Converting IMPROVE bleeding and VTE risk-assessment models into a fast-and-frugal decision tree for optimal VTE prophylaxis

Abstract

Current hospital VTE (venous thromboembolism) prophylaxis for medical patients has been characterized by both underuse and, increasingly, overuse. The American Society of Hematology (ASH) has endorsed the use of risk assessment models (RAM) as an approach to individualize VTE prophylaxis as a way of balancing overuse (excessive risk of bleeding) and underuse (risk of avoidable VTE). ASH has endorsed IMPROVE (International Medical Prevention Registry on Venous Thromboembolism) risk assessment models – the only RAM to assess short-term bleeding and VTE risk in acutely ill medical inpatients. ASH, however, notes that no RAMs have been thoroughly analyzed for their effect on patient outcomes. We aimed to validate the IMPROVE models and adapt them into a simple, fast-and-frugal (FFT) decision tree to evaluate the impact of VTE prevention on health outcomes and costs. We employed three methods: the "best evidence" from ASH guidelines, a "learning health system paradigm" combining guideline and real-world data from the Medical University of South Carolina (MUSC), and a "real-world data" approach based solely on MUSC data retrospectively extracted from electronic records. We found the most effective VTE prevention strategy utilizes the FFT decision tree, guided by an IMPROVE VTE score of ≥ 2 or ≥ 4 and a bleeding score of < 7. This method could prevent 45% of unnecessary treatments, saving about $5 million annually for patients like the MUSC cohort. We recommend integrating the IMPROVE models into hospital electronic medical records as a point-of-care tool, thereby enhancing VTE prevention in hospitalized medical patients.