 |
|
|
|
Web Site Provides New Tool in the War Against Prostate Cancer
DENVER, CO, October 22, 2002. A new online calculator now helps to forecast the medical future of the many men -- 40,000 a year in the U.S. alone -- who undergo a radical prostatectomy to treat localized prostate cancer. The calculator, available at www.prostatecalculator.org, predicts the likelihood of a man's level of serum prostate-specific antigen (PSA) remaining low seven years after his prostate gland was removed. Currently 30 to 40 percent of treated men experience an increase in their PSA level, which may be a sign of prostate cancer recurrence, within 5 to 10 years of the surgery.
To use the calculator, visitors to the web site -- patients with localized prostate cancer or their doctors -- simply enter the relevant information: pre-operative PSA level, either preoperative or post-operative cancer stage and biopsy or pathologic Gleason score. No personal information is collected and patient privacy is respected. Once the data has been entered, one mouse-click provides the prognosis. The site also provides access to informative cancer-related articles and illustrations, but does not promote particular doctors or medical treatments.
Dr. Ashutosh Tewari, with the Josephine Ford Cancer Center in Detroit, Mich., and primary author of the multi-institutional, multi-year study on which the calculator is based, believes that the new calculator and new research will help doctors and patients make more informed medical decisions. Tewari feels that patients deserve to have access to objective data regarding the possibility of disease recurrence. He also understands that they need guidance in estimating that risk.
The new calculator, a result of Dr. Tewari's study and the work of investigators at the ANNs in CaP Project (see below), is based on a modeling technique called "proportional hazards regression analysis." This technique looks at factors that influenced PSA recurrence in men who underwent a radical prostatectomy to treat their localized prostate cancer. Dr. Tewari's study gathered readily available clinical and histologic information from 2,065 men with localized prostate cancer who underwent a radical prostatectomy between 1988 and 2000. The calculator bases its probability estimates on patients who had similar characteristics to the new patient.
Those probability estimates are the most accurate to date -- but they still are not perfect. "The accuracy is more than 70 percent, which means the prediction may not be absolutely accurate for approximately 30 percent of users," says Dr. Tewari. He also cautions that, while the calculator is available to anyone with a Web browser, it is not intended to replace doctors. The complex computer program it uses provides a new and greatly improved way of predicting prostate cancer recurrence. But physicians, Tewari emphasizes, "are the cornerstone of medical practice."
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, Colo., this research collaborative is headed by leading prostate-cancer expert Dr. E. David Crawford and funded by the Institute for Clinical Research at the Veterans Affairs Medical Center 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 is located at www.annsincap.org.
|
|
|
|
|
