Effect of patient history data on the prediction of breast cancer from mammographic findings with artificial neural networks

Rationale and Objectives. The authors evaluated the contribution of medical history data to the prediction of breast cancer with artificial neural net work (ANN) models based on mammographic findings. Materials and Methods. Three ANNs were developed: first used 10 Breast Imag ing Reporting and Data System (BI-RADS) variables; the second, the BI-RADS variables plus patient age; the third, the BI-RADS variables,patient age. a nd seven other history variables, for a total of 18 inputs. Performance of the ANNs and the original radiologist's impression were evaluated with ve m etrics: receiver operating characteristic area index; (Az) specificity at g iven sensitivities of 100%, 98%, and 95%; and positive predictive value. Results. All three ANNs consistently outperformed the radiologist's impress ion over all five performance metrics. The patient-age variable was particu larly valuable. Adding the age variable to the basic ANN model, which used only the BI-RADS findings, significantly improved Az (P =.028). In fact, re placing all history data with just the age variable resulted in virtually n o changes for Az or specificity at 98% sensitivity (P =.324 and P = .410, r espectively). Conclusion. Patient age was an important variable for the prediction of bre ast cancer from mammographic findings with the ANNs, For this data set, all history data could br replaced with age alone.