University of Pittsburgh

SToPVTE: Screening to Prevent Venous Thromboembolism

As many as 38% of surgical patients experience postoperative venous thromboembolism (VTE), a dangerous condition in which a blood clot forms intravenously. It is the third leading vascular diagnosis behind heart attack and stroke, resulting in estimated costs to the US healthcare system in excess of $10 billion dollars per year. Our preliminary data suggests that assessing risk factors over time (i.e., during a patient’s recovery from surgery) increases the accuracy of risk appraisal. Consequently, an improved understanding of risk can be used to guide changes in preventative strategies, and importantly, a substantial reduction in these adverse events. SToPVTE is a clinical decision support software (CDSS) that will revolutionize VTE risk assessment and prevention to improve patient care and reduce economic losses due to postoperative VTE.

Description

Our product is an electronic health record (EHR)-embedded CDSS that uses existing patient data in real-time to recommend individualized thromboprophylaxis measures based on the most up-to-date assessment of a patient’s risk. Unlike other risk assessment instruments, our tool will predict time and type of VTE (i.e., deep vein thrombosis or pulmonary embolus) and generate recommendations for the dose, duration, and type of prophylaxis. In contrast to existing CDSS applications, our product will be compatible with multiple EHR platforms, use patient data in real-time, and automate the decision-making process for prophylaxis. Finally, SToPVTE is a sustainable solution: it captures outcome data for ongoing improvement of risk calculation and interventions to save lives.

Applications

· EHR platforms that encourage application development including, but not limited to, Cerner and EPIC
· Stand-alone applications for mobile devices that can be used by health-care providers in outpatient clinics.

Advantages

· Validated specifically for surgical patients
· Complete evaluation of only most salient risk factors
· Uses real-time patient data for most accurate risk profile
· Specifies type/dose/duration of prophylaxis to reduce bleeding complications and maximize anticoagulant potential
· Compatible with multiple EHR platforms to facilitate integration and congruent aggregation of clinical data

Invention Readiness

Preliminary data has provided validation of concept Development of machine learning algorithm is underway in a partnership with UPMC Clinical Analytics and University of Pittsburgh Department of Biomedical Informatics.

IP Status

Copyright