JMIR Publications

ABSTRACT

Background:

Primary care physicians are at the forefront of the clinical process that can lead to diagnosis, referral, and treatment. Their ability to navigate the clinical interaction whilst using technology, and level of engagement can profoundly impact the patient experience. The introduction of new technology in the patient and primary care interaction is not a new endeavor; in the past, having to integrate the use of Electronic Medical Records (EMRs) caused concern for the patient experience. Despite concerns and challenges, EMRs have now become a standard part of care. As EMRs have become a more integrated part of primary care delivery, it has also increasingly been recognized as a cause of physician burnout. Studies have demonstrated that physicians who are EMR users have actually reported being less satisfied with the amount of time allocated on tasks associated with their EMRs. This clearly demonstrates that EMRs have potential to be optimized as a tool that can support care delivery. Mirroring the example of EMR integration in a clinician’s workflow, a similar discovery of benefits outweighing the potential perceived risks can apply to tools enabled with AI in primary care.

Objective:

The primary objective of this research is to understand if the provider-centered design approach, rooted in contextual design, can enhance the use of an AI-enabled encounter module embedded in the primary care electronic medical record (EMR) to facilitate more characteristics of shared decision-making in a clinical interaction. Using human factors models to understand the results, generalizable guidance will be obtained to help design future AI tools.

Methods:

To accomplish this, a partnership has been established with an industry partner, TELUS Health, to use their EMR, the Collaborative Health Record (CHR). The overall objective is to understand how to improve shared decision-making when using AI tools in a primary care EMR. Given this objective, a user-centered approach will be used to accomplish it. The approach of user-centered design requires qualitative interviewing to gain a clear understanding of users’ approaches, intentions, and other key insights to inform the design process. A total of 5 phases have been designed for this study. •Phase 1 will interview primary care physicians to understand their current workflow in the traditional CHR using the encounter module •Phase 2 will interview the same primary care physician on the use of an AI-enabled encounter module in the CHR (wireframes will be used to convey this), •Phase 3 focuses on a qualitative analysis of the data collected in the interviews to develop user-centered requirements, •Phase 4 is the re-design of an AI-Enabled encounter module in the CHR based on the data analyzed in phase 3 and; •Phase 5 is the validation of the new designs in a secondary interview with the primary care physicians. A targeted group of 50 participants is anticipated to reach data saturation.

Results:

This research is ongoing; results will be available in a follow-up publication.

Conclusions:

This research is ongoing; results will be available in a follow-up publication.