ChatGPT for Automated Cross-Checking of Authors' Conflicts of Interest Against Industry Payments
Related Experiment Video
Updated: Jun 30, 2025

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
Published on: December 1, 2020
Conrad Safranek1,2, Christina Liu1, Rhys Richmond1
1Department of Surgery, Division of Otolaryngology, Yale School of Medicine, New Haven, Connecticut, USA.
Objective:
The Centers for Medicare & Medicaid Services "OpenPayments" database tracks industry payments to US physicians to improve research conflicts of interest (COIs) transparency, but manual cross-checking of articles' authors against this database is labor-intensive. This study aims to assess the potential of large language models (LLMs) like ChatGPT to automate COI data analysis in medical publications.
Study Design:
An observational study analyzing the accuracy of ChatGPT in automating the cross-checking of COI disclosures in medical research articles against the OpenPayments database.
Setting:
Publications regarding Food and Drug Administration-approved biologics for chronic rhinosinusitis with nasal polyposis: omalizumab, mepolizumab, and dupilumab.
Methods:
First, ChatGPT evaluated author affiliations from PubMed to identify those based in the United States. Second, for author names matching 1 or multiple payment recipients in OpenPayments, ChatGPT undertook a comparative analysis between author affiliation and OpenPayments recipient metadata. Third, ChatGPT scrutinized full article COI statements, producing an intricate matrix of disclosures for each author against each relevant company (Sanofi, Regeneron, Genentech, Novartis, and GlaxoSmithKline). A random subset of responses was manually checked for accuracy.
Results:
In total, 78 relevant articles and 294 unique US authors were included, leading to 980 LLM queries. Manual verification showed accuracies of 100% (200/200; 95% confidence interval [CI]: 98.1%-100%) for country analysis, 97.4% (113/116; 95% CI: 92.7%-99.1%) for matching author affiliations with OpenPayments metadata, and 99.2% (1091/1100; 95% CI: 98.5%-99.6%) for COI statement data extraction.
Conclusion:
LLMs have robust potential to automate author-company-specific COI cross-checking against the OpenPayments database. Our findings pave the way for streamlined, efficient, and accurate COI assessment that could be widely employed across medical research.
More Related Videos
Related Concept Videos
Cross-reactivity
Inductively Coupled Plasma-Mass Spectrometry (ICP-MS): Interferences
Crossing Over
The homologous pairs of sister chromosomes—one from the maternal and one from the paternal genome—then begin to align alongside each other lengthwise, matching corresponding DNA positions in a process...
Quantifying and Rejecting Outliers: The Grubbs Test
Confirmation Biases
Protein Folding Quality Check in the RER

