Simple tool effectively helps classify breast cancer into subtypes
Based on the findings of past studies which have shown that breast cancer is composed of several molecular subtypes, Benjamin Haibe-Kains, MD, from the Dana-Farber Cancer Institute, and colleagues sought to develop a tool for classifying these subtypes.
For the study, researchers analyzed 32 publicly available gene expression data sets, including more than 4600 breast cancer patients and six different classification models.
According to background information provided by the authors, the Single Sample Predictor (SSP) and the Sub-type Classification Model (SCM) are two main classes of classification models that have been published during the last decade.
“We studied these models in terms of concordance and prognostic value and, for the first time, we estimated their robustness: that is, their capacity to assign the same tumors to the same molecular sub-types whatever the gene expression data used to fit this model,” the author noted.
Researchers found that SCMs produced stronger concordance than SSPs. More significant, the study found that even the simplest SCM model that only uses three genes was significantly more robust than SSPs.
“By demonstrating the robustness of the SCM models, the new study is a significant step towards brining these classification models into the clinic,” said Dr. Haibe-Kains. “The robustness of SCMs makes them promising candidates for an implementation into the clinic especially in the simplest form -- that is, a model using only three genes.”