Implementation of a Novel Multi-Platform Evidence-Based Clinical Decision Support System (New York)

This project does not have any related annual summary.
This project does not have any related event.
This project does not have any related resource.
This project does not have any related survey.
This project does not have any related project spotlight.
This project does not have any related survey.
This project does not have any related story.
This project does not have any related emerging lesson.
Using clinical decision support (CDS) implemented with standards and service-oriented architecture, guidelines could be implemented throughout the healthcare system, allowing for faster dissemination and updates when guidelines change. Such an approach could markedly reduce the cost of developing and maintaining CDS, and potentially increase the uptake of evidence-based research findings into clinical practice.

Summary:

Clinical decision support (CDS) tools provide physicians and other healthcare providers with assistance in clinical decision-making tasks. Historically, these tools have been designed and built within organizations for specific electronic health records (EHRs) and clinical environments, which can make it difficult to use the tools across different organizations and clinical settings. In addition, when guidelines change, each individual organization must update their individual tools--a process many fail to do in a timely fashion, resulting in potential issues for patient safety and clinical care.

For more than a decade, the Northwell Health Center for Health Innovations and Outcomes Research (CHIOR) has been developing, testing, validating, and evaluating CDS tools and systems. One of CHIOR’s primary focuses has been on clinical prediction rules (CPRs), a form of CDS that uses data to calculate patient-specific probabilities. Recently, the focus has been on increasing the speed at which evidence is translated into clinical practice utilizing CDS. One mechanism to accomplish this would be to shift to a model that is vendor-agnostic using service-oriented architecture (SOA) software running outside of an EHR. This model would allow tools to be available to any EHR within any organization and clinical setting, and to allow for broader updating when guidelines change. Such an approach would markedly reduce the cost of developing and maintaining CDS, and potentially increase the uptake of evidence-based research findings into clinical practice. This current research will develop, test, and evaluate an SOA platform-based CDS system. Two evidence-based derived and validated CPRs--the IMPROVE-DD (D-Dimer) Risk Model for Venous Thromboembolism (VTE) and the Wells’ criteria for pulmonary embolism-–will be made available via this platform utilizing Fast Healthcare Interoperability Resources (FHIR) standards where possible. The research will take place in two healthcare settings: inpatient and the emergency department, at two clinical sites.

The specific aims of the research are as follows:

  • Blend CDS into the flow of clinical care by embedding two widely validated CPRs in two commercial EHRs using a CDS system built on a SOA. 
  • Leverage the results of iterative cycles of “think aloud,” “near live,” and live usability testing to map how the SOA-based CDS system should be integrated into the two selected clinical sites. 
  • Evaluate the effectiveness of the SOA-based CDS system in each healthcare environment by measuring adoption, acceptance, and clinical outcomes. 

Complications due to VTE have been associated with poor prognosis in patients with Coronavirus Disease 2019 (COVID-19). An AHRQ-funded supplemental grant will allow the researchers to expand on their original work by refining and validating the Wells’ criteria for pulmonary embolism in the emergency department and IMPROVE-DD risk model in hospitalized COVID-19 patients. The lessons learned and disseminated from this project will help healthcare system leaders understand how CDS can be delivered--through services and health information exchange--within their system and potentially shared between systems. In particular, this work will demonstrate how to use standards (e.g., SMART on FHIR where possible) within commercial EHRs and also provide evidence for how to implement validated CDS for important clinical domains, pulmonary, and venous thromboembolism, including for patients with COVID-19.