Machine learning prediction model for gray-level co-occurrence matrix features of synchronous liver metastasis in colorectal cancer

Table 2 Comparison of predictive efficacy of pulmonary infection prediction models via receiver operating characteristic curves

Model	Training set			Internal validation set
	AUC mean	AUC 95%CI	Variables1	AUC mean	AUC 95%CI	Variables1
RFM	0.917	0.866-0.968	7	0.909	0.858-0.960	7
ANNM	0.796	0.745-0.847	7	0.806	0.755-0.857	7
GLRM	0.783	0.732-0.834	6	0.739	0.688-0.790	6

¹Variables included in the model.

RFM: Random forest model; GLRM: Generalized linear regression model; AUC: Area under the curve; 95%CI: 95% confidence interval; ANNM: Artificial neural network model.