基于Logistic回归、ANN、SVM的乳腺癌复发影响因素研究

为找出乳腺癌复发的影响因素，并比较人工神经网络（ANN）型、支持向量机型（SVM）和logistic回归型在乳腺癌复发中的预测效能.本文结合南斯拉夫卢布尔雅那大学医疗中心乳腺癌肿瘤研究所的277例数据，对乳腺癌复发的影响因素进行研究.分别采用了logistic回归、人工神经网络和支持向量机方法来建立乳腺癌复发的预测模型，并对这三种分析方法进行了理论方法和预测效能的比较.结果发现，肿瘤大小、有无结节冒、肿瘤恶性程度（P<0.05）是乳腺癌术后复发的主要影响因素，而在不同的预测方法中相对于logistic回归模型，支持向量机和人工神经网络具有更好的预测效能，其中支持向量机的预测效能最好.

Research on Risks Factors of Female Breast Cancer Recurrence Based on Logistic Regression, Artificial Neural Network and Support Vector Machine

In order to find out the influencing factors of breast cancer recurrence, this paper investigates the artificial neural network(ANN), support vector machine(SVM) and logistic regression for the prediction of breast cancer recurrence. A data set containing 277patients'' records which is provided by the University of Wisconsin Hospitals, Madison from Wolberg is used to study the influencing factors of recurrence of breast cancer. By using logistic regression, artificial neural networks and support vector machine, it determines the important factors of breast cancer recurrence, and then compares these three methods. The results show that tumors size, nodules risk, the degree of malignancy(P<0.05) are the main factors of breast cancer recurrence. Compared to the logistic regression model, support vector machine and artificial neural network has better prediction performance, and support vector machine performs best.