Comparative study of esophageal stent and feeding gastrostomy/jejunostomy for tracheoesophageal fistula caused by esophageal squamous cell carcinoma

Abstract

Background: A malignant tracheoesophageal/bronchoesophageal fistula (TEF) is a life-threatening complication of esophageal squamous cell carcinoma. A feeding gastrostomy/jejunostomy had been the most common treatment method for patients with TEF before the era of stenting. The aim of this retrospective study is to compare the prognosis of esophageal squamous cell carcinoma patients with TEF treated with an esophageal metallic stent to those treated with a feeding gastrostomy/jejunostomy.

Methods: We retrospectively reviewed a total of 1011 patients with esophageal squamous cell carcinoma between 1996 and 2011 at Kaohsiung Chang Gung Memorial Hospital, and 86 patients with TEF (8.5%) were identified. The overall survival and other clinical data were compared between 30 patients treated with an esophageal metallic stent and 35 patients treated with a feeding gastrostomy/jejunostomy.

Results: Among the 65 patients receiving either an esophageal metallic stent or a feeding gastrostomy/jejunostomy, univariate analysis showed that treatment modality with an esophageal metallic stent (P = 0.007) and radiotherapy treatment after fistula diagnosis (P = 0.04) were predictive of superior overall survival. In the multivariate comparison, treatment modality with an esophageal metallic stent (P = 0.026, odds ratio: 1.859) represented the independent predictive factor of superior overall survival. There were no significant differences between groups in mean decrease in serum albumin or mean body weight loss. Compared to the feeding gastrostomy/jejunostomy group, a significantly higher proportion of patients in the stenting group (53% versus 14%, P = 0.001) were able to receive chemotherapy within 30 days after fistula diagnosis, indicating better infection control in the stenting group.

Conclusions: Compared with a feeding gastrostomy/jejunostomy, an esophageal metallic stent significantly improves overall survival in patients with malignant TEF in our retrospective analysis. Esophageal metallic stent placement may be considered the first-line of treatment for patients with malignant TEF.

Figure 1. Representative images before and after esophageal metallic stent placement.

A. Computed tomography of the chest obtained before stent placement showed a tracheoesophageal fistula (arrow). B. Computed tomography of the chest obtained after stent placement showed a metallic stent in the esophagus covering the tracheoesophageal fistula. C. Before stent placement, endoscopic picture showed a protruding mass with a hole in the esophagus, suggesting esophageal cancer with a tracheoesophageal fistula (arrowhead). D. Endoscopic picture of an esophageal metallic stent in place one month after insertion.

Figure 2. Overall survival of all 86 ESCC patients after fistula diagnosis.

ESCC: esophageal squamous cell carcinoma.

Figure 3. Survival curves of 65 ESCC patients according to the treatment modality(A) and radiotherapy after fistula(B).

ESCC: esophageal squamous cell carcinoma.

Figure 4. Nutrition status and other laboratory data in stenting and feeding gastrostomy/jejunostomy groups.

A. Serum albumin decrease was determined by the formula: [serum albumin level within 1 week before fistula diagnosis – serum albumin level at 3–4 weeks after fistula diagnosis]. There was no significant difference (P = 0.21) between the two groups in mean decrease in serum albumin. B. Body weight loss was determined by the formula: [body weight within 1 week before fistula diagnosis – body weight at 3–4 weeks after fistula diagnosis]. There was no significant difference (P = 0.66) between the two groups in mean body weight loss. C–H. There were no significant differences between stenting and feeding gastrostomy/jejunostomy groups in white blood cell(C), hemoglobin(D), platelet(E), AST(F), ALT(G), and total bilirubin(H) within the week before fistula diagnosis (Week 0) or at 3–4 weeks after fistula diagnosis (Week 3–4).