Venous thromboembolism (VTE) is a serious source of hospital morbidity and mortality. Chemoprophylaxis with heparin has been shown to reduce the occurrence of VTE, but it increases the risk of bleeding and it is uncomfortable to receive. For that reason, VTE prophylaxis should be reserved for patients at moderate to high risk of VTE and low risk of bleeding. However, identifying patients at low risk for VTE can be difficult, because most patients have at least one risk factor for VTE and there are no validated risk prediction tools for use in US hospitals. Instead, many hospitals have opted for a one-size-fits-all approach with near-universal prophylaxis, putting many patients at unnecessary risk of bleeding. However, to provide care that is truly patient-centered, US physicians face several challenges. First, there is no accepted risk calculator that they can use to estimate an individual patient's risk. Second, risk calculators are not readily available at the point of care. As a result, prophylaxis rates have remained stubbornly low in some institutions, while in others the rate of prophylaxis is high, but the rate of inappropriate prophylaxis is also high. This study uses a risk prediction tool developed at the Cleveland Clinic to assess an individual patient's risk of VTE. The tool is incorporated into the electronic health record in the form of a smart order set. In this randomized trial, we will assess the effects of the order set on physician behavior and patient outcomes . Examining the effectiveness of an electronic decision aid embedded in an EHR in routine clinical practice will test whether a smart order set can improve patient care by incorporating patient-specific factors into a complex decision process.

Specific Aim:

Assess the effects of a VTE risk calculator embedded in the admission order set vs. usual care on physician behavior and patient outcomes in a randomized trial

Research Strategy:

Utilizing a Step-Wedge design, this randomized controlled trial (RCT) will be conducted at 10 Cleveland Clinic hospitals in efforts to assess the effects of a VTE (venous thromboembolism) risk calculator embedded in the admission order set vs. usual care on physician behavior and patient outcomes. Hospitals will be randomized to display the risk calculator to physicians admitting patients or to the usual order set that contains only a description of VTE risk factors. The risk calculator will produce a predicted risk of VTE together with a recommendation regarding the use of prophylaxis for an individual patient. Physicians will be free to ignore the calculator or override its results if they so choose.

Inclusion Criteria:

• All adult patients (age ≥18 years) admitted to a medical service, including intensive care units, between September 1, 2017 and August 31, 2018 will be eligible.

Exclusion Criteria:

• patients not eligible to receive VTE prophylaxis because they are already receiving anticoagulation for another purpose (e.g. warfarin for atrial fibrillation or LMWH for DVT or PE present on admission),
• patients admitted with a terminal condition who are receiving comfort care only
• Surgical patients who are admitted to the medical service temporarily (e.g. hip fracture)