基于机器学习的三阴乳腺癌预测模型

Develop prediction model of TNBC based on machine learning

三阴乳腺癌是目前研究比较广泛的一类乳腺癌,但是目前仍然没有准确而又便捷的诊断预测方法,我们通过使用机器学习中决策树算法和支持向量机特征消除算法来构建三阴乳腺癌(TNBC)的预测模型.通过决策树算法,提取得到的9个特征基因,构建的三阴乳腺癌预测模型准确率达到95.5%.通过支持向量机特征消除算法,提取得到的6个特征基因,构建的预测模型准确率达到97.8%.

Triple negative breast cancer( TNBC) is an important subtype of breast cancer,and has been paid more and more attention in the research.Nowadays,there is no effective treatment of TNBC,and there is no significant biomarkers and easy diagnosis method. We develop prediction models of TNBC based on machine learning,such as decision tree algorithm and SVM recursive feature elimination algorithm. By decision tree algorithm,we obtained 9 genes to predict TNBC,the accuracy of this model is 95.5%; By SVM recursive feature elimination algorithm,we obtained 6 genes to predict TNBC,the accuracy of this model is 97.8%.