Data Representation Structure to Support Clinical Decision-Making in the Pediatric Intensive Care Unit: Interview...

Area of Science:

• Clinical Informatics
• Human-Computer Interaction
• Pediatric Critical Care Medicine

Background:

• Clinical decision-making relies on interpreting diverse data, with data representation impacting efficiency.
• Clinical decision support systems (CDSSs) aid clinicians, but high data volumes in PICUs pose challenges.
• Current data structures and visualizations hinder cognitive processes and decision-making in pediatric intensive care units (PICUs).

Purpose of the Study:

• To design a prototype optimizing clinical data representation from various sources for PICU CDSS integration.
• To analyze end-user needs and clinical workflows to inform the data structure design.

Main Methods:

• Observed clinical activities and staff workflows in a PICU.
• Conducted interviews with 11 clinicians to identify decision support needs.
• Structured data and designed a prototype, validating with a brain injury scenario and clinician feedback.

Main Results:

• Developed a 3-level data structure (unit, patient, system) for optimized representation and CDSS hosting.
• Created a preliminary prototype based on the new data structure.
• The structure facilitates patient prioritization, personalized assessment, and monitoring of clinical values.

Conclusions:

• The new data representation structure enhances patient prioritization, assessment, and monitoring in the PICU.
• Further research is needed to model criticality, problem recognition, and evolution.
• Feasibility testing is planned to ensure user satisfaction with the prototype.