Toward Global Validation Standards for Health AI
Markus Wenzel, Thomas Wiegand
Abstract
Machine learning (ML) and artificial intelligence (AI) methods hold great potential for healthcare, for example, for purposes of diagnosis or prognosis that include a wide range of pattern recognition tasks. Ensuring that health ML/AI models are trustworthy will consequently become increasingly important soon. The ITU/WHO focus group on "AI for Health" is working on validation standards for health AI that can help to assess the quality of the powerful but complex technologies in a comparable and transparent manner. In particular, standardized benchmarking can serve as a valuable tool to determine the merits and limits of different health ML/AI models. In this article, ongoing work of the ITU/WHO initiative is introduced and set into perspective with related digital health and AI standardization efforts.