Patient risk information improves mammogram interpretation

the Oncology Nurse Advisor take:

A research group’s findings demonstrate a role for risk profiling in the interpretation of mammograms. The new approach takes into account a woman’s health risk profile, which may reduce both the number of missed cancers and false positives. Although some controversy exists about whether profile information produces bias in mammography interpretation, the researchers consider whether this bias actually helps make readings more accurate. Using a decision science technique called linear opinion pooling, the researchers analyze the decision performance of three groups: a mammogram-only reading with no risk profile information; an unbiased reading in which radiologists consult the risk profile after reading the mammogram; and “influenced” readings in which radiologists consult a woman’s risk profile as they examine the mammogram. Numerical analysis using a clinical dataset from the Breast Cancer Surveillance Consortium revealed that using profile information could reduce the false positives and the number of missed cancers compared with cases in which no profile information was reviewed.