PREDICTION OF NODAL METASTASIS AND PROGNOSIS IN BREAST-CANCER - A NEURAL MODEL

Background. An increasing number of women with breast cancer are detec ted with the disease at an early stage, when the lymph nodes are not i nvolved. In or der to obviate the necessity to carry out axillary diss ection, accurate surrogates fbr lymph node involvement need to be iden tified. In this paper we have examined the use of a neural network to predict nodal involvement. The neural approach has also been extended to investigate its predictive applicability to the long-term prognosis of patients with breast cancer. A number of established and experimen tal prognostic markets have been studied in an attempt to accurately p redict patient outcome 72 months after first examination. Methods. 81, unselected patients, presenting clinically, who had all undergone mas tectomy for invasive breast carcinoma were considered in this study. A total of 12 markers were analysed for the prediction of lymph node me tastasis, while node status itself was used as an additional marker fo r the prognostic analysis. In this case the outcome related to whether a patient had relapsed within 72 months of diagnosis. In both cases, a number of marker combinations were analysed separately in an attempt to classify, those most favourable marker interactions with respect t o lymph node prediction and prognosis. Patients were randomly divided into a training set (n = 50) and a test set (n = 31). The simulation w as developed using the NeualWorks Professional II/Plus software (Neura lWare, Pittsburgh, Pa, USA). Results. In the case of lymph node metast asis, the neural network was able to correctly predict axillary involv ement, or otherwise, in 84% of the patients in the test set by conside ring 9 of the 12 available markers. This represents an improvement of 10% over the traditional approach which considers the tumour grade and size only. The sensitivity and specificity were also shown to be 73% and 90%, respectively. With regard to patient prognosis, again 84% cla ssification accuracy was obtained using a subset of the markers, with a sensitivity of 50% and a specificity of 96%. Conclusions. Although t his study considered a relatively small sample of patients, neverthele ss it demonstrates that artificial neural networks are capable of prov iding strong indicators for predicting lymph node involvement. There i s no longer a need for axillary dissection with all its implications i n patient morbidity and demands on clinical resources. The management of breast cancel and the planning of strategies for adjuvant treatment s is also facilitated by the use of neural networks for the long-term prognosis of patients.