This session shows how Python’s NLU library enables you to leverage hundreds of healthcare-specific, state-of-the-art models in one line of code.

This includes the full set of Spark NLP for Healthcare capabilities including Clinical & Biomedical Named Entity Recognition (NER), Entity Linking into medical terminologies (like ICD-10, RxNORM, SNOMED-CT, LOINC, CPT, HPO, etc.), Relation Extraction (for posology, adverse drug events, temporal features, body parts, etc.), Assertion Status Detection, De-Identification, and others.

Interactive visualization capabilities using pre-built Streamlit apps are also available, which can be used to visualize model predictions and test them out with 0 lines of code, directly in your web browser.