| Sun 25 Nov. |
- Speaker:
David Duke
- Title:
Intelligent Diabetes Assistant: Predicting and Optimizing Blood Glucose
- Time:
14:00 (11/25/2007)
- Location:
Qatar University,
men's campus Room 180 Corridor 9,
- Abstract:
-
In the United States there are approximately 20 million diabetics which is
an incidence rate of approximately 6%. In Qatar the incidence rate is
approximately 15%. In the US the disease and its related complications are
the 6th leading cause of death, but with proper management the risks of
complications can be substantially reduced. However many diabetics have
problems managing the disease on their own. An intelligent diabetes
assistant (IDA) has the potential to improve the health of many diabetics.
IDA could help such individuals by simplifying data collection, improving
the quality of the data, automating the data analysis, and sharing data
between patient and physician. The fundamental requirement of such an
assistant is to predict the impact of behavior on blood glucose levels as
an aid to therapy. To reach this goal we are collaborating with Hamad
Medical Center, and together have collected data from 9 diabetics.
Initial results and observations will be presented.
- Speaker's Bio:
-
David Duke received his Bachelors degree in Physics and Mathematics from
Harding University in Searcy, Arkansas in 2000. After graduating he spent
a year teaching at Chepkong'ony Secondary School in Kaptagat, Kenya before
enrolling as a PhD student in the Robotics Institute at Carnegie
Mellon. David has worked at NASA's Goddard Space Flight Center, Jet
Propulsion Laboratory, and on Sandstorm, Carnegie Mellon's robotic vehicle
in the original DARPA Grand Challenge. His current research interests are
in applying machine learning and robotic technology to help patients and
physicians work together to manage diabetes.
|
| Sun 4 Nov. |
- Speaker:
Uvais Qidwai
- Title:
Fuzzy classifier for failed back surgery syndrome
- Time:
9:00 (04/11/2007)
- Location:
Carnegie Mellon University,
LAS building, Lecture Hall B
- Abstract:
-
In this seminar a Fuzzy Inference System (FIS) will be presented that was
designed to predict the level of Risk for a class of patients to be
needing a repeated surgery for the herniated lumber disc (or more commonly
known as slipped disc). The FIS is based upon a clinical study that was
conducted by a number of doctors at Aga Khan University Hospital in
Pakistan with the objective that certain clinical measures can be used
from the beginning to assist the physician in making a better risk
estimate for the patient at hand. As such, over 90 clinical markers were
collected through patients' surveys over a period of 5 years
(2000-2004). The presented study utilizes a subset of 16 markers and has
recommendation for 7 of these markers for a reasonably accurate risk
prediction. A set of 11 rules has been established that constitute the
mapped understanding from the physicians' heuristics into logical decision
surfaces. Such a system will be a very helpful tool for medical
professionals for making quick risk assessment for a patient and will
enable them to more accurately define the treatment for the same.
- Speaker's Bio:
-
Uvais Qidwai received his Ph.D. from University of Massachusetts-Dartmouth
in 2001 from the Electrical and Computer Engineering Department. He worked
at the Electrical Engineering and Computer Science Department at Tulane
University in New Orleans, USA as Assistant Professor, and in-charge of
the Robotics lab from June 2001 till June 2005. He joined the Computer
Science and Engineering Department at Qatar University in Fall 2005 as
Assistant Professor. His present interests in research include Image
Enhancement & understanding for Machine Vision applications, Fuzzy
computations, Signal Processing and Interfacing, Expert System for testing
pipelines, and intelligent algorithms for Medical Informatics. He has
participated in several Government and Industry funded projects in USA,
Saudi Arabia, and Pakistan and has published over 50 papers in reputable
Journals and Conferences.
|