The relative importance of graft surveillance and warfarin therapy in infrainguinal prosthetic bypass failure

Background. We sought to describe modes of failure and associated limb loss after infrainguinal polytetrafluoroethylene bypass grafting in patients lacking a saphenous venous conduit and to define specific clinical or hemodynamic factors prognostic for bypass failure. Methods. We identified 121 patients (mean age, 67 years; 90 men and 31 women) with determinable outcomes (minimum follow-up, 2 months; mean, 17 months) after 130 prosthetic infrainguinal bypasses between 1997 and 2005. Ischemic presentation was rest pain in 52%, tissue loss in 34%, and disabling claudication and/or popliteal aneurysm in 14%, with 24% of patients requiring a redo bypass. Distal targets were the above-knee (n = 44), distal popliteal (n = 27), or tibial/pedal (n = 59) arteries. Sixty-six (77%) of the below-knee (BK) target (distal popliteal or tibial) bypasses had distal anastomotic adjuncts (vein cuff or patch). Duplex graft surveillance was performed at 1, 4, and 7 months after surgery and twice yearly thereafter, with recording of midgraft velocities and imaging encompassing inflow and outflow vessels. Arteriography and open/endovascular intervention was performed for stenoses identified by duplex scanning (peak systolic velocity > 300 cm/s; velocity ratio > 3.5). An attempt was made to salvage occluded grafts by using catheter-directed thrombolysis or open techniques. Eighty-six patients (74% of BK bypasses) were placed on chronic warfarin therapy with a target international normalized ratio range between 2 and 3. Prognostic factors were identified by using univariate statistics and multivariate logistic regression analysis. Results: Three-year primary, assisted, and secondary patency rates were 39%, 43%, and 59%, respectively, for all bypasses, with no difference noted between above-knee and BK grafts (P = .5). At 3 years, freedom from limb loss was 75%, and patient survival was only 70%, with no adverse effect on survival imparted by amputation. Sixty-nine total adverse events occurred as a result of thrombotic occlusion (n = 51), duplex scan- detected stenosis (n = 13), or graft infection (n = 5). Forty-nine percent of all initial graft occlusions eventually led to amputation. Twenty-three grafts (27% of 86 patients) in patients maintained on chronic warfarin were subtherapeutic at the time of occlusion. Use of a distal anastomotic adjunct: with BK bypasses reduced graft thrombosis (35% with vs 60% without) but did not impart a significant patency advantage (P = .07). Multivariate analysis revealed low graft flow (midgraft velocity <= 45 cm/s; odds ratio [OR], 6.1; 95% confidence interval [CI], 1.9-19.2), use of warfarin (OR, 8.4; 95% CI, 2.1-34.5), and therapeutic warfarin (OF, 24.6; 95% CI, 5.7-106) to be independently predictive for bypass patency. Graft patency was maintained in 89% of grafts remaining therapeutic on warfarin compared with only 55% of subtherapeutic or nonanticoagulated grafts (P < .001). Low-flow grafts (n = 61) occluded more frequently than higher-flow grafts (46% vs 13%; P < .001). Therapeutic warfarin augmented the patency of low-flow (P < .001) but not high-flow (P = .15) grafts. Conclusions. Low graft flow was a more common mode of prosthetic bypass failure than development of duplex scan-detected stenotic lesions during follow-up. Early duplex scanning may be more important for characterizing midgraft velocity and related thrombotic potential and selecting patients for chronic anticoagulation. Maintenance of therapeutic warfarin is paramount in optimizing prosthetic bypass patency and limb preservation.