CLAIM 2024 Checklist

Section / Topic	No.	Item	Page / Line No	No	NA
TITLE / ABSTRACT
	1	Identification as a study of AI methodology, specifying the category of technology used (e.g., deep learning)
ABSTRACT
	2	Summary of study design, methods, results, and conclusions
INTRODUCTION
	3	Scientific and/or clinical background, including the intended use and role of the AI approach
	4	Study aims, objectives, and hypotheses
METHODS
Study Design	5	Prospective or retrospective study
	6	Study goal
Data	7	Data sources
	8	Inclusion and exclusion criteria
	9	Data pre-processing
	10	Selection of data subsets
	11	De-identification methods
	12	How missing data were handled
	13	Image acquisition protocol
Reference Standard	14	Definition of method(s) used to obtain reference standard
	15	Rationale for choosing the reference standard
	16	Source of reference standard annotations
	17	Annotation of test set
	18	Measures of inter- and intra-rater variability of features described by the annotators
Data Partitions	19	How data were assigned to partitions
	20	Level at which partitions are disjoint
Testing Data	21	Intended sample size
Model	22	Detailed description of model
	23	Software libraries, frameworks, and packages
	24	Initialization of model parameters
Training	25	Details of training approach
	26	Method of selecting the final model
	27	Ensembling techniques
Evaluation	28	Metrics of model performance
	29	Statistical measures of significance and uncertainty
	30	Robustness or sensitivity analysis
	31	Methods for explainability or interpretability
	32	Evaluation on internal data
	33	Testing on external data
	34	Clinical trial registration
RESULTS
Data	35	Numbers of patients or examinations included and excluded
	36	Demographic and clinical characteristics of cases in each partition
Model performance	37	Performance metrics and measures of statistical uncertainty
	38	Estimates of diagnostic performance and their precision
	39	Failure analysis of incorrect results
DISCUSSION
	40	Study limitations
	41	Implications for practice, including intended use and/or clinical role
OTHER INFORMATION
	42	Provide a reference to the full study protocol or to additional technical details
	43	Statement about the availability of software, trained model, and/or data
	44	Sources of funding and other support; role of funders

* Indicate page and/or line number for each checklist item that is present. NA = not applicable.

Tejani AS, Klontzas ME, Gatti AA, et al. Checklist for Artificial Intelligence in Medical Imaging (CLAIM):2024 Update. Radiol Artif Intell 2024;6(4):e240300. https://doi.org/10.1148/ryai.240300