Scorecards for Synthetic Medical Data Evaluation and Reporting
This addresses the problem of inconsistent quality assessment for synthetic medical data, benefiting developers, users, and regulators, though it is incremental as it builds on existing evaluation concepts.
The paper tackles the lack of standardized evaluation for synthetic medical data by proposing SMD Card, a framework for comprehensive reporting, which aims to improve transparency and adoption in AI applications.
Although interest in synthetic medical data (SMD) for training and testing AI methods is growing, the absence of a standardized framework to evaluate its quality and applicability hinders its wider adoption. Here, we outline an evaluation framework designed to meet the unique requirements of medical applications, and introduce SMD Card, which can serve as comprehensive reports that accompany artificially generated datasets. This card provides a transparent and standardized framework for evaluating and reporting the quality of synthetic data, which can benefit SMD developers, users, and regulators, particularly for AI models using SMD in regulatory submissions.