JMIR Publications

ABSTRACT

Background:

EHR data that come from multiple providers often exhibit important, but convoluted and complex patterns that patients find hard and time consuming to identify and interpret. However, existing patient-facing applications lack the capability to incorporate such automatic pattern detection robustly and towards supporting making sense of the patient’s EHR data. On top of this, there is no means to organize the EHR data in an efficient way that suits the patient’s needs and makes them more actionable in real-life settings. These shortcomings often result in skewed and incomplete picture of the patient’s health status, thus may lead to suboptimal decision making and actions that put the patient at risk.

Objective:

Our main goal was to investigate the patients’ attitudes, needs and utilization scenarios with respect to automatic support for surfacing important patterns in their EHR data and providing means for organizing their EHR data that best suits their needs.

Methods:

We conducted a qualitative user-centered design study with 14 participants. Presented in the context of a cutting-edge application with strong emphasis on independent EHR data sensemaking, called Discovery, we used high-level mockups for the new features that were supposed to support: a) automatic identification of important data patterns and offer recommendations - Alerts, and b) means for organizing the medical records based on patient’s needs, much like photos in albums - Collections. The combined audio-recordings transcripts and in-study notes were thematically analyzed using the open-coding approach.

Results:

The Alerts and Collections can be used for raising awareness, reflection, planning, and especially evidence-based patient-provider communication. Also, the patients desired carefully designed automatic pattern detection with safe and actionable recommendations, which produces a well-tailored and scoped landscape of Alerts for both potential threats and positive progress. Further, patients wanted to contribute their own data: progress notes, and log feelings, daily observations and measurements; to enrich the meaning and enable easier sensemaking of the Alerts and Collections. Based on the findings, we rename the Alerts to Reports for more neutral tone and offer design implications for: a) deeper contextualization of the Reports for increased actionability, and automatic generation of the Collections for more expedite and exhaustive organization of the EHR data, b) enabling Patient Generated Data (PGD) input in various formats to support coarser organization, richer pattern detection and learning from experience, and c) utilizing the Reports and the Collections for efficient, reliable and common-ground patient-provider communication.

Conclusions:

Patients need to have a flexible and rich way to organize and annotate their EHR data, get introduced to insights from those data - both positive and negative, and share these artifacts with their physicians in clinical visits or via messaging for establishing shared mental models for clear goals, agreed-upon priorities and feasible actions.