Using Spark NLP to Enable Real World Evidence (RWE) and Clinical Decision Support in Oncology
Using Spark NLP to Enable Real World Evidence (RWE) and Clinical Decision Support in Oncology

Abstract: 

EHRs collect mass amounts of critical patient information but across the healthcare industry, most lack the ability to take meaningful action with this data and put it to its best possible use. RWE can make a difference by helping to determine the best course of treatment, particularly in the complicated field of cancer care. Spark NLP Healthcare modules are specifically designed to unlock this potential of RWE data by applying state-of-the-art clinical NLP algorithms in a secure platform and accurately extract facts from free-text medical reports, which can then be used for a variety of applications like cohort selection, real-world evidence studies, clinical trial recruitment, and others. In this demo, we will demonstrate how we leveraged Spark NLP to analyze longitudinal records of cancer patients, enabling oncologists to see patient data clearly and saving thousands of hours for human-level abstraction.

Bio: 

Veysel Kocaman is a Senior Data Scientist and ML Engineer at John Snow Labs and has a decade long industry experience. He is also pursuing his PhD in CS as well as giving lectures at Leiden University (NL) and holds an MS degree in Operations Research from Penn State University. He is affiliated with Google as a Developer Expert in Machine Learning.