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.
Adult ; Aged ; Aged, 80 and over ; Breast Neoplasms/*diagnosis/*epidemiology ; Diagnosis, Computer-Assisted/*methods ; Early Detection of Cancer/*methods ; Female ; Humans ; *Machine Learning ; Middle Aged ; Pattern Recognition, Automated/methods ; Prevalence ; Reproducibility of Results ; Republic of Korea/epidemiology ; Risk Assessment/methods ; Risk Factors ; Sensitivity and Specificity ; Women's Health/*statistics & numerical data

PURPOSE: We aimed to investigate organ-specific recurrence or the metastatic pattern of breast cancer according to biological subtypes and clinical characteristics. METHODS: We retrospectively analyzed the medical records of 168 patients with recurrent breast cancer who were diagnosed between January 1, 2000 and April 30, 2017. Four biological subtypes were classified according to estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and Ki-67 expression: luminal A, luminal B, HER2-enriched, and triple negative breast cancer (TNBC). To analyze recurrence patterns according to biological subtypes, we accessed clinical variables including age at diagnosis, TNM stage, type of surgery in the breast and axilla, histologic grade, nuclear grade, lymphatic, vascular, and neural invasion, Ki-67 expression and recurrence to distant organs. RESULTS: The biological subtypes of recurrent breast cancer comprised the following luminal A (n=33, 19.6%), luminal B (n=95, 56.5%), HER2 enriched (n=19, 11.3%), and TNBC (n=21, 12.5%). Luminal A (7.7%) and B (6.5%) subtypes were associated with the increased rate of local recurrence compared to HER2-enriched (2.4%) and TNBC subtypes (1.8%) (p=0.005). The bone (53.6%) was the most common metastatic organ, followed by the lung (34.5%), liver (29.8%), brain (17.9%), and other visceral organ (7.7%). Bone metastasis was commonly observed in individuals with luminal B (63.2%), HER2-enriched (57.9%), and luminal A (42.4%) subtypes (p=0.005). Most liver metastases occur in individuals with luminal B (40.0%) and HER2-enriched subtypes (31.6%) (p=0.002). CONCLUSION: Luminal B subtype was commonly observed in individuals with recurrent breast cancer, and the bone is the most common target organ for breast cancer metastasis, followed by the lungs and liver.
Axilla ; Brain ; Breast Neoplasms ; Breast ; Diagnosis ; Estrogens ; Humans ; Liver ; Lung ; Medical Records ; Neoplasm Metastasis ; Organ Specificity ; Phenobarbital ; Receptor, Epidermal Growth Factor ; Receptors, Progesterone ; Recurrence ; Retrospective Studies ; Triple Negative Breast Neoplasms