Standards-based and service-oriented clinical decision support systems have the potential for more efficient scale across healthcare systems and for greater uptake of evidence-based research findings into clinical practice.
Project Details -
Completed
-
Grant NumberR18 HS026196
-
Funding Mechanism(s)
-
AHRQ Funded Amount$1,541,803
-
Principal Investigator(s)
-
Organization
-
LocationManhassetNew York
-
Project Dates03/01/2019 - 06/30/2022
-
Care Setting
-
Medical Condition
-
Population
-
Type of Care
-
Health Care Theme
The Northwell Health Center for Health Innovations and Outcomes Research (CHIOR) develops, tests, validates, and evaluates clinical decision support (CDS) tools and systems. Shifting from historic models that are single facility-based to one that is vendor-agnostic using service-oriented architecture (SOA) software available to all is critical to increase the speed at which evidence is translated into clinical practice using CDS. The goal of this research was to increase the ease at which software-based CDS solutions can be created and disseminated to promote the use of evidence-based medicine at the point of care.
The specific aims of the research were as follows:
- Blend CDS into the flow of clinical care by embedding two widely validated clinical prediction rules in two commercial electronic health records (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.
The research team developed an EHR-agnostic CDS web-based platform called EvidencePoint that provides the ability to integrate individual CDS into clinical workflows. Three use cases were used: the Northwell COVID-19 Survival (NOCOS) CDS application comparing patients with and without COVID, the IMPROVE-DD (D-Dimer) CDS for pulmonary venous embolism (PE) risk stratification, and the Wells’ criteria for PE.
Two pilot studies were conducted: one with the NOCOS survival predication model deployed to emergency departments across the Northwell hospital system and with the IMPROVE-DD CDS application for venous thromboembolism risk assessment deployed to two of its largest tertiary hospitals. The second pilot used the Wells’ Criteria CDS application at two tertiary hospitals that were already using the IMPROVE-DD application, using a behavioral economics “nudge” to encourage adoption of the tool.
Appropriate thromboprophylaxis rates were higher at intervention sites using IMPROVE-DD during inpatient stays and after discharge, and had fewer venous, arterial, and total thromboembolic events. Sites using the behavior economics “nudges” with the Wells’ Criteria PE diagnostic risk assessment application had a near doubling of provider adoption. The use of Well’s Criteria was found to not differ significantly in ruling out PE in COVID-positive versus -negative patients.
Because the hospital system moved to a single EHR during the grant period, the evaluation could not be completed across a variety of EHRs as planned. Despite this, the EvidencePoint system was successfully developed in an EHR-agnostic manner and has retained that capability.