Clinical Research with Electronic Health Records Data (CR-EHR) Course

Duke AI Health and the Duke Clinical & Translational Sciences Institute are pleased to announce a call for applications to the Clinical Research with Electronic Health Records Data (CR-EHR) Course. CR-EHR is an interdisciplinary course designed to engage both clinical and quantitative researchers in learning how to access and work with Duke EHR data. Data captured in the Duke EHR represent the broad spectrum of patient care delivered by Duke Health, which can be leveraged for a variety of research questions and study designs. Clinical trainees will develop a deeper understanding of the types of analytic studies that can be conducted with EHR data, while quantitative trainees will develop a deeper knowledge base for how to query and process EHR data. Recognizing that working with EHR data requires a “team-science” approach, we will pair clinical and quantitative investigators to develop and address a research question using analysis of structured EHR data. To promote deep engagement with the course material, clinical applicants will be asked to come in with a research question that they wish to answer, and quantitative applicants should have prior experience in analytics and programming. Please note that applicants will be asked to determine whether a quantitative or clinical “track” is most appropriate based on their previous experiences and skillsets.

The course will cover topics in informatics, inference, and predictive modelling, including:

– Structure of the Duke EHR system
– Self-service tools for accessing EHR data
– Analytic techniques for EHR-based studies including:
         – Developing statistical analysis plans
         – Creating analytic data sets
         – Biases associated with EHR data
         – Inferential methods
         – Developing and implementing predictive models
– Incorporating external data sources into EHR-based studies (e.g., environmental data)
– Considerations for grant applications using EHR data

The course will meet virtually for 90 minutes every 2 weeks from January through May (meeting time TBD). Sessions will be conducted using a “flipped-classroom” format, in which lectures will be posted ahead of time and class time will be used to discuss the lecture topic, work through examples, and provide time for project teams to meet.  The course will culminate in final presentations where project teams will present their work.