JMIR Publications

ABSTRACT

Background:

Clinical decision-making is a complex cognitive process that relies on the interpretation of a large variety of data from different sources and involves using knowledge bases and scientific recommendations. The representation of clinical data plays a key role in the speed and efficiency of its interpretation. As well, the increasing use of clinical decision support systems (CDSS) provides assistance to clinicians in their practice, allowing them to improve patient outcomes. In the pediatric intensive care unit (PICU), clinicians must process high data volumes and deal with ever-growing workloads. Without optimal data structuring, the clinicians’ cognitive processes and clinical decision-making are hindered by these challenges.

Objective:

In this study, we optimized the representation of clinical data via a structure that supports the integration of CDSS based on an analysis of end-user needs and their clinical workflow.

Methods:

We first observed clinical activities in a PICU to secure a better understanding of the workflow, before conducting interviews with 11 participants from different staff categories (intensivists, fellows, nurses, and nurse practitioners) to put together their decision support needs. After completing the interviews, we structured the data to design a prototype that illustrates the proposed representation. Design meetings were held with 5 participants to present, revise, and adapt the designed prototype to meet their needs.

Results:

We created a 3-level structure to optimize data representation in response to the clinicians’ needs. Subsequently, we designed a prototype based on this structure.

Conclusions:

The data representation structure allows for prioritizing patients, assessing their conditions, and monitoring their courses. Further work is required to define and model the concepts of criticality, problem recognition and evolution.