Related Experiment Video
Updated: Jun 15, 2025

Interactive and Visualized Online Experimentation System for Engineering Education and Research
Published on: November 24, 2021
User-Centered Development of Explanation User Interfaces for AI-Based CDSS: Lessons Learned from Early Phases.
Ian-C Jung1, Maria Zerlik1, Katharina Schuler1
1Institute for Medical Informatics and Biometry, Faculty of Medicine Carl Gustav Carus, Technical University Dresden, Germany.
Physicians' explanation needs for AI clinical decision support systems varied significantly based on how they were identified. Early context analysis differed from later questionnaire responses, emphasizing careful user-centered design.
Area of Science:
- Medical Informatics
- Human-Computer Interaction
- Artificial Intelligence in Healthcare
Background:
- User-centered design (UCD) is crucial for developing effective AI-based clinical decision support systems (AI-CDSS).
- Understanding physician explanation needs is vital for the adoption and safe use of AI-CDSS in intensive care units (ICUs).
Purpose of the Study:
- To report lessons learned from the early UCD phases of an explanation user interface for an AI-CDSS in the ICU.
- To identify and verify physician explanation needs in a multi-center, multi-country project.
Main Methods:
- Context analysis and user requirements prioritization in an initial center.
- Questionnaire responses from N=9 physicians after a multi-center project workshop.
Main Results:
- Explanation needs identified via context analysis differed from those identified via questionnaires.
- Physician explanation needs varied depending on the elicitation method and project phase.
Conclusions:
- Caution is advised when eliciting explanation needs during the UCD process for AI-CDSS.
- Multi-center, multi-country projects require robust methods to capture diverse user needs accurately.
Related Concept Videos
Introduction to Cognitive Psychology
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...
Stereotype Content Model
Machines: Problem Solving II
Machines: Problem Solving I
The toggle clamp system is a machine structure consisting of movable, pin-connected multi-force members that form a stabilized system to transmit forces. The...
Deductive Reasoning
For example, a researcher can deduce specific predictions...
Non-equilibrium in the Cell

