PROGNOSTIC FACTORS FOR METACHRONOUS CONTRALATERAL BREAST-CANCER - A COMPARISON OF THE LINEAR COX REGRESSION-MODEL AND ITS ARTIFICIAL NEURAL-NETWORK EXTENSION

The purpose of the present study was to assess prognostic factors for metachronous contralateral recurrence of breast cancer (CBC). Two fact ors were of particular interest, namely estrogen (ER) and progesterone (PgR) receptors assayed with the biochemical method in primary tumor tissue. Information was obtained from a prospective clinical database for 1763 axillary node-negative women who had received curative surger y, mostly of the conservative type, and followed-up for a median of 82 months. The analysis was performed based on both a standard (linear) Cox model and an artificial neural network (ANN) extension of this mod el proposed by Faraggi and Simon [9]. Furthermore, to assess the progn ostic importance of the factors considered, model predictive ability w as computed. In agreement with already published studies, the results of our analysis confirmed the prognostic role of age at surgery, histo logy, and primary tumor site, in that young patients (less than or equ al to 45 years) with tumors of lobular histology or located at inner/c entral mammary quadrants were at greater risk of developing CBC. ER an d PgR were also shown to have a prognostic role. Their effect, however , was not simple in relation to the presence of interactions between E R and age, and between PgR and histology. In fact, ER appeared to play a protective role in young patients, whereas the opposite was true in older women. Higher levels of PgR implied a greater hazard of CBC occ urrence in infiltrating duct carcinoma or tumors with an associated ex tensive intraductal component, and a lower hazard in infiltrating lobu lar carcinoma or other histotypes. In spite of the above findings, the predictive value of both the standard and ANN Cox models was relative ly low thus suggesting an intrinsic limitation of the prognostic varia bles considered, rather than their suboptimal modeling. Research for b etter prognostic variables should therefore continue.