WASHINGTON (WUSA9) -- Can doctors tell you the likelihood that you'll survive breast cancer? Although not ready to be used by doctors, there is now a computer model proven to be highly predictive.
Columbia Engineering researchers created a computational model for the Sage Bionetworks/ DREAM Breast Cancer Prognosis Challenge. The team won the contest and had their work published in Science Translational Medicine.
The study used gene signatures called "attractor metagenes," which can be found in many different types of cancers, to create a computer model. The team found a strong predictor of breast cancer survival when these cancer signatures were combined.
"These signatures manifest themselves in specific genes that are turned on together in the tissues of some patients in many different cancer types," says Dimitris Anastassiou, lead researcher and Charles Batchelor Professor in Electrical Engineering and member of the Columbia Initiative in Systems Biology.
"And if these general cancer signatures are useful in breast cancer, as we proved in this challenge, then why not in other types of cancer as well? I think that the most significant - and exciting - implication of our work is the hope that these signatures can be used for improved diagnostic, prognostic, and eventually, therapeutic products, applicable to multiple cancers," Anastassiou says.
The study used genetic and clinical data from over 1,000 women with breast cancer. Then, they tested their model on 184 women diagnosed with breast cancer and found their model was the best predictor in the challenge.