JMIR Publications

ABSTRACT

Background:

Diagnostic error in ambulatory care, a frequent cause of preventable harm, may be mitigated by harnessing collective intelligence emerging from the collaboration of multiple clinicians. The National Academy of Medicine has identified enhanced clinician collaboration and digital tools as means to improve the diagnostic process. This study aims to assess the efficacy of a collective intelligence output to improve diagnostic confidence and accuracy in ambulatory care cases (from primary care and urgent care clinic visits) with diagnostic uncertainty.

Objective:

In this pragmatic randomized controlled trial, we will examine the efficacy of a collective intelligence technology platform on improving primary clinicians’ confidence in their diagnostic assessments and their accuracy in making a correct diagnosis. We will also examine clinicians’ perceptions of the usability of the collective intelligence technology platform and their likelihood of using (i.e. intention to use) such a platform in routine primary care or urgent care practice to assist with the diagnosis process.

Methods:

This study will assess both the efficacy and usability of a digital tool that facilitates access to collective intelligence. We will assess efficacy through a pragmatic randomized controlled trial involving cases with diagnostic uncertainty from clinicians at primary care and urgent care clinics in two health systems in a single city. Real-life cases, identified for having an element of diagnostic uncertainty, will be entered into a digital platform to acquire a collective intelligence from at least five clinicians. Cases will be randomized to an intervention group (where clinicians will view the collective intelligence output) or control (where clinicians will not view the collective intelligence output). Clinicians will complete a post-visit questionnaire for each case that assesses their diagnostic confidence for the case; for in the intervention cases, clinicians will complete the questionnaire after reviewing the collective intelligence output for the case. Using logistic regression accounting for clinician clustering, we will compare the primary outcome of diagnostic confidence and secondary outcome of time to diagnosis, for intervention vs. control groups. We will also assess the usability and satisfaction with the digital tool, using measures adapted from the Technology Acceptance Model and Net Promoter Score.

Results:

We have recruited 32 out of our recruitment goal of 33 participants. This study is funded until May 2019 and is approved by the University of California San Francisco Institutional Review Board until March 2019. We expect to complete data collection in December 2018 and complete our proposed analyses by June 2019.

Conclusions:

This study will determine if use of a digital platform for determining a collective intelligence is acceptable, useful, and efficacious in improving diagnostic confidence and accuracy in outpatient cases with diagnostic uncertainty. If shown to be valuable in improving clinicians’ diagnostic process, this type of digital tool may be one of the first innovations for reducing diagnostic errors in outpatient care. The findings of this study may provide a path forward for improving the diagnosis process.