机器学习预测乳腺癌新辅助治疗后炎症代谢状态改变的模型评价
吴其蓁, 刘启明, 柴烨子, 陶政宇, 王依楠, 郭欣宁, 姜萌, 卜军

Evaluation of machine learning prediction of altered inflammatory metabolic state after neoadjuvant therapy for breast cancer
WU Qizhen, LIU Qiming, CHAI Yezi, TAO Zhengyu, WANG Yinan, GUO Xinning, JIANG Meng, PU Jun
表2 乳腺癌新辅助治疗前后患者5种模型在测试集中的单特征变量预测性能比较
Tab 2 Comparison of the predictive performance of the five models for single-feature variables in the test set for patients with breast cancer before and after neoadjuvant therapy
Single featureModelAUCAccuracyPrecision rateRecallF1 score
WBCRF0.7150.6030.6560.6360.646
GB0.7550.6550.6590.8180.730
SVM0.7670.6900.6830.8480.757
DT0.6550.5690.6430.5450.590
KNN0.7870.6900.7030.7880.743
HBRF0.8350.8450.8530.8790.866
GB0.8160.7590.7880.7880.788
SVM0.9060.8100.8240.8480.836
DT0.7480.7590.7880.7880.788
KNN0.8460.7930.8620.7580.806
HDLRF0.8720.8100.8240.8480.836
GB0.8530.8280.8290.8790.853
SVM0.8890.8450.8330.9090.870
DT0.8180.7590.7710.8180.794
KNN0.8920.8280.8290.8790.853
IL-2RRF0.7090.6720.6840.7880.732
GB0.7210.6550.7100.6670.688
SVM0.7310.6900.6830.8480.757
DT0.6270.6380.6760.6970.687
KNN0.7190.6550.6510.8480.737
IL-8RF0.6720.6030.6920.5450.610
GB0.6610.6900.7270.7270.727
SVM0.3300.5690.5691.0000.725
DT0.6500.6720.7330.6670.698
KNN0.4750.5000.5530.6360.592