Stratifying heart failure patients with graph neural network and transformer using Electronic Health Records to optimize drug response prediction.

Shaika ChowdhuryYongbin ChenPengyang LiSivaraman RajaganapathyAndrew WenXiao MaQiying DaiYue YuSunyang FuXiaoqian JiangZhe HeSunghwan SohnXiaoke LiuSuzette J BielinskiAlanna M ChamberlainJames R CerhanNansu Zong

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

Longitudinal EHR data have the potential to enhance personalized prognostic predictions through the application of graph-based AI techniques.

Keyphrases

electronic health record
neural network
heart failure
adverse drug
clinical decision support
artificial intelligence
left ventricular
cross sectional
atrial fibrillation
human health
cardiac resynchronization therapy
acute heart failure
risk assessment
emergency department
drug induced
machine learning
big data