Cautious Artificial Intelligence Improves Outcomes and Trust by Flagging Outlier Cases.

Abhiraj S Kanse Nikhil C KurianHimanshu P AswaniZakia KhanPeter H Gann Swapnil U Rane Amit Sethi

Published in: JCO clinical cancer informatics (2022)

The ability to flag outlier test cases need not be at odds with the ability to accurately classify nonoutliers in AI models. Although the latter capability has received research and regulatory attention, AI models for clinical deployment should possess the former as well.

Keyphrases

artificial intelligence
machine learning
big data
deep learning
working memory
transcription factor
health information
healthcare
adipose tissue
weight loss
insulin resistance