Related Experiment Video
Updated: Jul 4, 2025
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
849
Radiologists' perspectives on the workflow integration of an artificial intelligence-based computer-aided detection
Katharina Wenderott1, Jim Krups1, Julian A Luetkens2
1Institute for Patient Safety, University Hospital Bonn, Venusberg-Campus 1, 53127, Bonn, Germany.
Applied Ergonomics
|February 2, 2024
Summary
Implementing artificial intelligence computer-aided detection (AI-CAD) in healthcare requires a holistic approach. Successful adoption depends on addressing workflow barriers like time delays and unstable performance, while leveraging facilitators such as good usability and self-organization.
Area of Science:
- Medical Imaging
- Health Informatics
- Radiology
Background:
- Artificial intelligence (AI) shows promise for improving healthcare work processes.
- Current research often overlooks real-world clinical implementation challenges of AI.
- Understanding AI's impact on clinical workflows is crucial for successful adoption.
Purpose of the Study:
- To evaluate the implementation process of an AI-based computer-aided detection (AI-CAD) system for prostate MRI.
- To identify workflow effects, facilitators, and barriers associated with AI-CAD implementation in radiology.
Main Methods:
- A pre-post study design involving interviews with German radiologists.
- Utilized the Model of Workflow Integration and the Technology Acceptance Model for analysis.
Main Results:
- Key barriers included time delays, additional work steps, and unstable AI-CAD performance.
- Facilitators identified were good self-organization and software usability.
- The study highlights the sociotechnical aspects of AI implementation.
Conclusions:
- A holistic approach considering the sociotechnical work system is vital for AI implementation in healthcare.
- Addressing identified barriers and leveraging facilitators are key to successful AI adoption in clinical settings.
- Insights gained can inform future AI integration strategies in medical imaging.
