Evaluating large language models for quality control in research ethics review

Abstract Large Language Models (LLMs) could streamline research ethics and governance review by automating routine quality control checks. This study assessed Claude 3.5 Sonnet, ChatGPT4o, and Microsoft CoPilot in evaluating participant information sheets against Health Research Authority standards. Six clinical trial applications were processed using 32 standardised queries, with accuracy, processing time, error rates, and response quality assessed by two blinded reviewers. Claude showed the highest accuracy, detected more deviations from guidance, and had the fastest processing time (7.17 ± 0.68 min vs. ChatGPT 13.58 ± 2.2 min, CoPilot 23.25 ± 6.21 min). Hallucination rates were lowest in Claude, followed by ChatGPT and CoPilot. Claude also received the highest response quality ratings (77.6% “very good” vs. ChatGPT 56.7%, CoPilot 45.2%). While all three models were capable, Claude consistently outperformed the others, demonstrating the potential of LLM-assisted quality control while emphasizing the need for human oversight.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-16
DOI
https://doi.org/10.1038/s41598-026-62027-y
Citations
2
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
2.03
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Evaluating large language models for quality control in research ethics review

Simon Erik Kolstoe, Pearse Andrew Keane, Zoher Kapacee, Jonathan Fennelly-Barnwell et al.
2 citations
Scientific Reports
Artificial Intelligence in Healthcare and Education
2.03
article

Evaluating large language models for quality control in research ethics review

Simon Erik Kolstoe, Pearse Andrew Keane, Zoher Kapacee, Jonathan Fennelly-Barnwell, Xiaoxuan Liu, Panagiotis Maghsoudlou, A. Abraham, Sunil Mamtora, Alastair Keith Denniston, Ashley Totenhofer
article en
2 citations

Abstract

Abstract Large Language Models (LLMs) could streamline research ethics and governance review by automating routine quality control checks. This study assessed Claude 3.5 Sonnet, ChatGPT4o, and Microsoft CoPilot in evaluating participant information sheets against Health Research Authority standards. Six clinical trial applications were processed using 32 standardised queries, with accuracy, processing time, error rates, and response quality assessed by two blinded reviewers. Claude showed the highest accuracy, detected more deviations from guidance, and had the fastest processing time (7.17 ± 0.68 min vs. ChatGPT 13.58 ± 2.2 min, CoPilot 23.25 ± 6.21 min). Hallucination rates were lowest in Claude, followed by ChatGPT and CoPilot. Claude also received the highest response quality ratings (77.6% “very good” vs. ChatGPT 56.7%, CoPilot 45.2%). While all three models were capable, Claude consistently outperformed the others, demonstrating the potential of LLM-assisted quality control while emphasizing the need for human oversight.

Scientific ReportsVol. 16(1)
University Hospitals Birmingham NHS Foundation Trust (GB), Moorfields Eye Hospital NHS Foundation Trust (GB), University of Bristol (GB), NIHR Moorfields Biomedical Research Centre (GB), UCL Biomedical Research Centre (GB), Health Research Authority (GB), University College London (GB), University of Portsmouth (GB), University of Birmingham (GB)
Openalex Percentile: Top 14%
Artificial Intelligence in Healthcare and Education
2.03
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon