[Construction and verification of nomogram prediction model for postoperative recurrence risk of congenital lingual root cysts in infants].
AI interpretation is pending for this paper.
Open original publication →What the AI sees
Not AI summarized yet.
Research significance
Pending deeper interpretation.
Source abstract
Objective:To identify the independent risk factors for postoperative recurrence of congenital lingual root cysts in infants and to construct and validate a nomogram prediction model for recurrence risk. Methods:A retrospective analysis was conducted on infants with congenital lingual root cysts who underwent surgical treatment in the Department of Otorhinolaryngology Head and Neck Surgery at Hebei Children's Hospital between April 2019 and April 2023. Based on recurrence status during the 2-year follow-up period, children were divided into a recurrence group and a non-recurrence group. The total dataset was split into a training set and a validation set at a ratio of 7∶3. General characteristics between the two groups were compared. The Least Absolute Shrinkage and Selection Operator（Lasso） regression algorithm with 10-fold cross-validation was used to further screen potential predictive variables associated with postoperative recurrence. Multivariate logistic regression was employed to identify independent risk factors for postoperative recurrence, based on which a nomogram model was constructed. Subsequently, the model's discriminatory ability, calibration, and clinical applicability were validated using the receiver operating characteristic（ROC） curve, calibration curve, and decision curve analysis, respectively. Results:A total of 164 infants with congenital lingual root cysts were included. 32 cases （19.5%） experienced recurrence during the 2-year follow-up, while 132 cases did not. Lasso regression identified eight potential predictive variables, including age at surgery, cyst location, surgical approach, intraoperative bleeding, cyst length, preoperative infection, postoperative complications, and surgeon experience. Multivariate logistic regression analysis ultimately identified five independent risk factors for postoperative recurrence: age at surgery（OR=1.446, 95%CI 0.973-2.149, P=0.020）, surgical approach（OR=4.614, 95%CI 1.759-12.101, P=0.002）, cyst length（OR=3.466, 95%CI 1.191-10.087, P=0.020）, preoperative infection（OR=1.839, 95%CI 1.031-3.278, P=0.006）, and postoperative complications（OR=1.808, 95%CI 1.149-2.843, P=0.020）. The predictive performance of the nomogram model was confirmed by the area under the curve（AUC） values（0.899 and 0.882 for the training and validation sets, respectively）, indicating good discriminatory ability. The calibration curves for both cohorts showed good consistency between predicted and observed probabilities. Decision curve analysis demonstrated a positive net benefit within a threshold probability range of 10% to 80%. Conclusion:The nomogram model, constructed based on factors such as age at surgery and surgical approach, demonstrates strong predictive performance and can serve as a practical tool for assessing postoperative recurrence risk and guiding individualized clinical management in infants with congenital lingual root cysts.