Computer System "Trained" to Evaluate Breast Cancer Cases

A computer system has been "trained" to predict the outcome of breast cancer cases, and thereby help doctors make decisions on the best course of treatment, according to researchers at the University of Newcastle upon Tyne in England.

In the study of 100 women, the computer system correctly predicted in almost nine out of ten cases whether the breast cancer would spread and whether the women would survive for five years without a recurrence of their cancer, researchers reported in New Scientist magazine.

The system was trained to analyze images of cells from breast cancer biopsy samples for patterns of abnormality that could be used to predict the outcome of the disease. The computer was then programmed to measure four "indicators" of how aggressive the cancer might be. That information was fed into the system to spot specific patterns and then was subjected to fuzzy logic, which 'weights' the data to make it fit the patterns as closely as possible.

Tissue samples from 50 breast cancer patients were used to calibrate the system, along with data about the outcome of the cases, such as recurrence of the cancer and the five-year survival rate.

Data from another 50 cases was then fed into the computer, which was asked to predict which of the women would develop tumors in their lymph glands. The computer's feedback was 88 percent accurate in that analysis as well as in analyzing the patients' five-year survival rate.

"The results are promising but they would need to be confirmed by full-scale trials before the technique could be introduced into hospitals," said Dr. Gajanan Sherbet, professor at the Institute of Molecular Medicine in California and co-author of the study.

Researchers are hopeful that this computer system will one day save lives by helping physicians decide at an early stage which patient should have intensive treatment.

Other sources: University of Newcastle upon Tyne