Flaker, Susan M

Abstract Purpose Excessive purchasing of influenza vaccine can lead to costly overages and waste of resources. Insufficient quantities, however, can jeopardize population health. Our project aimed to use predictive analytics to determine the influenza vaccine quantities that would be needed for the next influenza season while minimizing vaccine waste and meeting patient care demands. Methods Several data sources were evaluated to develop a predictive analytics model to better estimate future influenza vaccine orders during upcoming influenza seasons. A retrospective analysis of influenza vaccine administrations over the last 4 influenza seasons allowed the team to develop an algorithm to predict influenza vaccine needs. Two regions within Mayo Clinic were selected to determine the validity of our ordering process. These 2 regions, identified as regions 3 and 5, ordered influenza vaccines based on the algorithm, while the other 3 regions acted as control groups, ordering though traditional methods based on purchasing data. Results Predictive analysis for the 2 intervention regions resulted in a savings of over $1 million when compared to traditional ordering methods. The model predicted that the quantity of vaccine ordered should be 17,574.16 and 9,164.29 quadrivalent influenza vaccines for regions 3 and 5, respectively. On the basis of actual administration data, 15,902 vaccines for region 3 and 9,016 vaccines for region 5 will be administered by the end of the season, both of which are less than the predicted amount needed, demonstrating the accuracy of the analytics. Conclusion Compared to the traditional ordering method, ordering using predictive analytics allowed the team to more accurately determine future order volumes and spend, yielding significant cost savings.

Abstract Objectives Since the 1970s, a plethora of tools have been introduced to support the medication use process. However, automation initiatives to assist pharmacists in prospectively reviewing medication orders are lacking. The review of many medications may be protocolized and implemented in an algorithmic fashion utilizing discrete data from the electronic health record (EHR). This research serves as a proof of concept to evaluate the capability and effectiveness of an electronic prospective medication order review (EPMOR) system compared to pharmacists’ review. Materials and methods A subset of the most frequently verified medication orders were identified for inclusion. A team of clinical pharmacist experts developed best-practice EPMOR criteria. The established criteria were incorporated into conditional logic built within the EHR. Verification outcomes from the pharmacist (human) and EPMOR (automation) were compared. Results Overall, 13 404 medication orders were included. Of those orders, 13 133 passed pharmacist review, 7388 of which passed EPMOR. A total of 271 medication orders failed pharmacist review due to order modification or discontinuation, 105 of which passed EPMOR. Of the 105 orders, 19 were duplicate orders correctly caught by both EPMOR and pharmacists, but the opposite duplicate order was rejected, 51 orders failed due to scheduling changes. Discussion This simulation was capable of effectively discriminating and triaging orders. Protocolization and automation of the prospective medication order review process in the EHR appear possible using clinically driven algorithms. Conclusion Further research is necessary to refine such algorithms to maximize value, improve efficiency, and minimize safety risks in preparation for the implementation of fully automated systems.