Development of Novel Breast Cancer Recurrence Prediction Model Using Support Vector Machine

Abstract

PurposeThe prediction of breast cancer recurrence is a crucial factor for successful treatment and follow-up planning. The principal objective of this study was to construct a novel prognostic model based on support vector machine (SVM) for the prediction of breast cancer recurrence within 5 years after breast cancer surgery in the Korean population, and to compare the predictive performance of the model with the previously established models.MethodsData on 679 patients, who underwent breast cancer surgery between 1994 and 2002, were collected retrospectively from a Korean tertiary teaching hospital. The following variables were selected as independent variables for the prognostic model, by using the established medical knowledge and univariate analysis: histological grade, tumor size, number of metastatic lymph node, estrogen receptor, lymphovascular invasion, local invasion of tumor, and number of tumors. Three prediction algorithms, with each using SVM, artificial neural network and Cox-proportional hazard regression model, were constructed and compared with one another. The resultant and most effective model based on SVM was compared with previously established prognostic models, which included Adjuvant! Online, Nottingham prognostic index (NPI), and St. Gallen guidelines.ResultsThe SVM-based prediction model, named 'breast cancer recurrence prediction based on SVM (BCRSVM),' proposed herein outperformed other prognostic models (area under the curve=0.85, 0.71, 0.70, respectively for the BCRSVM, Adjuvant! Online, and NPI). The BCRSVM evidenced substantially high sensitivity (0.89), specificity (0.73), positive predictive values (0.75), and negative predictive values (0.89).ConclusionAs the selected prognostic factors can be easily obtained in clinical practice, the proposed model might prove useful in the prediction of breast cancer recurrence. The prediction model is freely available in the website (http://ami.ajou.ac.kr/bcr/).

A Hybrid Computer-aided-diagnosis System for Prediction of Breast Cancer Recurrence (HPBCR) Using Optimized Ensemble Learning

“…The NPI calculation equation is as follows: tumor size (cm) × 0.2 + histological grade + lymph node point (negative nodes = 1; 1–3 positive nodes = 2; ≥ 4 positive nodes = 3). The patients were then classified into the low-risk (NPI point < 3.4) and high-risk groups (NPI point ≥ 3.4) [27], [28].…”

“…Kim et al [28] used normalized mutual information index for feature selection and supported vector machines (SVM), Cox-proportional hazard regression model, and artificial neural network classifiers for classification in a sample size of 679 patients (the recurrence prevalence of 28.6%). The following features were used in their prognosis system: local invasion of tumor, number of tumors, number of metastatic lymph nodes, the histological grade, tumor size, estrogen receptor, and lymphovascular invasion and reached the sensitivity, specificity and area under the curve of 89%, 73% and 0.85, respectively for the best classifier (SVM).…”

“…In fact, having metastasis was one of the attributes primarily used by their proposed system. This necessary exclusion has been implemented in similar studies [28], [30]. The reason for such an exclusion is that the survival rate of patients with stage IV (metastasis) breast cancer within 5 years is about 10% to 15%.…”

Computational prognostic indicators for breast cancer

“…Given a time after diagnosis for values of the predictor variables, the model produces a survival function for the probability that the binary event of interest (eg, death or survival at the endpoint) occurs. In this context, additional computational models to improve the prediction have been proposed, including Bayesian network analysis evaluating probabilistic relationships among candidate genes24 and support vector machine methodologies 25. A review of standard survival analyses and the use of the outstanding Bioconductor tool suite is available at http://cran.r-project.org/web/views/Survival.html.…”

Study and Analysis of Breast Cancer Cell Detection using Naïve Bayes, SVM and Ensemble Algorithms

“…In the paper [17] by Kim W et al SVM technique was used on breast cancer dataset consisting of 679 records. The types of data were clinical, pathologic and epidemiologic.…”