Pancreatic stump closure techniques and pancreatic fistula formation after distal pancreatectomy: Meta-analysis and single-center experience

Abstract

Background: Pancreatic fistula/PF is the most frequent and feared complication after distal pancreatectomy/DP. However, the safest technique of pancreatic stump closure remains an ongoing debate. Here, we aimed to compare the safety of different pancreatic stump closure techniques for preventing PF during DP.

Methods: We performed a PRISMA-based meta-analysis of all relevant studies that compared at least two techniques of stump closure during DP with regard to PF rates/PFR. We further performed a retrospective analysis of our institutional PFR in correlation with stump closure techniques.

Results: 8301 studies were initially identified. From these, ten randomized controlled trials/RCTs, eleven prospective and 59 retrospective studies were eligible. Stapler closure (26%vs.31%, OR:0.73, p = 0.02), combination of stapler and suture (30%vs.33%, OR:0.70, p = 0.05), or stump anastomosis (14%vs.28%, OR:0.51, p = 0.02) were associated with lower PFR than suture closure alone. Spleen preservation/splenectomy, or laparoscopic/open DP, TachoSil®, fibrin-like glue-application, or bioabsorbable-stapler-reinforcements (Seamguard®) did not influence PFR after DP. In contrast, autologous patches (falciform ligament/seromuscular patches) resulted in lower PFR than no patch application (21.9%vs.25,8%, OR:0.60, p = 0.006). In our institution, the major three techniques of stump closure resulted in comparable PFR (suture:27%, stapler:29%, or combination:24%). However, selective suturing/clipping of the main pancreatic duct during pancreatic stump closure prevented severe PF (p = 0.02).

Conclusion: After DP, stapler closure, pancreatic anastomosis, or falciform/seromuscular patches lead to lower PFR than suture closure alone. However, the differences are rather small, and further RCTs are needed to test these effects. Selective closure of the main pancreatic duct during stump closure may prevent severe PF.

Fig 1. Flowchart of the systematic review and meta-analysis.

The boxes to the right indicate the number of excluded studies with the specified reasons.

Fig 2. Stapler closure of the pancreatic remnant during distal pancreatectomy/DP is associated with less frequent pancreatic fistula/PF formation.

Forrest plot of studies that provided quantitative data on the PF rates after handsewn/suture vs. stapler closure of the pancreatic stump during DP. 95%CI: 95% confidence interval. RCTs: randomized controlled trials. Grading of PF as B or C in the eligible studies was according to the ISGPF definition [16]. Bottom right: funnel plot of included studies.

Fig 3. Impact of stapler and suture combination on pancreatic fistula rates during DP.

A. Forrest plot of studies that compared the overall (upper plot) and clinically relevant (grade B/C, lower plot) PF rates after DP with either combined stapler and suture closure versus isolated stapler closure of the pancreatic stump. B. Forrest plot of studies that compared the overall (upper plot) and clinically relevant (grade B/C, lower plot) PF rates after combined stapler and suture closure during DP versus isolated suture of the pancreatic stump. 95%CI: 95% confidence interval.

Fig 4. Anastomosis of the pancreatic stump during DP is superior to suture, but not to stapling, for reducing fistula rates.

A. Forrest plot of studies that compared anastomosis (i.e. pancreatico-gastrostomy or–enterostomy) of the pancreatic stump to stapler closure with regard to overall (upper plot) and clinically relevant (grade B/C, lower plot) postoperative PF rates after DP. RCTs: randomized controlled trials. B. The Forrest plot of studies that compared anastomosis to suture closure of the pancreatic stump show a beneficial effect of anastomosis for reducing overall (upper plot) and clinically relevant (grade B/C, lower plot) postoperative PF rates after DP. Bottom: funnel plot of included studies in the comparison of anastomosis vs. suture with regard to PF rates after DP.

Fig 5. Impact of spleen-preservation and laparoscopic approach on PF rates after DP.

A. Forrest plot of studies that provided comparative data on overall (upper plot) and clinically relevant (grade B/C, lower plot) PF rates after either spleen-preserving or spleen-resecting DP. B. The Forrest plot of studies that compared overall (upper plot) and clinically relevant (grade B/C, lower plot) PF rates after laparoscopic vs. open DP, showing no difference in PF probability after either approach. Bottom right: Funnel plot of the included studies in the comparison of laparoscopic vs. open DP with regard to PF rates. Studies that were associated with high PF rates after laparoscopic DP seem to be lacking.

Fig 6. Stump “coverage” techniques and PF rates after DP.

A. Three RCTs analyzed the effect of TachoSil^® application on PF rates, where TachoSil^® clearly lacked any benefit. RCTs: randomized controlled trials. B. Forrest blot of 2 RCTs and 2 retrospective studies that analyzed the impact of fibrin-glue application on PF rates after DP. C. The bioabsorbable staple-line reinforcement Seamguard^® did also not relevantly influence PF rates in the five corresponding studies. BioRein: bioabsorbable staple-line reinforcement/Seamguard^®. D. Application of biological, i.e. autologous, seromuscular enteric, omental, falciform ligament, teres hepatis ligament patches was associated with a lower risk of postoperative PF after DP. 95%CI: 95% confidence interval.

Fig 7. Retrospective analysis of our institutional experience on PF rates and stump closure techniques during DP (Department of Surgery, TU München, 2007–2015).

A. Three different techniques of stump closure were applied for closure of the pancreatic remnant, where suture closure dominated. The overall PF rate was 27% (Grade A: 11%, Grade 2: 11%, Grade 3: 5% according to the ISGPS definition from 2005 [16]). B. The overall PF rate, but also the grade of the PF did not differ between DPs performed via any of the three techniques. n.s.: not significant. C. We also analyzed whether targeted, i.e. extra closure of the main pancreatic duct (e.g. via sutures or clipping) prior to suturing of the whole stump during DP influenced PF grade. Indeed, duct suturing or clipping prior to stump suture decreased the proportion of higher grade PF. D. The beneficial effect of pancreatic duct closure on reduction of higher grade PF was most obvious for closure with the monofilamentous PDS^® sutures.