Development of a risk prediction model for transfusion in carotid endarterectomy and demonstration of cost-saving potential by avoidance of "type and screen"

Abstract

Objective: Preoperative testing for carotid endarterectomy (CEA) often includes blood typing and antibody screen (T&S). In our institutional experience, however, transfusion for CEA is rare. We assessed transfusion rate and risk factors in a national clinical database to identify a cohort of patients in whom T&S can safely be avoided with the potential for substantial cost savings.

Methods: With use of the National Surgical Quality Improvement Program database, transfusion events and timing were established for all elective CEAs in 2012-2013. Comorbidities and other characteristics were compared for patients receiving intraoperative or postoperative transfusion and those who did not. After random assignment of the total data to either a training or validation set, a prediction model for transfusion risk was created and subsequently validated.

Results: Of 16,043 patients undergoing CEA in 2012-2013, 276 received at least one transfusion before discharge (1.7%); 42% of transfusions occurred on the day of surgery. Preoperative hematocrit <30% (odds ratio [OR], 57.4; 95% confidence interval [CI], 29.6-111.1), history of congestive heart failure (OR, 2.8; 95% CI, 1.1-7.1), dependent functional status (OR, 2.7; 95% CI, 1.5-5.1), coagulopathy (OR, 2.5; 95% CI, 1.7-3.6), creatinine concentration ≥1.2 mg/dL (OR, 2.3; 95% CI, 1.6-3.3), preoperative dyspnea (OR, 2.0; 95% CI, 1.4-3.1), and female gender (OR, 1.6; 95% CI, 1.1-2.3) predicted transfusion. A risk prediction model based on these data produced a C statistic of 0.85; application of this model to the validation set demonstrated a C statistic of 0.81. In the validation set, 93% of patients received a score of 6 or less, corresponding to an individual predicted transfusion risk of 5% or less. Omitting a T&S in these patients would generate a substantial annual cost saving for National Surgical Quality Improvement Program hospitals.

Conclusions: Whereas T&S are commonly performed for patients undergoing CEA, transfusion after CEA is rare and well predicted by a transfusion risk score. Avoidance of T&S in this low-risk population provides a substantial cost-saving opportunity without compromise of patient care.

Figure 1

Accuracy of risk score model. There is a high degree of agreement between the predicted probability of transfusion generated by the risk score and the actual probability of transfusion in the validation set. There is, however, a less precise fit at higher points of the risk score, especially for 14 and 15 points, which is not statistically significant. This is likely due to few patients at risk at these points.

Figure 2

Cumulative proportion of patients. Patients in the validation set are displayed according to their risk score. 93% of patients have a risk score of 6 or less, corresponding to an individual predicted transfusion risk of 5%.