Objectives: This paper draws attention to: i) key considerations for evaluating artificial intelligence (AI) enabled clinical decision support; and ii) challenges and practical implications of AI design, development, selection, use, and ongoing surveillance.
Method: A narrative review of existing research and evaluation approaches along with expert perspectives drawn from the International Medical Informatics Association (IMIA) Working Group on Technology Assessment and Quality Development in Health Informatics and the European Federation for Medical Informatics (EFMI) Working Group for Assessment of Health Information Systems.
Results: There is a rich history and tradition of evaluating AI in healthcare. While evaluators can learn from past efforts, and build on best practice evaluation frameworks and methodologies, questions remain about how to evaluate the safety and effectiveness of AI that dynamically harness vast amounts of genomic, biomarker, phenotype, electronic record, and care delivery data from across health systems. This paper first provides a historical perspective about the evaluation of AI in healthcare. It then examines key challenges of evaluating AI-enabled clinical decision support during design, development, selection, use, and ongoing surveillance. Practical aspects of evaluating AI in healthcare, including approaches to evaluation and indicators to monitor AI are also discussed.
Conclusion: Commitment to rigorous initial and ongoing evaluation will be critical to ensuring the safe and effective integration of AI in complex sociotechnical settings. Specific enhancements that are required for the new generation of AI-enabled clinical decision support will emerge through practical application.
SummaryObjectives: To set the scientific context and then suggest principles for an evidence-based approach to secondary uses of clinical data, covering both evaluation of the secondary uses of data and evaluation of health systems and services based upon secondary uses of data. Method: Working Group review of selected literature and policy approaches.Results: We present important considerations in the evaluation of secondary uses of clinical data from the angles of governance and trust, theory, semantics, and policy. We make the case for a multi-level and multi-factorial approach to the evaluation of secondary uses of clinical data and describe a methodological framework for best practice. We emphasise the importance of evaluating the governance of secondary uses of health data in maintaining trust, which is essential for such uses. We also offer examples of the re-use of routine health data to demonstrate how it can support evaluation of clinical performance and optimize health IT system design. Conclusions: Great expectations are resting upon "Big Data" and innovative analytics. However, to build and maintain public trust, improve data reliability, and assure the validity of analytic inferences, there must be independent and transparent evaluation. A mature and evidence-based approach needs not merely data science, but must be guided by the broader concerns of applied health informatics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.