Objective: This study is to evaluate the effectiveness and frequency factors of endoscopic bougie dilatation in treating postoperative anastomotic stenosis of congenital esophageal atresia (CEA).
Methods: The clinical data of patients of anastomotic stenosis with endoscopic bougie were retrospectively analyzed. According to the number of dilation times (ND), patients were divided into two groups (Group 0: ND < 3; Grooup1: ND ≥ 3), and the differences in multiple clinical data were compared. Lasso regression and Ridge regression were used to screen important variables. Classification models were built utilizing various machine learning algorithms and their performance were evaluated. Finally, Kaplan-Meier model was used to estimate the probable-time distribution of children achieving normal feeding.
Results: Seventy-five patients underwent a total of 210 times of dilation, with a median of 3 times of dilation. The overall effectiveness was 98.67% (74/75), with perforation in 2 case (0.95%), and obvious bleeding in 3 cases (1.43%). Initial diameter of bougie, final diameter of bougie, treatment pattern (Regular: dilation each 4weeks; Wait-and-see: dilation until symptoms present), age at final dilation, esophageal obstruction by food were the factors related to ND. Random Forest (RF) and Logistic regression (LR) model were excellent models for predicting ND. The median age for achieving normal eating in Group0 was 120 days (95% CI: 90-160), while it was 270 days (95% CI: 240-460) in Group1 with a statistically significant difference (P < 0.0001).
Conclusion: Endoscopic bougie dilatation is a safe and effective treatment for anastomotic stenosis. Selecting the appropriate bougie, using symptoms as the criterion for dilation, and minimizing the dilations under 3 times constitute a rational strategy.
Keywords: Random Forest model; anastomotic stenosis; congenital esophageal atresia; endoscopic bougie dilatation; logistic regression model; machine learning models; nomogram.
© 2024 He, Xiong, Deng, Yang, Yan, Zhang, Shang, Xie, Liu and Li.