ArticleCochrane evidence synthesis and methods2025
Data Extractions Using a Large Language Model (Elicit) and Human Reviewers in Randomized Controlled Trials: A Systematic Comparison.
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 7 papers, 1 of them a synthesis that pooled it.
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
7 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Barriers and facilitators to initiating and adhering to harm reduction services among people who inject drugs in the United States: a systematic review.Harm reduction journal · 2026Pooled it
- Characterizing core outcomes of responsible stewardship for human genomic data in the cloud.BMC medical genomics · 2026Article
- Policies and Interventions in Middle Eastern and North African Countries to Mitigate Heat Stress Experienced by Outdoor Workers: A Scoping Literature Review.Current environmental health reports · 2026Article
- The Impact of Politicization on Adolescent Medicine Care: A Rapid Review.Current pediatrics reports · 2026Review
- Performance of large language models and prompt engineering strategies for data extraction in systematic reviews.Frontiers in digital health · 2026Article
- Harnessing meta-analyses' insights in ecology and evolution research.Royal Society open science · 2025Article
- Forms of transphobia and their influence on health outcomes among transgender, nonbinary, and gender diverse individuals: a global systematic review.International journal of transgender health · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Aim: We aimed at comparing data extractions from randomized controlled trials by using Elicit and human reviewers. Background: Elicit is an artificial intelligence tool which may automate specific steps in conducting systematic reviews. However, the tool's performance and accuracy have not been independently assessed. Methods: For comparison, we sampled 20 randomized controlled trials of which data were extracted manually from a human reviewer. We assessed the variables study objectives, sample characteristics and size, study design, interventions, outcome measured, and intervention effects and classified the results into "more," "equal to," "partially equal," and "deviating" extractions. STROBE checklist was used to report the study. Results: We analysed 20 randomized controlled trials from 11 countries. The studies covered diverse healthcare topics. Across all seven variables, Elicit extracted "more" data in 29.3% of cases, "equal" in 20.7%, "partially equal" in 45.7%, and "deviating" in 4.3%. Elicit provided "more" information for the variable study design (100%) and sample characteristics (45%). In contrast, for more nuanced variables, such as "intervention effects," Elicit's extractions were less detailed, with 95% rated as "partially equal." Conclusions: Elicit was capable of extracting data partly correct for our predefined variables. Variables like "intervention effect" or "intervention" may require a human reviewer to complete the data extraction. Our results suggest that verification by human reviewers is necessary to ensure that all relevant information is captured completely and correctly by Elicit. Implications: Systematic reviews are labor-intensive. Data extraction process may be facilitated by artificial intelligence tools. Use of Elicit may require a human reviewer to double-check the extracted data.
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.