Graphical Presentations of Clinical Data in a Learning Electronic Medical Record

Abstract

Background: Complex electronic medical records (EMRs) presenting large amounts of data create risks of cognitive overload. We are designing a Learning EMR (LEMR) system that utilizes models of intensive care unit (ICU) physicians' data access patterns to identify and then highlight the most relevant data for each patient.

Objectives: We used insights from literature and feedback from potential users to inform the design of an EMR display capable of highlighting relevant information.

Methods: We used a review of relevant literature to guide the design of preliminary paper prototypes of the LEMR user interface. We observed five ICU physicians using their current EMR systems in preparation for morning rounds. Participants were interviewed and asked to explain their interactions and challenges with the EMR systems. Findings informed the revision of our prototypes. Finally, we conducted a focus group with five ICU physicians to elicit feedback on our designs and to generate ideas for our final prototypes using participatory design methods.

Results: Participating physicians expressed support for the LEMR system. Identified design requirements included the display of data essential for every patient together with diagnosis-specific data and new or significantly changed information. Respondents expressed preferences for fishbones to organize labs, mouseovers to access additional details, and unobtrusive alerts minimizing color-coding. To address the concern about possible physician overreliance on highlighting, participants suggested that non-highlighted data should remain accessible. Study findings led to revised prototypes, which will inform the development of a functional user interface.

Conclusion: In the feedback we received, physicians supported pursuing the concept of a LEMR system. By introducing novel ways to support physicians' cognitive abilities, such a system has the potential to enhance physician EMR use and lead to better patient outcomes. Future plans include laboratory studies of both the utility of the proposed designs on decision-making, and the possible impact of any automation bias.

Fig. 1

Study workflow. A non-systematic qualitative evidence synthesis provided insights on design principles applicable to a LEMR system, which inspired the creation of preliminary paper prototypes. To gain an understanding of information needs and practices in ICUs, we interviewed ICU physicians and observed their interactions with the current EMR system. A focus group of ICU physicians generated design ideas for the LEMR system and provided feedback on the concept and our prototypes, leading to the creation of a final series of prototypes, which will inform LEMR display development. ICU, intensive care unit; LEMR, Learning Electronic Medical Record.

Fig. 2

Non-systematic qualitative evidence synthesis flow diagram. A non-systematic qualitative evidence synthesis provided insights on design principles applicable to a learning electronic medical record system designed for ICU care.

Fig. 3

One of four preliminary paper prototypes: use of Midgaard's semantic zoom to summarize clinical information, displaying a greater number of parameters at once. As displayed in the yellow box on the right (which was superimposed on the prototype for illustrative purposes and did not represent an actual component of the Learning Electronic Medical Record user interface), Midgaard's semantic zoom technique allows to visualize variables at levels of detail that vary with the zoom level.

Fig. 4

One of four revised prototypes, showing how the Learning Electronic Medical Record interface might prioritize the display of ( 1 ) new information and ( 2 ) high-value patient data in dedicated panels that support analytical reasoning by ( 3 ) grouping related data, ( 4 ) highlighting changes and ( 5 ) trends, ( 6 ) providing unobtrusive alerts, and ( 7 ) augmenting clinical notes with links to related data items. For each parameter, the green color is used in the graphs to identify in-range values, while red and blue indicate values above or below the normal range, respectively.

Fig. 5

One of two proposed electronic medical record home screen designs. Relevant data pertinent to the patient's specific diagnoses, ( F ) newly available and ( D ) significantly changed information, and ( C , E ) unobtrusive alerts are displayed in a dedicated “highlighted data” box at the top of the screen ( B ). Static boxes display ( A , G , I , K , M – U ) information important for every patient. Mouseovers or right-clicks on data items provide access to additional information. Blue indicators identify newly available data, while red indicators are used for alerts.

Fig. 6

A combination of information essential for every patient, diagnosis-specific patient data, significant changes and trends, and select newly available information is predicted by the LEMR system to be of high-value, and displayed in a prioritized way in the LEMR interface by utilizing static and dynamic screen components. LEMR, Learning Electronic Medical Record.