Creating and evaluating a decision support tool to reduce critically low hemoglobin and blood transfusions in-hospital

BackgroundHospitalized patients have multiple risk factors for bleeding including critical illness, interventional procedures, frequent phlebotomy, and use of anticoagulant and antiplatelet medications. It is unknown if a decision support tool to identify inpatients at highest risk of bleeding can prevent critically low hemoglobin and its associated sequelae, such as requiring blood transfusion. ObjectiveTo create a decision support tool to identify hospitalized patients at high risk of bleeding sequelae ("high risk") and to evaluate the impact of this tool on rates of critically low hemoglobin and blood transfusion. MethodsWe conducted a cohort study of patients hospitalized under general internal medicine at a tertiary-care teaching hospital in Toronto, Ontario. We defined "high risk" as patients with a hemoglobin < 86 g/L, or an absolute decrease in hemoglobin of [&ge;] 30 g/L, or a platelet count < 50 x 109/L. We then created, implemented, and prospectively evaluated a decision support tool to identify these high-risk patients and alert their clinical team. Our primary outcome was the percentage of patients who received a blood transfusion. ResultsOur retrospective pre-deployment phase included 6,401 hospitalizations and our prospective phase included 4,274 hospitalizations. The median age of patients was 67 years (IQR 52,80), 43% were female, and the median length of stay was 5 days (IQR 2,10). Overall, 9% had a hemoglobin of 70 g/L or lower and 10% received a blood transfusion in hospital. After model implementation, the median timing of alerts was 1 day after admission (IQR 1,4). The most common trigger for an alert was a hemoglobin < 86 g/L (N=624, 76%), followed by a decrease in hemoglobin [&ge;] 30 g/L (N=131, 16%), and a platelet count < 50 x 109/L (N=37, 5%). Deployment of the decision support tool was associated with a reduction in the primary outcome (OR 0.78, 95% CI 0.64, 0.96), which was driven by a reduction in red blood cell transfusion (OR 0.78, 95% CI 0.64, 0.96) as opposed to platelet transfusion (OR 1.10, 95% CI 0.46, 2.91). We also observed a reduction in our secondary outcome of critically low hemoglobin (OR 0.81, 95% CI 0.65, 0.99). InterpretationOur decision support tool was associated with a modest reduction in our primary outcome of blood transfusions and secondary outcome of critically low hemoglobin. Because our study was single-centre, we believe future larger studies are needed to validate our findings.