Related Experiment Video
Updated: May 5, 2026

A Fast and Quantitative Method for Post-translational Modification and Variant Enabled Mapping of Peptides to Genomes
Published on: May 22, 2018
Exploring the potential of ChatGPT in the peer review process: An observational study
Ahmed Saad1, Nathan Jenko2, Sisith Ariyaratne2
1Department of Orthopedics, Royal Orthopaedic Hospital, Birmingham, B31 2AP, UK.
Artificial intelligence (AI) chatbots like ChatGPT can assist human scientific peer review by improving efficiency. While not a replacement for human judgment, AI tools can offer valuable support in the editorial process.
Area of Science:
- Scholarly Publishing
- Artificial Intelligence in Research
Background:
- Scientific peer review is crucial for research quality but faces challenges due to increasing submission volumes.
- Reviewer burden and time constraints can impact participation and quality assurance.
- Artificial intelligence (AI) tools show potential to alleviate these pressures in manuscript evaluation.
Purpose of the Study:
- To explore the efficiency and effectiveness of ChatGPT, an AI chatbot, in the scientific peer review process.
- To compare AI-driven reviews with human evaluations of research manuscripts.
Main Methods:
- Anonymized review of 21 research articles by two human reviewers and ChatGPT (versions 3.5 and 4.0).
- AI was prompted to provide positive/negative comments and acceptance/rejection recommendations.
- Comparison of human and AI reviews using a 5-point Likert scale and correlation analysis.
Main Results:
- Subjective review similarity scores: 3.6/5 for ChatGPT 3.5 and 3.76/5 for ChatGPT 4.0.
- Statistically significant correlation between human and AI review scores for ChatGPT 3.5, but not for ChatGPT 4.0.
- AI review showed moderate similarity to human reviewers.
Conclusions:
- ChatGPT can complement human scientific peer review, improving editorial efficiency and promptness.
- Fully automated AI review is not currently advisable; AI's role should be constrained.
- AI tools offer potential support but do not replace human expertise in peer review.
Related Concept Videos
Proofreading
Statistical Significance
Study Design in Statistics
Does aspirin reduce the risk of heart attacks? Is one brand of fertilizer more effective at growing roses than another? Is fatigue as dangerous to a driver as the influence of alcohol? Questions like these are answered using randomized experiments with proper...
Observational Studies
There are three types of observational studies – Prospective, retrospective, and cross-sectional.
Prospective Study
Prospective studies, also known as longitudinal or cohort studies, are carried out by collecting future data from groups sharing similar characteristics. One...
Randomized Experiments
Simple randomization
Simple...
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...

