In contrast to the structured clinical data typically used for administrative purposes, clinical notes are more nuanced and are primarily used by healthcare providers for detailed documentation. Each patient encounter is associated with several clinical notes.
This poses many challenges for analyzing the free text in these documents. The same holds for notes taken in the mental health domain due to the open domain nature of the context. This presentation will draw parallels between the two healthcare worlds and discuss relevant challenges and recent advances. It will explore solutions to these issues using natural language processing techniques.
Finally, it will discuss the remaining issues in this space and point to future opportunities for novel research directions.