Basser Seminar Series

ANALYSIS OF PHYSIOLOGICAL SIGNALS

Speaker: Professor John Guttag
Computer Science and Artificial Intelligence Laboratory, MIT

Time: Thursday 24 March 2011, 4:00-5:00pm **Please note different day to usual
Refreshments will be available from 3:30pm

Location: The University of Sydney, School of IT Building, Lecture Theatre (Room 123), Level 1

Add seminar to my diary

Abstract

Electrical signals emanating from the human body carry information than can be used to predict and detect adverse events. This talk will cover some ways in which our research group has used techniques drawn from signal processing, machine learning, and data mining to analyze electrical signals emanating from the brain (EEG) and from the heart (ECG).

People with epilepsy suffer from recurrent seizures that occur at unpredictable times and usually without warning. The unpredictability of seizures all too frequently leads to serious injuries and even death. A device capable of quickly detecting and reacting to a seizure by delivering therapy or notifying a caregiver could ease the burden of seizures for patients and families. This talk will present our work on building patient-specific seizure detectors, an evaluation of our detectors against other state-of-the-art techniques, and our approach to translating these results into clinical applications.

Approximately 1.5 million Americans have an acute coronary syndrome (ACS) each year. Between 15% and 20% of these people will suffer cardiac-related death within four years. There are many post-ACS treatment options, and the choice of treatment is based on an assessment of future risk. This talk will present several novel approaches to ECG-based cardiovascular risk stratification. It will include a comparison to other methods using retrospective data from roughly 5,000 post-ACS patients.

Speaker's biography

John Guttag is the Dugald C. Jackson Professor of Computer Science and Electrical Engineering at MIT. He leads the Computer Science and Artificial Intelligence Laboratory’s Data-driven Medical Research Group. This group applies advanced data networking, signal processing, machine learning, and data mining techniques to develop software-based medical instrumentation and decision systems. Current research projects include mobile telemedicine, prediction of nosocomial infections, detection and amelioration of epileptic seizures, and risk stratification of cardiac patients. Professor Guttag has also done research in the areas of software-defined radios, data networking, software engineering, mechanical theorem proving, and hardware verification.

From 1999 to 2004, Professor Guttag served as Head of MIT’s Electrical Engineering and Computer Science Department. Prior to that he spent five years as the Associate Department Head from Computer Science. He is a Fellow of the ACM and a member of the American Academy of Arts and Sciences.