Prediction of nodal metastasis and prognosis of breast cancer by ANN-based assessment of tumour size and p53, Ki-67 and steroid receptor expression.

BACKGROUND: Tumour stage and the appropriate course of treatment in patients with breast cancer are primarily characterized by the state of metastasis in the axillary lymph nodes. In recent years, substantial research has focused on the prediction of lymph node status based on various pathological and molecular markers in order to obviate the necessity to carry out axillary dissection. In the present study, artificial neural network (ANN) is employed as the analysis platform to examine the prognostic significance of a group of well-established prognostic markers for breast cancer outcome prediction in terms of nodal status. Furthermore, we investigated existing interactions between these markers. PATIENTS AND METHODS: The data set contained 66 patient records, where 5 pathological and molecular markers including tumour size, oestrogen receptor status (ER), progesterone receptor status (PR), Ki-67 and p53 expression had been assessed for each patient. The spread of metastasis to the axillary lymph nodes was clinically diagnosed and patients were accordingly categorized into node-positive and node-negative groups. The aforementioned markers were analyzed using a probabilistic neural network (PNN) for nodal status prediction which was considered as the network output. Furthermore, the interactions between these markers were evaluated using different marker combinations as the network input for finding the best marker arrangement for nodal predication. RESULTS: The best prediction accuracy was obtained by a 3-marker combination including tumour size, PR and p53 with 71% accuracy for nodal prediction. Leaving out ER and PR from the full marker set showed approximately the same variations in the results, which is an indication of the direct correlation of these two markers. Furthermore, tumour size was proved to be the most significant individual marker for predicting nodal metastasis. However, when used in combination with Ki-67 the prediction results drop significantly. CONCLUSION: The results presented here indicate that molecular and pathological markers can provide useful information for early-stage prognosis. However, the interactions between these markers must be considered in order to achieve accurate and reliable prediction.

Applicability of the Bethesda System 2001 to a public health setting.

BACKGROUND: The degree of applicability of the Bethesda System 2001 (TBS 2001) for cervicovaginal cytology to a public health setting is unknown, and extrapolations from available data are unwarranted. METHODS: A "before/after" study design was used to evaluate the impact of TBS 2001 on an organized, population-based screening program in northern Italy. Between 2003-2004, 6 cytology laboratories converted from TBS 1991 to TBS 2001. A set of screening indicators based on TBS 2001 (85,012 patients) were compared with those based on TBS 1991 (199,833 patients) by means of their laboratory- and patient age-standardized ratio with a 95% confidence interval (CI). RESULTS: The prevalence of cervical intraepithelial neoplasm (CIN)2-3/carcinoma was stable between the 2 populations. TBS 2001 had no effect on the unsatisfactory rate (1.99% vs. 2.03% for TBS 1991) nor on follow-up compliance rate (93.2% vs. 92.3%). The reporting rate of atypical squamous cells (ASC) decreased from 17.1 to 14.7 per 1000 (ratio, 0.86; 95% CI, 0.81-0.91), the total positivity rate from 31.1 to 29.0 per 1000 (ratio, 0.93; 95% CI, 0.90-0.97), and the ASC:SIL (squamous intraepithelial lesion) ratio from 1.38 to 1.16. Compared with the ASCUS (ASC of undetermined significance) reports of TBS 1991, the predictive value for CIN2-3/carcinoma decreased from 5.2 to 3.5% (ratio, 0.68; 95% CI, 0.48-0.93) among ASCUS reports, but increased from 5.1 to 17.2% (ratio, 3.41; 95% CI, 1.64-6.28) among ASC-cannot exclude high grade lesion (ASC-H) reports. ASC-H had a 5.01-fold (95% CI, 2.23-10.2) greater predictive value than ASCUS. CONCLUSIONS: TBS 2001 is applicable to cervical screening in a public health setting.