Clinical Analysis of Primary Tracheobronchial Tumors in Children and Evaluation of the Predicting Models for Mucoepidermoid Carcinoma.

Objective: To determine the clinical characteristics and prognosis of primary tracheobronchial tumors (PTTs) in children, and to explore the most common tumor identification methods.
Methods: The medical records of children with PTTs who were hospitalized at the Children's Hospital of Chongqing Medical University from January 1995 to January 2020 were reviewed retrospectively. The clinical features, imaging, treatments, and outcomes of these patients were statistically analyzed. Machine learning techniques such as Gaussian naïve Bayes, support vector machine (SVM) and decision tree models were used to identify mucoepidermoid carcinoma (ME).
Results: A total of 16 children were hospitalized with PTTs during the study period. This included 5 (31.3%) children with ME, 3 (18.8%) children with inflammatory myofibroblastic tumors (IMT), 2 children (12.5%) with sarcomas, 2 (12.5%) children with papillomatosis and 1 child (6.3%) each with carcinoid carcinoma, adenoid cystic carcinoma (ACC), hemangioma, and schwannoma, respectively. ME was the most common tumor type and amongst the 3 ME recognition methods, the SVM model showed the best performance. The main clinical symptoms of PPTs were cough (81.3%), breathlessness (50%), wheezing (43.8%), progressive dyspnea (37.5%), hemoptysis (37.5%), and fever (25%). Of the 16 patients, 7 were treated with surgery, 8 underwent bronchoscopic tumor resection, and 1 child died. Of the 11 other children, 3 experienced recurrence, and the last 8 remained disease-free. No deaths were observed during the follow-up period.
Conclusion: PTT are very rare in children and the highest percentage of cases is due to ME. The SVM model was highly accurate in identifying ME. Chest CT and bronchoscopy can effectively diagnose PTTs. Surgery and bronchoscopic intervention can both achieve good clinical results and the prognosis of the 11 children that were followed up was good.
(© 2022. Huazhong University of Science and Technology.)