Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
AI Reporting Guidelines: How to Select the Best One for Your Research
54
Zitationen
4
Autoren
2023
Jahr
Abstract
T he rapid increase in publications related to artificial intelligence (AI) in medical imaging has pinpointed the need for transparent and organized research reporting.Publications on AI research should provide the necessary information to ensure adherence to high scientific standards while allowing the independent reproduction of the research.Reproducibility is necessary to enable clinical translation and adoption of AI algorithms that may otherwise remain on paper.For this purpose, a series of tools have been developed to guide the comprehensive reporting of AI research to promote research reproducibility, adherence to ethical standards, comprehensibility of research manuscripts, and publication of scientifically valid results.The use of such guidelines has been encouraged or mandated by scientific journals to allow appropriate evaluation of research output during the review process.The majority of existing guidelines and checklists allow authors to confirm the inclusion of specific information in each manuscript section: Title, Abstract, Introduction, Methods, Results, and Discussion.The content of these checklists highlights the minimum information a journal requires for the publication of an AI study, providing researchers with guidelines to conduct their research while also easing and standardizing the review process.Existing guidelines or guidelines under development specific to AI include CLAIM (Checklist for Artificial Intelligence in Medical Imaging), STARD-AI (Standards for Reporting of Diagnostic Accuracy Study-AI), CONSORT-AI (Consolidated Standards of Reporting Trials-AI), SPIRIT-AI (Standard Protocol Items: Recommendations for Interventional Trials-AI), FUTURE-AI (Fairness Universality Traceability Usability Robustness Explainability-AI), MI-CLAIM (Minimum Information about Clinical Artificial Intelligence Modeling), MINIMAR (Minimum Information for Medical AI Reporting), and RQS (Radiomics Quality Score).In this editorial, we compare these guidelines and their content to help readers find the best guideline for their research.Table 1 provides a high-level overview including a summary of guidelines' availability, purpose, and format and brief information about which manuscript sections they address.
Ähnliche Arbeiten
New response evaluation criteria in solid tumours: Revised RECIST guideline (version 1.1)
2008 · 28.795 Zit.
TNM Classification of Malignant Tumours
1987 · 16.123 Zit.
A survey on deep learning in medical image analysis
2017 · 13.500 Zit.
Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening
2011 · 10.736 Zit.
The American Joint Committee on Cancer: the 7th Edition of the AJCC Cancer Staging Manual and the Future of TNM
2010 · 9.101 Zit.