What question did this study set out to answer?

This viewpoint aims to emphasize the necessity of validating AI-enhanced mammography tools on diverse patient populations and new technologies.

September 9, 2019Open Access

Pathways to breast cancer screening artificial intelligence algorithm validation

CLChristoph I. LeeUniversity of Wisconsin–Madison NHNehmat HoussamiThe University of Sydney JEJoann G. ElmoreUniversity of California, Los Angeles

Key Points

This viewpoint aims to emphasize the necessity of validating AI-enhanced mammography tools on diverse patient populations and new technologies.
Review of previous validations of AI algorithms in mammography screening
Discussion of the importance of continuous monitoring and recalibration of AI tools
Emphasis on stakeholder engagement and development of shared policies.
Highlights the gaps in current validation practices for AI mammography tools.
Identifies the need for a structured framework for ongoing AI tool assessment.
Advocates for collaborative efforts in creating guidelines for AI integration in breast cancer screening.

Abstract

As more artificial intelligence (AI)-enhanced mammography screening tools enter the clinical market, greater focus will be placed on external validation in diverse patient populations. In this viewpoint, we outline lessons learned from prior efforts in this field, the need to validate algorithms on newer screening technologies and diverse patient populations, and conclude by discussing the need for a framework for continuous monitoring and recalibration of these AI tools. Sufficient validation and continuous monitoring of emerging AI tools for breast cancer screening will require greater stakeholder engagement and the creation of shared policies and guidelines.

AIに質問

Bookmark

View Full Paper