VCU Biological Complexity

NIH BCIG Event: "Brainstorming: 'Finding What You Want When You Don't Want to Learn How to Find It - Searching Clinical Medical Records Painlessly'"
Thursday, July 1, 2004 * 3:00-4:30pm
NIH Clinical Center (Building 10) Medical Board Room (Room 2C116)

NIH BCIG Event: "Brainstorming: 'Finding What You Want When You Don't Want to Learn How to Find It - Searching Clinical Medical Records Painlessly'"
Facilitator: Mohammad Al-Ubaydli, M.D., NLM

Google changes what users expect to be able to find, and how
they expect to find it. It gives the user the right answer (or at least a
"good enough" answer) most of the time, and no training, syntax, or
understanding is necessary. What would happen if we searched medical
records using Google? And what will happen the day clinicians do start
demanding Google-like search engines in their medical records software?

Mohammad Al-Ubaydli is a doctor and programmer who uses IT to
improve healthcare. He graduated as a doctor with a first-class degree from
Cambridge University. His research project, ImmunoSim, won the Fulton
Roberts Immunology Prize that year. This was the first time that a software
project received the prize. Since then, he has continued to combine his
medical and computing knowledge. He has worked for several institutions and
companies around the UK and the USA. This includes developing the software
for Project Palm at Cambridge University, which allowed medical students to
share their learning using handhelds. In this project, he also provided
teaching, training and technical support to thirty medical students on the
best use of their machines. In 2001, he co-founded Medical Futures, which
launched the Medical Futures Innovation Awards. The awards, now a
much-anticipated annual event, have greatly raised awareness amongst doctors
on the process of using their ideas and inventions to improve healthcare.
The event also raises money for UK hospitals. During his first year of
clinical practice, he was still able to lecture and consult on the use of
handhelds in medicine. He also co-founded Medical Approaches, which
published the world's first peer-reviewed electronic medical text, available
for all handheld platforms. In 2003 he wrote "Handheld Computers for
Doctors", which immediately gained 4/4 stars from the British Medical
Journal and was translated into Spanish in 2004. He is now a Visiting
Research Fellow at the National Centre for Biotechnology Information at the
National Institutes of Health (NIH) in the USA. He is on the Executive
Committees of the UK Health Informatics Society, the Royal Society of
Medicine, the International Journal of Surgery and NIH's Biomedical Enabling
Sciences and Technologies (BEST) Umbrella Group.

More information
Visit the BCIG web site at www.nih-bcig.org.

Please bring your own refreshments.

NIH BCIG Event: "Sample Size Planning for Experiments with High Dimensional Data'"
Thursday, July 8, 2004 * 3:00-4:30pm
NIH Clinical Center Building 40, Room 1201/1203

NIH BCIG Event: "Brainstorming: 'Finding What You Want When You Don't Want to Learn How to Find It - Searching Clinical Medical Records Painlessly'"
Facilitator: Mohammad Al-Ubaydli, M.D., NLM

Sample size planning itself generally does not involve a large
amount of computing, but it has a serious impact on the amount of computing
you need to do in the future. Incorrect sample size can undermine analysis
efforts. Many sample size calculations are based on simple class comparison
sample size formulas. It is important to know at what sample sizes various
analysis techniques are stable, especially for class prediction and
discovery analysis techniques. The sample size needed to make a method
stable and the sample size needed for class comparison can differ by several
fold. Too small of a sample size can lead to spurious results after a large
effort expenditure. Simulations and Monte Carlo methods can only help to a
point. During the tutorial we will go through some of the theory and
formulas traditionally used, the pitfalls of what can occur, what can be
done to help, what information you need to calculate a sample size, and some
examples of calculations and sample size planning.

Laura Lee Johnson graduated with a BA in mathematics from the
University of Virginia and a Ph.D. in biostatistics from the University of
Washington's School of Public Health and Community Medicine. She was a
pre-doctoral trainee at the Northwest Veterans Affairs Health Services
Research and Development Center of Excellence in Seattle and a Presidential
Fellow in the Department of Biostatistics at the University of Washington
where she taught biostatistics to clinical fellows. Currently she is a
Research Fellow helping lead the biostatistics core in the Cancer Prevention
Studies Branch in the Center for Cancer Research at the National Cancer
Institute. Her research interests include analysis of biomarker data,
statistical methodology for non-parametric joint modeling of longitudinal
and survival data, and longitudinal crossover designs.

More information
Visit the BCIG web site at www.nih-bcig.org.

NIH BCIG Event: "Multidisciplinary Research Team (MRT) Event: Systems Learning Organization Team (SLOT) - 'More of 'The Fifth Discipline'"
Thursday, July 8, 2004 * 5:30-7:30pm
NIH Clinical Center (Building 10) Medical Board Room (Room 2C116)

NIH BCIG Event: "Brainstorming: 'Finding What You Want When You Don't Want to Learn How to Find It - Searching Clinical Medical Records Painlessly'"
Facilitator: Mohammad Al-Ubaydli, M.D., NLM

We will continue exploring Peter Senge's "The Fifth
Discipline" with short presentations by Chris Cheadle, Katherine Peterson,
Lynne Oetjen-Gerdes, and Jim DeLeo based on this book and related materials.
The main part of the gathering will be group dialogue about applying Fifth
Discipline insights and related work to effective and productive functioning
of the Biomedical Data Mining, Microarray, and other possible
multidisciplinary Research Teams(MRTs)such as Text Mining, and Proteomics
currently being incubated under BCIG. All are welcome to attend.

Chris Cheadle, Ph.D., NCI

More information
Visit the BCIG web site at www.nih-bcig.org.

NIH BCIG Event: "Featured Presentation: 'Multi-Agent Artificial Intelligent Systems' "
Thursday, July 15, 2004 * 3:00 -4:30pm
NIH Clinical Center (Building 10) Medical Board Room (Room 2C116)

NIH BCIG Event:"Featured Presentation: 'Multi-Agent Artificial Intelligent Systems' "
Speaker: Sean Luke, Ph.D., George Mason University

More information
Visit the BCIG web site at www.nih-bcig.org.

NIH BCIG Event: "Book Club: 'How to Lie with STatistics,' by Darrell Huff"
Thursday, July 22, 2004 * 5:30-7:30pm
NIH Clinical Center (Building 10) Medical Board Room (Room 2C116)

NIH BCIG Event: "Book Club: 'How to Lie with STatistics,' by Darrell Huff"
Facilitator: Mohammad Al-Ubaydli, M.D.