From Clinical Language Representation to Patient Representation using Electronic Health Records
Webinar
The widespread adoption of Electronic Health Records (EHRs) has enabled the use of clinical data for clinical research and practice. Since a significant portion of relevant patient information is embedded in clinical narratives, natural language processing (NLP) techniques such as information extraction have become critical for using EHRs in clinical research. Meanwhile, encoding entire EHR data in a patient representation has shown promising results in predictive modeling, and could help clinical decision making and facilitate translational research. This talk will feature clinical NLP methodologies and applications, and discuss why learning better representations from EHRs is crucial for clinical and translational research.