Leveraging explainable artificial intelligence to optimize clinical decision support.

Siru LiuAllison B McCoyJosh F PetersonThomas A LaskoDean F Sittig Scott D NelsonJennifer AndrewsLorraine PattersonCheryl M CobbDavid MulherinColleen T MortonAdam Wright

Published in: Journal of the American Medical Informatics Association : JAMIA (2024)

We developed a data-driven process to generate suggestions for improving alert criteria using XAI techniques. Our approach could identify improvements regarding clinical decision support (CDS) that might be overlooked or delayed in manual reviews. It also unveils a secondary purpose for the XAI: to improve quality by discovering scenarios where CDS alerts are not accepted due to workflow, education, or staffing issues.

Keyphrases

clinical decision support
artificial intelligence
quantum dots
electronic health record
machine learning
big data
deep learning
quality improvement
climate change
healthcare
visible light