DENVER, CO, September 24, 2001. A new web site can now forecast the
medical future for men with prostate disease. The site,
prostatecalculator.org, uses online calculators and a kind of
artificial intelligence, called artificial neural networks (ANNs), to
address various prostate cancer-related conditions. The calculators
"learn" and make prognoses by comparing each patient's
characteristics with a database of information from hundreds or
thousands of other patients.
A visitor to the web site -- a patient or doctor -- begins by
entering the relevant information, such as patient age and tumor
stage, into one of the easy-to-use calculators. Moments later, the
calculator provides a prognosis: the overall likelihood of the
patient's survival in the coming years, the chance of the cancer
spreading beyond the man's prostate, or the chance that the cancer
will recur after surgical treatment. Visitors also have access to
informative cancer-related articles and illustrations, and their
privacy is respected. The site does not collect personal information.
While the web site uses ANNs -- the first to do so -- for the
diagnosis, prognosis, and treatment of prostate cancer, according to
project director Dr. E. David Crawford, it is meant to complement
doctors, not substitute for them. Says Crawford, "Neural networks are
not intended to replace doctors, and never could. They're like CT
scans and other diagnostic tests that help physicians care for their
patients. Since no one test is perfect, predictions must be
incorporated with other data to make informed treatment decisions."
According to Crawford, neural networks are an exciting new medical
field. "Our collaboration with researchers across the globe is
enabling us to use increasingly larger data sets that in turn improve
our models' accuracy and render them more useful. We are currently
developing models that will help us predict which treatment option
will be best for a particular patient and designing a system that
will identify cancer using ultrasound images. Our research is focused
on creating superior tools for doctors' use."
Crawford continues, "The accuracy of new techniques such as
artificial intelligence is under close scrutiny by the medical
community. Our results are thoroughly analyzed using time-proven
statistical techniques and then published in peer-reviewed medical
journals. We also continuously validate our models as new data
becomes available. We believe our work has great potential to benefit
patients everywhere."
About Artificial Neural Networks
Artificial neural networks are a form of artificial intelligence that
simulates the functioning of the human brain to solve problems. ANNs
have been used in engineering, meteorology, and, now, in medicine.
Several studies have been conducted that suggest that ANNs can
supplement traditional statistical methods that are currently in use.
About ANNs in CaP
The prostatecalculator.org web site was produced by the
Artificial Neural Networks in Prostate Cancer (ANNs in CaP) Project.
Based in Denver, this research collaboration is headed by leading
prostate-cancer expert Dr. E. David Crawford and funded by the
Institute for Clinical Research in Washington, DC. Under the guidance
of Dr. Crawford, national and international authorities in the fields
of prostate cancer and artificial intelligence are working together
to investigate the use of ANNs in the diagnosis, prognosis, and
treatment of prostate cancer. The project web site can be found at
www.annsincap.org.
