Development of a machine learning model for preoperative prediction of spread through air spaces in resectable non-small cell lung cancer: A single-center retrospective study.

DeLong's tests demonstrated that XGBoost yielded significantly higher AUCs compared with logistic regression, naïve Bayes and random forest (all P<0.05), whereas its difference with SVM did not reach statistical significance (P>0.05; Fig. 1G ).

also in 111,027 other papers