Skip to main content
Fig. 2 | BMC Surgery

Fig. 2

From: Risk assessment of postoperative atelectasis in elderly lung cancer patients undergoing thoracoscopic surgery based on a nomogram model

Fig. 2

Receiver operating characteristic (ROC) curves for the predictive performance of the nomogram in the training cohort (A) and validation cohort (B). (A) ROC curve for the training set, presenting an AUC of 0.826 (95% CI: 0.767–0.885), indicating an excellent discriminative ability for distinguishing patients with and without atelectasis. (B) ROC curve for the validation set, with an AUC of 0.918 (95% CI: 0.802–0.991), demonstrating a strong predictive performance in an independent dataset. Explanation: the x-axis represents 1-specificity (false-positive rate), and the y-axis represents sensitivity (true positive rate). The diagonal dashed line represents the performance of a random classifier (AUC = 0.5). A larger area under the curve indicates a better model performance

Back to article page

BMC Surgery

ISSN: 1471-2482

Contact us