THIS CONTENT IS BROUGHT TO YOU BY the Norwegian centre for E-health research - read more

With the new solution, the X-ray images taken at the hospital will be sent to a cloud service

Artificial intelligence makes it easier and cheaper for doctors to diagnose patients

Annually, around 250,000 women in Norway are screened for breast cancer, which captures a standard set of four images per woman. This translates to a substantial dataset of 1 million images each year.

Hasse Berntsen
COMMUNICATIONS ADVISER
Presented by: Norwegian centre for E-health research
Published

The use of artificial intelligence will contribute to even better diagnostic imaging for patients. The Norwegian Centre for E-health Research is conducting follow-up research on the project.

The goal is to improve the healthcare service and free radiologist resources, enabling them to allocate more time to advanced examinations, where time can be more crucial for patients.

Using artificial intelligence (AI) for this purpose can improve healthcare for half the population of Norway within a short time.

“We aim for AI to enhance the daily work experience for our radiologists by assisting them in managing the substantial volume of diagnostics and offering valuable professional support. While AI may not address all the challenges, it will undoubtedly make a significant contribution,” Jon Haakon Malmer-Høvik says.

He is head of the Department of Diagnostic Imaging at Vestre Viken Hospital Trust.

Head of the Department of Diagnostic Imaging at Vestre Viken Hospital Trust, Jon Haakon Malmer-Høvik

Enhances quality and efficiency

With the new AI solution, X-ray images captured at the hospital will be transmitted to a cloud-based service. 

Within this system, algorithms analyse the images, and the AI-generated responses are then returned to an image storage system.

This process aims to enhance the quality and efficiency of patient pathways and the radiologists' workflow.

The scheme is platform-based and offers the algorithms radiologists need. A kind of app store for CE labelled algorithms.

Researchers need to get involved early

While the healthcare sector should embrace AI utilisation, there is a pressing need for research to explore both the opportunities and challenges presented by the medical application of artificial intelligence.

Senior researcher Line Silsand in the Department for Patient Pathways at the Norwegian Centre for E-health Research.

Researchers from the Norwegian Centre for E-health Research have been engaged in the project from its inception and are currently conducting ongoing follow-up research. This involves closely monitoring the implementation of artificial intelligence in the Department of Diagnostic Imaging at Vestre Viken Hospital Trust over an extended period.

“We are currently collaborating with the Norwegian Directorate of Health and Vestre Viken on a follow-up research project that explores the prerequisites for the effective implementation of artificial intelligence,” Line Silsand says. 

She is a researcher in the Department for Patient Pathways at the Norwegian Centre for E-health Research.

“We are evaluating aspects of procurement, implementation, and the associated benefits, and we will provide ongoing updates to the project team to facilitate adjustments as needed,” she says.

Expectations and challenges

Artificial intelligence in radiology holds the promise of efficiently managing the growing influx of imaging examinations.

However, the adoption of AI introduces fresh challenges concerning ICT security, data quality, privacy, ethics, and organisational dynamics.

“Artificial intelligence holds the potential to facilitate early disease detection, thereby enhancing patient survival rates. It also plays a crucial role in optimising patient prioritisation, ensuring timely and appropriate healthcare delivery," Silsand says.

However, she adds, to deploy AI technologies safely and effectively, it's crucial to conduct research into the clinical application processes. This will help the researchers understand the prerequisites for the successful incorporation of AI.

Major savings

Annually, the Norwegian Breast Cancer Screening Programme screens around 250,000 women, capturing a standard set of four images per woman. This translates to a substantial dataset of 1 million images each year.

Solveig Hofvind, Head of the Breast Cancer Screening Programme at the Cancer Registry of Norway.

Currently, two radiologists independently interpret these images.

If artificial intelligence could effectively select half of these, it would represent a substantial relief for radiologists.

“We're currently facing a significant shortage of breast radiologists, and our objective is to optimise their time through the integration of AI. In addition to improving screening examination sensitivity, we aim to achieve long-term cost-effectiveness," Solveig Hofvind says.

She is head of the Breast Cancer Screening Programme at the Cancer Registry of Norway.

"To realise this goal, we are dedicated to developing and testing both proprietary and CE-marked algorithms within the Screening Programme to identify and implement the most effective solutions,” she says.

Video about radiologists and artificial intelligence

Artificial intelligence is being trialled as a work tool for radiologists. 

Vestre Viken Hospital Trust and the Cancer Registry of Norway talk about their expectations and what they want to achieve by utilising artificial intelligence. 

The video below was produced as part of the project Better use of artificial intelligence in the Norwegian specialist health services at the Norwegian Centre for E-health Research.

Link to video here.

More content from the Norwegian centre for E-health research:

e-health-research informasjonsteknologi kunstig intelligens medisinske metoder teknologi big data partner
Powered by Labrador CMS