all AI news
A Study into Patient Similarity through Representation Learning from Medical Records. (arXiv:2108.10682v2 [cs.CL] UPDATED)
cs.CL updates on arXiv.org arxiv.org
Patient similarity assessment, which identifies patients similar to a given
patient, can help improve medical care. The assessment can be performed using
Electronic Medical Records (EMRs). Patient similarity measurement requires
converting heterogeneous EMRs into comparable formats to calculate their
distance. While versatile document representation learning methods have been
developed in recent years, it is still unclear how complex EMR data should be
processed to create the most useful patient representations. This study
presents a new data representation method for EMRs …
arxiv learning medical medical records patient records representation representation learning study