open science practices in major medical journals: development of an automatized tool based on a Large Language Model.Open research Europe · 2026Article
- Optimizing systematic reviews in health sciences education: a mentefact-based algorithmic framework.Frontiers in medicine · 2026Article
- Responsible Integration of Artificial Intelligence in Rapid Reviews: A Position Statement From the Cochrane Rapid Reviews Methods Group.Cochrane evidence synthesis and methods · 2025Article
- Ignorance Is Not Bliss: A Systematic Review on the Impact of Ignoring UK Medical Students During Clinical Placements.Cureus · 2025Review
- Evaluating artificial intelligence-enabled medical tests in cardiology: Best practice.International journal of cardiology. Heart & vasculature · 2025Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Background: Systematic reviews are essential but time-consuming and expensive. Large language models (LLMs) and artificial intelligence (AI) tools could potentially automate data extraction, but no comprehensive workflow has been tested for different review types. Objective: To evaluate Elicit's and ChatGPT's abilities to extract data from journal articles as a replacement for one of two human data extractors in systematic reviews. Methods: Human-extracted data from three systematic reviews (30 articles in total) was compared to data extracted by Elicit and ChatGPT. The AI tools extracted population characteristics, study design, and review-specific variables. Performance metrics were calculated against human double-extracted data as the gold standard, followed by a detailed error analysis. Results: Precision, recall and F1-score were all 92% for Elicit and 91%, 89% and 90% for ChatGPT. Recall was highest for study design (Elicit: 100%; ChatGPT: 90%) and population characteristics (Elicit: 100%; ChatGPT: 97%), while review-specific variables achieved 77% in Elicit and 80% in ChatGPT. Elicit had four instances of confabulation while ChatGPT had three. There was no significant difference between the two AI tools' performance (recall difference: 3.3% points, 95% CI: -5.2%-11.9%, Conclusion: AI tools demonstrated high and similar performance in data extraction compared to human reviewers, particularly for standardized variables. Error analysis revealed confabulations in 4% of data points. We propose adopting AI-assisted extraction to replace the second human extractor, with the second human instead focusing on reconciling discrepancies between AI and the primary human extractor.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.