Computational Discrimination of Breast Cancer for Korean Women Based on Epidemiologic Data Only

Abstract

Breast cancer is the second leading cancer for Korean women and its incidence rate has been increasing annually. If early diagnosis were implemented with epidemiologic data, the women could easily assess breast cancer risk using internet. National Cancer Institute in the United States has released a Web-based Breast Cancer Risk Assessment Tool based on Gail model. However, it is inapplicable directly to Korean women since breast cancer risk is dependent on race. Also, it shows low accuracy (58%-59%). In this study, breast cancer discrimination models for Korean women are developed using only epidemiological case-control data (n = 4,574). The models are configured by different classification techniques: support vector machine, artificial neural network, and Bayesian network. A 1,000-time repeated random sub-sampling validation is performed for diverse parameter conditions, respectively. The performance is evaluated and compared as an area under the receiver operating characteristic curve (AUC). According to age group and classification techniques, AUC, accuracy, sensitivity, specificity, and calculation time of all models were calculated and compared. Although the support vector machine took the longest calculation time, the highest classification performance has been achieved in the case of women older than 50 yr (AUC = 64%). The proposed model is dependent on demographic characteristics, reproductive factors, and lifestyle habits without using any clinical or genetic test. It is expected that the model could be implemented as a web-based discrimination tool for breast cancer. This tool can encourage potential breast cancer prone women to go the hospital for diagnostic tests.

Keywords: Breast Neoplasms; Computers; Neural Networks; Support Vector Machines.

Fig. 1. Incidence rates of breast cancer (in 2008): Korean women vs white women in the USA (1415).

Fig. 2. Artificial neural network (ANN) structure. AFFP, age of first full-term pregnancy; NOC, number of children; AOMn, age of menarche; BMI, body mass index; FMH, family medical history of breast cancer; MS, menopausal status; RM, regular mammography; RE, regular exercise; ED, estrogen duration.

Fig. 3. Naive structure of a Bayesian network (BN).

Fig. 4. Receiver operating characteristic (ROC) curves according to the classification algorithms and age division models. (A) Support Vector Machine (SVM). (B) Artificial Neural Network (ANN). (C) Bayesian Network (BN).

Fig. 5. Contribution of a specific risk factor on the area under curve (AUC). AFFP, age of first full-term pregnancy; NOC, number of children; AOMn, age of menarche; BMI, body mass index; FMH, family medical history of breast cancer; MS, menopausal status; RM, regular mammography; RE, regular exercise; ED, estrogen duration; SVM, support vector machine; ANN, artificial neural network, BN, Bayesian network; U50, under 50 yr old group; O50, equal to or over 50 yr old group.