Applications of Real-Time Streaming Computing and Machine Learning in Intensive Care Units: Dr. Sharath Cholleti, Emory
- Starts: 11:00 am on Wednesday, July 24, 2013
- Ends: 12:00 pm on Wednesday, July 24, 2013
Description:
Patients in intensive care units (ICU) are continuously monitored for
their critical illness or post-surgery complications. Variety of
sensors measure patients’ physiology and generate high velocity and
high volume streaming data. Part of the raw data and some calculated
metrics are displayed on computer monitors for the clinicians to
observe current state of the patients. Progress in critical care
monitoring has been slow due to technical, clinical, financial, and
regulatory reasons. Meanwhile tremendous progress has been in made in
the fields of machine learning, stream computing, and data
visualization in the past decade along with middleware to interface
with proprietary ICU monitoring systems and electronic health record
systems in real time. In this talk, I will discuss how above
technologies are being applied to create the next generation ICU
monitoring with numerous algorithms to keep track of large number of
patients 24/7 to detect and predict adverse trends and events while
improving patient care and reducing costs.
Bio:
Dr. Sharath Cholleti is a Senior Research Scientist at the Center for
Comprehensive Informatics at Emory University. He received his Ph.D.
and M.S. in Computer Science from Washington University in St. Louis,
and B.Tech. in Computer Science and Engineering from Indian Institute
of Technology, Guwahati, India.
His research interests are in machine learning, data mining, and their
applications to medicine. He developed machine learning algorithms and
applications for variety of medical software involving pathology
images, radiology images, glycomics data, and clinical data from
electronic health records and intensive care units. His current work
involves development of predictive modeling software for 30-day
hospital readmission, and development of real-time analytics and
visualization system for intensive care units
- Location:
- MCS 148