What's in a Note? Unpacking Predictive Value in Clinical Note Representations.

摘要: Electronic Health Records (EHRs) have seen a rapid increase in adoption during the last decade. The narrative prose contained clinical notes is unstructured and unlocking its full potential has proved challenging. Many studies incorporating applied simple information extraction models to build representations that enhance downstream prediction task, such as mortality or readmission. Improved predictive performance suggests "good" representation. However, these extrinsic evaluations are blind most of insight notes. In order better understand power expressive prose, we investigate both intrinsic methods for understanding several common note representations. To ensure replicability support modeling community, run all experiments on publicly-available data provide our code.