Related Experiment Videos
Adherence of CLAIM in Artificial Intelligence Research: A Cross-Sectional Study
Chenhao Gao1, Yilan Zhang1, Renjie Zhao2
1Clinical Epidemiology and Evidence-Based Medicine Center, West China Hospital, Sichuan University, Chengdu, China.
Journal of Evidence-Based Medicine
|June 25, 2026
Summary
Adherence to the Checklist for Artificial Intelligence (AI) in Medical Imaging (CLAIM) is inadequate in top journals, highlighting a need for improved reporting standards in AI medical research.
Area of Science:
- Medical Imaging AI Research
- Scientific Reporting Standards
- Artificial Intelligence in Medicine
Background:
- Artificial intelligence (AI) is increasingly used in medical imaging, necessitating standardized reporting to ensure research quality and reproducibility.
- The Checklist for Artificial Intelligence (AI) in Medical Imaging (CLAIM) was developed to guide the reporting of AI studies in this field.
- Assessing the adherence to CLAIM in high-impact medical imaging journals is crucial for understanding current reporting practices.
Purpose of the Study:
- To evaluate the extent to which AI research published in leading medical imaging journals adheres to the CLAIM guidelines.
- To identify factors influencing the reporting quality and compliance rate with CLAIM.
- To analyze temporal trends in CLAIM adherence over time.
Main Methods:
- A systematic search of AI research articles was conducted in prominent medical imaging journals indexed in the Web of Science Core Collection.
- Reporting scores and compliance rates were calculated based on the 42 items of the CLAIM checklist.
- Statistical analyses, including correlation and logistic regression, were performed to identify factors associated with CLAIM adherence.
Main Results:
- A total of 501 articles were analyzed, with a median CLAIM score of 19 and an overall median compliance rate of 51.4%.
- Significant gaps in reporting were observed, particularly concerning annotation quality control, sample size determination, model robustness, failure analysis, and data/code availability.
- While overall adherence showed a weak positive trend with publication year, specific items like structured abstracts and data availability demonstrated significant improvements over time. Research objectives focused on image reconstruction, artifact reduction, multimodal imaging, and the use of public datasets were associated with lower reporting quality.
Conclusions:
- Current adherence to the CLAIM checklist in top medical imaging journals is insufficient, indicating a need for enhanced reporting standards.
- Collaborative efforts among researchers, editors, and reviewers are essential to strengthen the implementation and application of CLAIM.
- Improving adherence to CLAIM will enhance the quality, transparency, and reproducibility of AI research in medical imaging.
Related Concept Videos
Stereotypes, Prejudice, and Discrimination
Humans are very diverse and although we share many similarities, we also have many differences. The social groups we belong to help form our identities (Tajfel, 1974). These differences may be difficult for some people to reconcile, which may lead to prejudice toward people who are different. Prejudice is a negative attitude and feeling toward an individual based solely on one’s membership in a particular social group (Allport, 1954; Brown, 2010). Prejudice is common against people who are...
Social Proof
Social proof is a form of persuasion based on comparison and conformity. People compare their behavior and actions to what others are doing and will change to conform to do what their peers do.
Cause and Effect
While variables are sometimes correlated because one does cause the other, it could also be that some other factor, a confounding variable, is actually causing the systematic movement in our variables of interest. For instance, as sales in ice cream increase, so does the overall rate of crime. Is it possible that indulging in your favorite flavor of ice cream could send you on a crime spree? Or, after committing crime do you think you might decide to treat yourself to a cone?