A significant portion of biomedical “big data” is unstructured or free flowing natural language text data such as data in clinical or patient notes, medical records, or items such as Pathology reports. The value from such unstructured data can be derived only from a structured representation of the data, and often the structuring and synthesis requirements are specific and sophisticated.
In this talk, I will describe work in building systems for unstructured data understanding in the biomedical and health domains including 1) a pipeline for structuring of Pathology reports, 2) mining insights from patient conversations on condition specific online forums, and 3) understanding patient notes. I will describe the technical details of building text understanding solutions employing technologies from machine-learning, NLP, and semantics to address these problems. We will also discuss active-learning approaches to alleviate the training effort in configuring such systems.
About our Speaker
Dr. Naveen Ashish is an Associate Professor in Informatics at the USC Medical School. He also advises multiple start-up companies, particularly in the area of text analytics. His areas of expertise include text analytics, machine-learning, data management, semantics and biomedical and health informatics. He has authored two books and close to 100 papers in these areas. He holds a PhD in Computer Science from the University of Southern California, and a BTech, also in Computer Science, from IIT Kanpur (India).
About our Sponsor
Galvanize is the premiere dynamic learning community for technology. With campuses located in booming technology sectors throughout the country, Galvanize provides a community for each the following:
To learn more about Galvanize, visit galvanize.com.