June 2020: Dutch paper on implementation of AI in radiology
European Radiology features an article from Utrecht UMC, investigating the adoption of BoneXpert and other AI methods in radiology in the Netherlands
The article Implementation of artificial intelligence (AI) applications in radiology: hindering and facilitating factors is authored by four researchers from Utrecht University Medical Center, plus Erik Ranschaert.
The study set out to interview radiologists who have implemented AI, and the authors noted:
“BoneXpert is one of the first commercial applications of AI in radiology and appeared to be the only AI application in clinical use across several hospitals in The Netherlands”
Therefore, the study interviewed 24 persons from seven hospitals, all using BoneXpert. The study seeked to identify the factors, that facilitate the adoption of AI, and the following four were mentioned most often (by 58-75% of the interviewed users):
- Expected added benefit wrt improved diagnostic practice (more precise and objective diagnoses, avoidance of mistakes, and the automation of cumbersome tasks)
- Expected added benefit wrt operational benefits (diminishing workloads, time-saving, more consistent reporting across radiologists, and advanced service availability)
- Easy integration in PACS
- Minimal workflow changes
Specifically, it is reported that:
“The interviewed users experienced the integration of BoneXpert into the PACS as very smooth, being the main reason for its perceived user-friendliness”