Development and validation of a postoperative pulmonary infection prediction model for patients with primary hepatic carcinoma

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	0.823	0.766-0.880	7	0.801	0.744-0.858	7
ANNM	0.815	0.766-0.864	8	0.787	0.738-0.836	8
GLRM	0.766	0.717-0.815	6	0.734	0.677-0.791	6

¹Variables included in the model.

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