Machine learning model predicting factors for incisional infection following right hemicolectomy for colon cancer

BMC Surgery

Table 3 Evaluation indicators for each model

Model		F1 score	ROC-AUC	95%CI
Logistic Regression
	Training	0.882	0.863	0.744–0.935
	Validation	0.791	0.796	0.684–0.717
Random Forest
	Training	0.837	0.844	0.786–0.923
	Validation	0.763	0.757	0.612–0.882
Support Vector Machine
	Training	0.759	0.786	0.637–0.902
	Validation	0.707	0.737	0.590–0.849
Deep Learning
	Training	0.906	0.885	0.781–0.970
	Validation	0.858	0.879	0.768–0.963

Abbreviations ROC: receiver operator characteristic; AUC: area under the curve; CI: confidence interval

ISSN: 1471-2482