Harnessing Health Information Technology to Promote Equitable Care for Patients with Limited English Proficiency and Complex Care Needs

Communication problems in  clinical settings can lead to poor health outcomes and increased hospitalization, especially among patients with limited English proficiency (LEP)--those who have a limited ability to read, write, or understand English. Evidence strongly suggests that medical interpreters improve communication, patient satisfaction, and clinical outcomes when incorporated into care. In-person medical interpretation reduces cultural, linguistic, and literacy barriers, supporting more equitable care. Despite this evidence, interpreters in healthcare are often underutilized. As a result, patients with LEP and complex care needs are significantly impacted, receiving lower-quality care than patients who are proficient in English. There is a critical need to prioritize interpreter engagement to support decision making and enhance patient-centered care for LEP patients with complex care needs.

There are substantial gaps in clinical operations to increase interpreter use. This research aims to promote equitable care for patients with LEP and complex care needs by increasing the utilization of interpretation services. The research team will develop an application that identifies patients with LEP and  complex care needs to increase appropriate and timely interpreter use utilizing digital healthcare technology.

The specific aims of the research are as follows:

• Engage stakeholders in testing and validating a health information-based screening tool or “sniffer” to reliably identify patients with LEP and complex care needs.
• Engage stakeholders in designing an effective process for proactively reaching patients with unmet interpreter needs early in their hospitalization.
• Examine the preliminary effectiveness of the developed intervention on interpreter use and time to interpreter use among patients with LEP and complex care needs using a stepped-wedge cluster randomized trial.

The research team will codesign the technology with participant stakeholders, recruiting clinicians, and interpreters to build a process to connect the patients identified with the tool to interpreter services. A machine learning predictive analytic framework used in a former study will be modified in this application to identify patients with LEP and complex care needs. Taking place in the Mayo Clinic Hospital-Rochester, the deployment of this application in clinical workflow will allow for stakeholder feedback and evaluation in a real-life setting. The research team hypothesizes this intervention will increase appropriate and timely interpreter use among patients with LEP and complex care needs.