Healthcare and Life Sciences Workshop: Extract Real-World Data with NLP
Learn how to generate novel patient insights with natural language processing solutions from John Snow Labs and Databricks
HIMSS estimates that the U.S. healthcare industry produces over a billion clinical documents every year. Contained within these unstructured documents and PDF reports is important patient information — for example, patient symptoms that can be signals of deteriorating status or disease. Unlocking these insights requires natural language processing (NLP) tools tailored for the healthcare industry along with a modern scalable platform for data, analytics and AI. Join this virtual workshop to learn how to extract patient insights buried in clinical text with NLP solutions from Databricks and John Snow Labs Inc., a leader in Healthcare AI and the creator of SparkNLP. Specifically, we’ll showcase how to use NLP to automate the removal of sensitive PHI and generate real-world evidence from oncology reports.
In this workshop, you will:
- Learn how to modernize your analytics with a simple, open and collaborative platform for data, analytics and AI
- Gain deeper insights into Delta Lake and the Health Lakehouse architecture
- Learn about new healthcare NLP solutions from John Snow Labs and Databricks
- Train an NLP model to generate real-world evidence from pathology reports
- Learn how to use NLP to automate data de-identification and obfuscation
Event Agenda (Pacific Time)
- 9:00–9:15 AM PT Modernizing Analytics With a Health Lakehouse
- 9:15–9:30 AM PT Healthcare NLP at Scale With John Snow Labs and Databricks
- 9:30–9:45 AM PT Break and Prep for Hands-On Workshop
- 9:45–10:15 AM PT Technical Workshop Part 1: Extracting Text Data for Oncology
- 10:15–10:45 AM PT Technical Workshop Part 2: Automating PHI De-Identification
- 10:45-11:00 AM PT Q&A
Watch On Demand!

